From d7c4467d4437516fdd367fc17fc50942b3848763 Mon Sep 17 00:00:00 2001 From: "docling-java-ops[bot]" <245010719+docling-java-ops[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 04:40:32 +0000 Subject: [PATCH] docs: Update docling-serve compatibility table (from Version tests run # 74) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- .../docling-serve/serve-compatibility.md | 5502 +++++++++-------- 1 file changed, 2911 insertions(+), 2591 deletions(-) diff --git a/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md b/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md index b15ad876..4444837f 100644 --- a/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md +++ b/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md @@ -1,9 +1,11 @@ -# Results for ghcr.io/docling-project/docling-serve as of 2026-10-19T04:57:13.999045549Z +# Results for ghcr.io/docling-project/docling-serve as of 2026-10-26T04:40:28.814996565Z Here are the results: | Tag | Result | Details | | --- | ------ | ------- | +| v1.38.1 | ✅ SUCCESS | [Click for run details](#v1.38.1-details) | +| v1.38.0 | ✅ SUCCESS | [Click for run details](#v1.38.0-details) | | v1.37.0 | ✅ SUCCESS | [Click for run details](#v1.37.0-details) | | v1.36.0 | ✅ SUCCESS | [Click for run details](#v1.36.0-details) | | v1.35.0 | ✅ SUCCESS | [Click for run details](#v1.35.0-details) | @@ -58,6 +60,324 @@ Here are the results: ## Details +### ghcr.io/docling-project/docling-serve:v1.38.1 + +
+Click to expand + +#### Message + +
+Click to collapse + +~~~markdown +Tag v1.38.1 is ok +~~~ + +
+ + +#### Docling server logs + +
+click to expand + +``` +Starting production server 🚀 + +Server started at http://0.0.0.0:5001 +Documentation at http://0.0.0.0:5001/docs +Scalar docs at http://0.0.0.0:5001/scalar + +Logs: +INFO: 04:40:07 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:40:07 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:40:07 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:40:07 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:40:07 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:40:07 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/readyz$,/healthz$,/livez$,/metrics$,/ready$) +INFO: 04:40:07 - uvicorn.error - Started server process [1] +INFO: 04:40:07 - uvicorn.error - Waiting for application startup. +INFO: 04:40:07 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:40:08 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:40:08 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:40:08 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:40:08 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:40:08 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 075f230fac5aebc745d88ef3fbda9018 +INFO: 04:40:08 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:40:08 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:40:08 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:40:08.464773599 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:40:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:40:08 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:40:08 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:40:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:40:10 - docling.document_converter - Going to convert document batch... +INFO: 04:40:10 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 2d2bc2649b3c11d3a30957f32a9ad221 +INFO: 04:40:10 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:40:10 - docling.document_converter - Finished converting document file in 0.42 sec. +/opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice + np.nanmean( +/opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered + return _nanquantile_unchecked( +INFO: 04:40:10 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 04:40:10 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 6332eae1-60f0-4b74-aad3-bfc7bd2d5922 in 0.46 seconds +INFO: 04:40:11 - uvicorn.access - 172.17.0.1:35638 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:40:11 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:40:11 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:40:11 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:40:11 - docling_serve.app - [TENANT_ID] Task 7beeb51f-ae13-4a93-8133-54e1f3f5f352 created with tenant_id='default' +INFO: 04:40:11 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 7beeb51f-ae13-4a93-8133-54e1f3f5f352 +INFO: 04:40:11 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:40:12 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 2d2bc2649b3c11d3a30957f32a9ad221 +INFO: 04:40:12 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:40:12 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:40:12 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:40:12 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:40:12 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:40:13 - docling.document_converter - Going to convert document batch... +INFO: 04:40:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 2d2bc2649b3c11d3a30957f32a9ad221 +INFO: 04:40:13 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:40:13 - docling.document_converter - Finished converting document file in 0.39 sec. +/opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice + np.nanmean( +/opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered + return _nanquantile_unchecked( +INFO: 04:40:13 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:40:13 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 7beeb51f-ae13-4a93-8133-54e1f3f5f352 in 0.39 seconds +INFO: 04:40:13 - uvicorn.access - 172.17.0.1:35638 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:40:13 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:40:13 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:40:13 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:40:13 - docling_serve.app - [TENANT_ID] Task bb328a87-d3e5-415e-b8ff-cefec27364d4 created with tenant_id='default' +INFO: 04:40:13 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task bb328a87-d3e5-415e-b8ff-cefec27364d4 +INFO: 04:40:13 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:40:14 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6818f1c9e7117ed09accacfe8b15928f +INFO: 04:40:14 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:40:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:40:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:40:14 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:40:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:40:14 - docling.document_converter - Going to convert document batch... +INFO: 04:40:14 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6818f1c9e7117ed09accacfe8b15928f +INFO: 04:40:14 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:40:14 - docling.document_converter - Finished converting document file in 0.40 sec. +/opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice + np.nanmean( +/opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered + return _nanquantile_unchecked( +INFO: 04:40:14 - docling_jobkit.convert.results - Processed 1 docs in 0.42 seconds. +INFO: 04:40:14 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job bb328a87-d3e5-415e-b8ff-cefec27364d4 in 0.42 seconds +INFO: 04:40:15 - uvicorn.access - 172.17.0.1:35638 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:40:16 - uvicorn.access - 172.17.0.1:35638 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:40:16 - uvicorn.access - 172.17.0.1:35638 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 + +``` + +
+ +
+ +### ghcr.io/docling-project/docling-serve:v1.38.0 + +
+Click to expand + +#### Message + +
+Click to collapse + +~~~markdown +Tag v1.38.0 is ok +~~~ + +
+ + +#### Docling server logs + +
+click to expand + +``` +Starting production server 🚀 + +Server started at http://0.0.0.0:5001 +Documentation at http://0.0.0.0:5001/docs +Scalar docs at http://0.0.0.0:5001/scalar + +Logs: +INFO: 04:38:47 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:47 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:38:47 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:38:47 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:38:47 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:38:47 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/readyz$,/healthz$,/ready$,/health$) +INFO: 04:38:47 - uvicorn.error - Started server process [1] +INFO: 04:38:47 - uvicorn.error - Waiting for application startup. +INFO: 04:38:47 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:48 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:38:48 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:48 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:38:48 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:48 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5ceafb4991c7490e0b7efdf717df2e9e +INFO: 04:38:48 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:48 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:38:48 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:38:48.768777748 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:38:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:38:49 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:49 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:51 - docling.document_converter - Going to convert document batch... +INFO: 04:38:51 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash f4d135977c7be9de4714a34145c6c2db +INFO: 04:38:51 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:51 - docling.document_converter - Finished converting document file in 0.48 sec. +/opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice + np.nanmean( +/opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered + return _nanquantile_unchecked( +INFO: 04:38:51 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. +INFO: 04:38:51 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job d99c52ee-e60b-4894-b67e-04c0626d9468 in 0.52 seconds +INFO: 04:38:52 - uvicorn.access - 172.17.0.1:51668 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:52 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:38:52 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:38:52 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:38:52 - docling_serve.app - [TENANT_ID] Task 0d7e958d-89df-47e5-81fb-dee94cf20e0c created with tenant_id='default' +INFO: 04:38:52 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 0d7e958d-89df-47e5-81fb-dee94cf20e0c +INFO: 04:38:52 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:52 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f4d135977c7be9de4714a34145c6c2db +INFO: 04:38:52 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:38:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:38:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:52 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:53 - docling.document_converter - Going to convert document batch... +INFO: 04:38:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash f4d135977c7be9de4714a34145c6c2db +INFO: 04:38:53 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:53 - docling.document_converter - Finished converting document file in 0.41 sec. +/opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice + np.nanmean( +/opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered + return _nanquantile_unchecked( +INFO: 04:38:53 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:38:53 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 0d7e958d-89df-47e5-81fb-dee94cf20e0c in 0.41 seconds +INFO: 04:38:54 - uvicorn.access - 172.17.0.1:51668 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:54 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:38:54 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:38:54 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:38:54 - docling_serve.app - [TENANT_ID] Task 77336d0f-3752-4096-bcbf-730c897724ab created with tenant_id='default' +INFO: 04:38:54 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 77336d0f-3752-4096-bcbf-730c897724ab +INFO: 04:38:54 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:54 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1ab46a2f2f5e101645d512a318f1f0e4 +INFO: 04:38:54 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:38:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:38:54 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:54 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:55 - docling.document_converter - Going to convert document batch... +INFO: 04:38:55 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 1ab46a2f2f5e101645d512a318f1f0e4 +INFO: 04:38:55 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:55 - docling.document_converter - Finished converting document file in 0.52 sec. +/opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice + np.nanmean( +/opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered + return _nanquantile_unchecked( +INFO: 04:38:55 - docling_jobkit.convert.results - Processed 1 docs in 0.54 seconds. +INFO: 04:38:55 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 77336d0f-3752-4096-bcbf-730c897724ab in 0.54 seconds +INFO: 04:38:56 - uvicorn.access - 172.17.0.1:51668 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:56 - uvicorn.access - 172.17.0.1:51668 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:38:56 - uvicorn.access - 172.17.0.1:51668 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 + +``` + +
+ +
+ ### ghcr.io/docling-project/docling-serve:v1.37.0
@@ -88,128 +408,128 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:56:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:56:52 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:56:52 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:56:52 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:56:52 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:56:52 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/healthz$,/readyz$,/ready$,/metrics$,/livez$) -INFO: 04:56:52 - uvicorn.error - Started server process [1] -INFO: 04:56:52 - uvicorn.error - Waiting for application startup. -INFO: 04:56:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:56:55 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:56:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:56:55 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:56:55 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:56:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b7c97d300ed2fcdc7261aa1781c865c1 -INFO: 04:56:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:56:56 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:56:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:56:56.112074872 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:56:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:56:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:56:56 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:56:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:56:59 - docling.document_converter - Going to convert document batch... -INFO: 04:56:59 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 403b8a679c64c10008a36e608e210292 -INFO: 04:56:59 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:56:59 - docling.document_converter - Finished converting document file in 0.67 sec. +INFO: 04:37:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:37:34 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:37:34 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:37:34 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:37:34 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:37:34 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/healthz$,/livez$,/metrics$,/health$,/readyz$) +INFO: 04:37:34 - uvicorn.error - Started server process [1] +INFO: 04:37:34 - uvicorn.error - Waiting for application startup. +INFO: 04:37:36 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:37:37 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:37:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:37:37 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:37:37 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:37:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6fd839ac611c9db52927dbffc3739297 +INFO: 04:37:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:37:37 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:37:37 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:37:37.284936142 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:37:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:37:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:37:37 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:37:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:37:39 - docling.document_converter - Going to convert document batch... +INFO: 04:37:39 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 898c26974c29f1a8aa3dc05214235bb1 +INFO: 04:37:39 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:37:39 - docling.document_converter - Finished converting document file in 0.37 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:681: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:56:59 - docling_jobkit.convert.results - Processed 1 docs in 0.74 seconds. -INFO: 04:56:59 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 088c2530-5fba-4cd8-aa28-0212ddd37668 in 0.74 seconds -INFO: 04:57:00 - uvicorn.access - 172.17.0.1:56138 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:57:00 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:57:00 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:57:00 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:57:00 - docling_serve.app - [TENANT_ID] Task f0cee892-2530-4b43-af8b-89bd9f5f696d created with tenant_id='default' -INFO: 04:57:00 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task f0cee892-2530-4b43-af8b-89bd9f5f696d -INFO: 04:57:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:57:00 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 403b8a679c64c10008a36e608e210292 -INFO: 04:57:00 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:57:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:57:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:57:00 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:57:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:57:01 - docling.document_converter - Going to convert document batch... -INFO: 04:57:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 403b8a679c64c10008a36e608e210292 -INFO: 04:57:01 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:57:01 - docling.document_converter - Finished converting document file in 0.64 sec. +INFO: 04:37:39 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:37:39 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f66b37c0-43a7-4161-b205-6434bb2eae50 in 0.41 seconds +INFO: 04:37:40 - uvicorn.access - 172.17.0.1:38388 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:37:40 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:37:40 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:37:40 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:37:40 - docling_serve.app - [TENANT_ID] Task d9d143aa-98d7-4894-9f0a-3e0dda3111eb created with tenant_id='default' +INFO: 04:37:40 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task d9d143aa-98d7-4894-9f0a-3e0dda3111eb +INFO: 04:37:40 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:37:40 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 898c26974c29f1a8aa3dc05214235bb1 +INFO: 04:37:40 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:37:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:37:40 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:37:40 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:37:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:37:41 - docling.document_converter - Going to convert document batch... +INFO: 04:37:41 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 898c26974c29f1a8aa3dc05214235bb1 +INFO: 04:37:41 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:37:41 - docling.document_converter - Finished converting document file in 0.40 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:681: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:57:01 - docling_jobkit.convert.results - Processed 1 docs in 0.65 seconds. -INFO: 04:57:01 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job f0cee892-2530-4b43-af8b-89bd9f5f696d in 0.65 seconds -INFO: 04:57:02 - uvicorn.access - 172.17.0.1:56138 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:57:02 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:57:02 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:57:02 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:57:02 - docling_serve.app - [TENANT_ID] Task c698dc4f-b72a-41cd-9b43-a717847b5dcf created with tenant_id='default' -INFO: 04:57:02 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task c698dc4f-b72a-41cd-9b43-a717847b5dcf -INFO: 04:57:02 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:57:02 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash cea7d05b1524033a4df86987baef949c -INFO: 04:57:02 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:57:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:57:02 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:57:02 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:57:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:57:03 - docling.document_converter - Going to convert document batch... -INFO: 04:57:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash cea7d05b1524033a4df86987baef949c -INFO: 04:57:03 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:57:03 - docling.document_converter - Finished converting document file in 0.48 sec. +INFO: 04:37:41 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. +INFO: 04:37:41 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job d9d143aa-98d7-4894-9f0a-3e0dda3111eb in 0.40 seconds +INFO: 04:37:42 - uvicorn.access - 172.17.0.1:38388 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:37:42 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:37:42 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:37:42 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:37:42 - docling_serve.app - [TENANT_ID] Task 896b50da-6dfa-4b79-8436-0db279b3400e created with tenant_id='default' +INFO: 04:37:42 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 896b50da-6dfa-4b79-8436-0db279b3400e +INFO: 04:37:42 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:37:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6751db9cc2bed0ebd01688c71d799129 +INFO: 04:37:43 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:37:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:37:43 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:37:43 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:37:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:37:44 - docling.document_converter - Going to convert document batch... +INFO: 04:37:44 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6751db9cc2bed0ebd01688c71d799129 +INFO: 04:37:44 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:37:44 - docling.document_converter - Finished converting document file in 0.41 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:681: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:57:03 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 04:57:03 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c698dc4f-b72a-41cd-9b43-a717847b5dcf in 0.52 seconds -INFO: 04:57:04 - uvicorn.access - 172.17.0.1:56138 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:57:04 - uvicorn.access - 172.17.0.1:56138 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:57:04 - uvicorn.access - 172.17.0.1:56138 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:37:44 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:37:44 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 896b50da-6dfa-4b79-8436-0db279b3400e in 0.43 seconds +INFO: 04:37:44 - uvicorn.access - 172.17.0.1:38388 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:37:45 - uvicorn.access - 172.17.0.1:38388 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:37:45 - uvicorn.access - 172.17.0.1:38388 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -247,152 +567,152 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:55:22 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:55:22 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:55:22 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:55:23 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:55:23 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:55:23 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/ready$,/metrics$,/livez$,/health$,/readyz$) -INFO: 04:55:23 - uvicorn.error - Started server process [1] -INFO: 04:55:23 - uvicorn.error - Waiting for application startup. -INFO: 04:55:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:55:26 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:55:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:55:26 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:55:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:55:27 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash efdd46b5a86adf601464fb018044639e -INFO: 04:55:27 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:55:27 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:55:27 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:55:27.046312248 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:55:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:55:27,293 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:27,294 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:55:27,355 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:27,355 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:55:27,415 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:27,415 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:55:27 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:55:27 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:55:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:55:30 - docling.document_converter - Going to convert document batch... -INFO: 04:55:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 75ca4cb6076463e98d454ff45a644929 -INFO: 04:55:30 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:55:30 - docling.document_converter - Finished converting document file in 0.54 sec. +INFO: 04:35:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:35:55 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:35:55 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:35:56 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:35:56 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:35:56 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/healthz$,/ready$,/metrics$,/health$,/readyz$) +INFO: 04:35:56 - uvicorn.error - Started server process [1] +INFO: 04:35:56 - uvicorn.error - Waiting for application startup. +INFO: 04:35:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:35:58 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:35:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:35:58 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:35:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:35:58 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 18ae58bcb4fe6b42a6340fe46841d95c +INFO: 04:35:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:35:58 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:35:58 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:35:58.619908044 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:35:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:35:58,751 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:35:58,751 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:35:58,782 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:35:58,782 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:35:58,812 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:35:58,812 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:35:58 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:35:58 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:35:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:36:01 - docling.document_converter - Going to convert document batch... +INFO: 04:36:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash cfd5fb9acb196e0ba819ddef8d92ca9f +INFO: 04:36:01 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:36:01 - docling.document_converter - Finished converting document file in 0.44 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:675: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:55:31 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. -INFO: 04:55:31 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 41f89b3d-59af-4ac8-be18-c41a656011cc in 0.64 seconds -INFO: 04:55:31 - uvicorn.access - 172.17.0.1:45918 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:55:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:55:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:55:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:55:31 - docling_serve.app - [TENANT_ID] Task b1048c54-f888-4157-929e-273fbc655946 created with tenant_id='default' -INFO: 04:55:31 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b1048c54-f888-4157-929e-273fbc655946 -INFO: 04:55:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:55:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 75ca4cb6076463e98d454ff45a644929 -INFO: 04:55:31 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:55:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:55:31,480 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:31,480 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:55:31,535 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:31,535 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:55:31,581 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:31,581 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:55:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:55:31 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:55:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:55:32 - docling.document_converter - Going to convert document batch... -INFO: 04:55:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 75ca4cb6076463e98d454ff45a644929 -INFO: 04:55:32 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:55:32 - docling.document_converter - Finished converting document file in 0.50 sec. +INFO: 04:36:01 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. +INFO: 04:36:01 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 90dbb386-2732-4800-bc5b-e922a0c079c9 in 0.48 seconds +INFO: 04:36:02 - uvicorn.access - 172.17.0.1:50180 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:36:02 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:36:02 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:36:02 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:36:02 - docling_serve.app - [TENANT_ID] Task dcb149b9-ea95-4f31-b5c9-3bdc30bfad5b created with tenant_id='default' +INFO: 04:36:02 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task dcb149b9-ea95-4f31-b5c9-3bdc30bfad5b +INFO: 04:36:02 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:36:02 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash cfd5fb9acb196e0ba819ddef8d92ca9f +INFO: 04:36:02 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:36:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:36:02,345 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:36:02,345 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:36:02,376 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:36:02,376 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:36:02,398 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:36:02,398 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:36:02 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:36:02 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:36:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:36:03 - docling.document_converter - Going to convert document batch... +INFO: 04:36:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash cfd5fb9acb196e0ba819ddef8d92ca9f +INFO: 04:36:03 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:36:03 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:675: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:55:32 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:55:32 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b1048c54-f888-4157-929e-273fbc655946 in 0.50 seconds -INFO: 04:55:33 - uvicorn.access - 172.17.0.1:45918 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:55:33 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:55:33 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:55:33 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:55:33 - docling_serve.app - [TENANT_ID] Task 63dd63f9-22af-4d3e-8e45-2798b5ddb0ca created with tenant_id='default' -INFO: 04:55:33 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 63dd63f9-22af-4d3e-8e45-2798b5ddb0ca -INFO: 04:55:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:55:33 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1aed49c9ef6d9bb9cf439513841ea298 -INFO: 04:55:33 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:55:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:55:33,474 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:33,475 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:55:33,544 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:33,545 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:55:33,589 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:55:33,589 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:55:33 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:55:33 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:55:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:55:35 - docling.document_converter - Going to convert document batch... -INFO: 04:55:35 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 1aed49c9ef6d9bb9cf439513841ea298 -INFO: 04:55:35 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:55:35 - docling.document_converter - Finished converting document file in 0.53 sec. +INFO: 04:36:03 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:36:03 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job dcb149b9-ea95-4f31-b5c9-3bdc30bfad5b in 0.37 seconds +INFO: 04:36:04 - uvicorn.access - 172.17.0.1:50180 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:36:04 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:36:04 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:36:04 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:36:04 - docling_serve.app - [TENANT_ID] Task 97f46c35-4149-4467-996b-dd0ab1480675 created with tenant_id='default' +INFO: 04:36:04 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 97f46c35-4149-4467-996b-dd0ab1480675 +INFO: 04:36:04 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:36:04 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a6391ced9f20f2b4dcf5aa8f62fbca11 +INFO: 04:36:04 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:36:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:36:04,365 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:36:04,365 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:36:04,393 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:36:04,393 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:36:04,415 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:36:04,415 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:36:04 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:36:04 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:36:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:36:05 - docling.document_converter - Going to convert document batch... +INFO: 04:36:05 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a6391ced9f20f2b4dcf5aa8f62fbca11 +INFO: 04:36:05 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:36:05 - docling.document_converter - Finished converting document file in 0.38 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:675: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:55:35 - docling_jobkit.convert.results - Processed 1 docs in 0.57 seconds. -INFO: 04:55:35 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 63dd63f9-22af-4d3e-8e45-2798b5ddb0ca in 0.57 seconds -INFO: 04:55:37 - uvicorn.access - 172.17.0.1:45918 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:55:37 - uvicorn.access - 172.17.0.1:45918 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:55:37 - uvicorn.access - 172.17.0.1:45918 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:36:05 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:36:05 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 97f46c35-4149-4467-996b-dd0ab1480675 in 0.39 seconds +INFO: 04:36:06 - uvicorn.access - 172.17.0.1:50180 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:36:06 - uvicorn.access - 172.17.0.1:50180 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:36:06 - uvicorn.access - 172.17.0.1:50180 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -430,152 +750,152 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:53:20 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:53:20 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:53:20 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:53:21 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:53:21 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:53:21 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/livez$,/readyz$,/metrics$,/ready$) -INFO: 04:53:21 - uvicorn.error - Started server process [1] -INFO: 04:53:21 - uvicorn.error - Waiting for application startup. -INFO: 04:53:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:53:24 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:53:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:53:24 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:53:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:53:25 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash dfe2431abb6c042b807792dc5d845e78 -INFO: 04:53:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:53:25 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:53:25 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:53:25.107519248 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:53:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:53:25,645 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:25,646 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:53:25,699 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:25,700 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:53:25,749 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:25,749 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:53:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:53:25 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:53:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:53:29 - docling.document_converter - Going to convert document batch... -INFO: 04:53:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash d03cd86a89be52a4e9ef541b21c7abea -INFO: 04:53:29 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:53:29 - docling.document_converter - Finished converting document file in 0.77 sec. +INFO: 04:34:30 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:30 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:34:30 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:34:30 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:34:30 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:34:30 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/metrics$,/ready$,/readyz$,/livez$) +INFO: 04:34:30 - uvicorn.error - Started server process [1] +INFO: 04:34:30 - uvicorn.error - Waiting for application startup. +INFO: 04:34:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:32 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:34:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:32 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:34:32 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:34:32 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 8023b26772976b29c65f0ae4b134cc9e +INFO: 04:34:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:33 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:34:33 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:34:33.049559385 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:34:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:34:33,491 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:33,492 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:34:33,542 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:33,542 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:34:33,566 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:33,566 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:34:33 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:34:33 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:34:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:34:35 - docling.document_converter - Going to convert document batch... +INFO: 04:34:35 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash b4e2195b62e48bb25e75c1b1bcebdfbf +INFO: 04:34:35 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:34:36 - docling.document_converter - Finished converting document file in 0.51 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:53:29 - docling_jobkit.convert.results - Processed 1 docs in 0.86 seconds. -INFO: 04:53:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 324c9760-d159-4d1f-8d86-c4aa01a91b9e in 0.86 seconds -INFO: 04:53:31 - uvicorn.access - 172.17.0.1:58934 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:53:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:53:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:53:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:53:31 - docling_serve.app - [TENANT_ID] Task a96d2410-8241-44e4-b40f-ebc11ad2372f created with tenant_id='default' -INFO: 04:53:31 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task a96d2410-8241-44e4-b40f-ebc11ad2372f -INFO: 04:53:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:53:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash d03cd86a89be52a4e9ef541b21c7abea -INFO: 04:53:31 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:53:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:53:31,503 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:31,503 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:53:31,547 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:31,547 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:53:31,603 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:31,603 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:53:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:53:31 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:53:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:53:33 - docling.document_converter - Going to convert document batch... -INFO: 04:53:33 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash d03cd86a89be52a4e9ef541b21c7abea -INFO: 04:53:33 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:53:33 - docling.document_converter - Finished converting document file in 0.84 sec. +INFO: 04:34:36 - docling_jobkit.convert.results - Processed 1 docs in 0.56 seconds. +INFO: 04:34:36 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job cb2bcee9-c0b6-4085-b176-61f8aaefc08c in 0.56 seconds +INFO: 04:34:36 - uvicorn.access - 172.17.0.1:51200 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:34:36 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:34:36 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:34:36 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:34:36 - docling_serve.app - [TENANT_ID] Task 5b7bf234-b034-4e5c-9427-dd7b678072ee created with tenant_id='default' +INFO: 04:34:36 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5b7bf234-b034-4e5c-9427-dd7b678072ee +INFO: 04:34:36 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:34:36 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b4e2195b62e48bb25e75c1b1bcebdfbf +INFO: 04:34:36 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:34:36 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:34:36,878 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:36,878 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:34:36,912 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:36,912 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:34:36,976 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:36,978 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:34:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:34:37 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:34:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:34:38 - docling.document_converter - Going to convert document batch... +INFO: 04:34:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash b4e2195b62e48bb25e75c1b1bcebdfbf +INFO: 04:34:38 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:34:38 - docling.document_converter - Finished converting document file in 0.70 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:53:33 - docling_jobkit.convert.results - Processed 1 docs in 0.84 seconds. -INFO: 04:53:33 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job a96d2410-8241-44e4-b40f-ebc11ad2372f in 0.84 seconds -INFO: 04:53:35 - uvicorn.access - 172.17.0.1:58934 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:53:35 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:53:35 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:53:35 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:53:35 - docling_serve.app - [TENANT_ID] Task 365f8e4f-abc0-4e37-9d8c-8bacd0b39775 created with tenant_id='default' -INFO: 04:53:35 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 365f8e4f-abc0-4e37-9d8c-8bacd0b39775 -INFO: 04:53:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:53:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash d7830f5dab0a04ba862152aaefa2bab0 -INFO: 04:53:35 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:53:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:53:35,503 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:35,503 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:53:35,552 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:35,552 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:53:35,610 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:53:35,611 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:53:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:53:35 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:53:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:53:36 - docling.document_converter - Going to convert document batch... -INFO: 04:53:36 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash d7830f5dab0a04ba862152aaefa2bab0 -INFO: 04:53:36 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:53:36 - docling.document_converter - Finished converting document file in 0.52 sec. +INFO: 04:34:38 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. +INFO: 04:34:38 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5b7bf234-b034-4e5c-9427-dd7b678072ee in 0.70 seconds +INFO: 04:34:38 - uvicorn.access - 172.17.0.1:51200 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:34:38 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:34:38 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:34:38 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:34:38 - docling_serve.app - [TENANT_ID] Task bbe0a365-dbe8-46fe-a5d8-76147d314fa1 created with tenant_id='default' +INFO: 04:34:38 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task bbe0a365-dbe8-46fe-a5d8-76147d314fa1 +INFO: 04:34:38 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:34:38 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9b5e7d8e31d700cd6cd78fc9a3ab2a0f +INFO: 04:34:38 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:34:38 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:34:38,888 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:38,889 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:34:38,918 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:38,918 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:34:38,985 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:34:38,986 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:34:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:34:39 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:34:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:34:39 - docling.document_converter - Going to convert document batch... +INFO: 04:34:39 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 9b5e7d8e31d700cd6cd78fc9a3ab2a0f +INFO: 04:34:39 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:34:39 - docling.document_converter - Finished converting document file in 0.44 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:53:36 - docling_jobkit.convert.results - Processed 1 docs in 0.56 seconds. -INFO: 04:53:36 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 365f8e4f-abc0-4e37-9d8c-8bacd0b39775 in 0.56 seconds -INFO: 04:53:37 - uvicorn.access - 172.17.0.1:58934 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:53:37 - uvicorn.access - 172.17.0.1:58934 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:53:37 - uvicorn.access - 172.17.0.1:58934 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:34:39 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 04:34:39 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job bbe0a365-dbe8-46fe-a5d8-76147d314fa1 in 0.46 seconds +INFO: 04:34:40 - uvicorn.access - 172.17.0.1:51200 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:34:41 - uvicorn.access - 172.17.0.1:51200 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:34:41 - uvicorn.access - 172.17.0.1:51200 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -613,153 +933,153 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:51:20 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:20 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:51:20 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:51:21 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:51:21 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:51:21 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/metrics$,/healthz$,/ready$,/health$,/livez$) -INFO: 04:51:21 - uvicorn.error - Started server process [1] -INFO: 04:51:21 - uvicorn.error - Waiting for application startup. -INFO: 04:51:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:24 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:51:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:24 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:51:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:51:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b -INFO: 04:51:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:24 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:51:24 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:51:24.803882190 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:51:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:51:25,325 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:25,326 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:51:25,379 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:25,379 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:51:25,420 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:25,420 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:51:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:51:25 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:51:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:51:28 - docling.document_converter - Going to convert document batch... -INFO: 04:51:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:51:28 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:51:28 - docling.document_converter - Finished converting document file in 0.54 sec. +INFO: 04:32:51 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:32:51 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:32:51 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:32:52 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:32:52 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:32:52 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/ready$,/metrics$,/livez$,/healthz$,/readyz$) +INFO: 04:32:52 - uvicorn.error - Started server process [1] +INFO: 04:32:52 - uvicorn.error - Waiting for application startup. +INFO: 04:32:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:32:54 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:32:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:32:54 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:32:54 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:32:55 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b +INFO: 04:32:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:32:55 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:32:55 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:32:55.053975997 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:32:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:32:55,511 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:32:55,513 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:32:55,565 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:32:55,565 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:32:55,587 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:32:55,587 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:32:55 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:32:55 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:32:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:32:57 - docling.document_converter - Going to convert document batch... +INFO: 04:32:57 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:32:57 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:32:57 - docling.document_converter - Finished converting document file in 0.39 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:51:28 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:51:28 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. -INFO: 04:51:28 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f22fb35b-9778-4c46-9bfb-4d531caa3984 in 0.64 seconds -INFO: 04:51:28 - uvicorn.access - 172.17.0.1:49566 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:51:28 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:51:28 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:51:28 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:51:28 - docling_serve.app - [TENANT_ID] Task 84c596cc-9c4a-4ab3-8e20-ab89610227d2 created with tenant_id='default' -INFO: 04:51:28 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 84c596cc-9c4a-4ab3-8e20-ab89610227d2 -INFO: 04:51:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:51:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:51:28 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:51:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:51:28,789 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:28,789 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:51:28,840 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:28,841 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:51:28,892 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:28,892 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:51:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:51:29 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:51:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:51:30 - docling.document_converter - Going to convert document batch... -INFO: 04:51:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:51:30 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:51:30 - docling.document_converter - Finished converting document file in 0.52 sec. +WARNING: 04:32:57 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:32:57 - docling_jobkit.convert.results - Processed 1 docs in 0.42 seconds. +INFO: 04:32:57 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 1517d35c-1cef-4889-b45c-0a6908a80687 in 0.42 seconds +INFO: 04:32:58 - uvicorn.access - 172.17.0.1:35472 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:32:58 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:32:58 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:32:58 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:32:58 - docling_serve.app - [TENANT_ID] Task a9a87813-2936-4d14-984d-92dcf330cf05 created with tenant_id='default' +INFO: 04:32:58 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task a9a87813-2936-4d14-984d-92dcf330cf05 +INFO: 04:32:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:32:58 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:32:58 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:32:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:32:58,331 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:32:58,331 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:32:58,361 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:32:58,361 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:32:58,406 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:32:58,406 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:32:58 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:32:58 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:32:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:32:59 - docling.document_converter - Going to convert document batch... +INFO: 04:32:59 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:32:59 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:32:59 - docling.document_converter - Finished converting document file in 0.25 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:51:30 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 04:51:30 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 84c596cc-9c4a-4ab3-8e20-ab89610227d2 in 0.52 seconds -INFO: 04:51:30 - uvicorn.access - 172.17.0.1:49566 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:51:30 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:51:30 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:51:30 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:51:30 - docling_serve.app - [TENANT_ID] Task c088f6a9-b750-436b-94a0-e2a2b44840f5 created with tenant_id='default' -INFO: 04:51:30 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task c088f6a9-b750-436b-94a0-e2a2b44840f5 -INFO: 04:51:30 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:51:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:51:31 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:51:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:51:31,133 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:31,133 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:51:31,184 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:31,184 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:51:31,249 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:51:31,249 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:51:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:51:31 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:51:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:51:32 - docling.document_converter - Going to convert document batch... -INFO: 04:51:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:51:32 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:51:32 - docling.document_converter - Finished converting document file in 0.73 sec. +INFO: 04:32:59 - docling_jobkit.convert.results - Processed 1 docs in 0.25 seconds. +INFO: 04:32:59 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job a9a87813-2936-4d14-984d-92dcf330cf05 in 0.25 seconds +INFO: 04:33:00 - uvicorn.access - 172.17.0.1:35472 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:33:00 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:33:00 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:33:00 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:33:00 - docling_serve.app - [TENANT_ID] Task 2f178d28-4dbd-4149-9124-8057eabb2d69 created with tenant_id='default' +INFO: 04:33:00 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 2f178d28-4dbd-4149-9124-8057eabb2d69 +INFO: 04:33:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:33:00 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:33:00 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:33:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:33:00,741 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:33:00,741 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:33:00,784 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:33:00,784 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:33:00,812 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:33:00,812 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:33:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:33:00 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:33:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:33:01 - docling.document_converter - Going to convert document batch... +INFO: 04:33:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:33:01 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:33:01 - docling.document_converter - Finished converting document file in 0.39 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:51:32 - docling_jobkit.convert.results - Processed 1 docs in 0.78 seconds. -INFO: 04:51:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c088f6a9-b750-436b-94a0-e2a2b44840f5 in 0.78 seconds -INFO: 04:51:34 - uvicorn.access - 172.17.0.1:49566 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:51:34 - uvicorn.access - 172.17.0.1:49566 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:51:34 - uvicorn.access - 172.17.0.1:49566 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:33:01 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. +INFO: 04:33:01 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2f178d28-4dbd-4149-9124-8057eabb2d69 in 0.40 seconds +INFO: 04:33:02 - uvicorn.access - 172.17.0.1:35472 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:33:02 - uvicorn.access - 172.17.0.1:35472 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:33:02 - uvicorn.access - 172.17.0.1:35472 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -797,151 +1117,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:49:20 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:49:20 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:49:20 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:49:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:49:21 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:49:21 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:49:21 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:49:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:49:21 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:49:21 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:49:21 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:49:21 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/metrics$,/ready$,/healthz$,/readyz$,/health$) -INFO: 04:49:21 - uvicorn.error - Started server process [1] -INFO: 04:49:21 - uvicorn.error - Waiting for application startup. -INFO: 04:49:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:49:24 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:49:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:49:24 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:49:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:49:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b -INFO: 04:49:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:49:24 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:49:24 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:49:24.921457210 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:49:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:49:25,176 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:25,178 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:49:25,231 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:25,231 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:49:25,288 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:25,288 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:49:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:49:25 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:49:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:49:28 - docling.document_converter - Going to convert document batch... -INFO: 04:49:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:49:28 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:49:28 - docling.document_converter - Finished converting document file in 0.52 sec. +INFO: 04:31:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:37 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:31:37 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:31:37 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:31:37 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:31:37 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:31:37 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:31:37 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:31:37 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:31:37 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:31:37 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:31:37 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/metrics$,/ready$,/livez$,/readyz$,/healthz$) +INFO: 04:31:37 - uvicorn.error - Started server process [1] +INFO: 04:31:37 - uvicorn.error - Waiting for application startup. +INFO: 04:31:39 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:40 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:31:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:40 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:31:40 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:40 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b +INFO: 04:31:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:40 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:31:40 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:31:40.326527699 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:31:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:31:40,523 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:40,524 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:31:40,591 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:40,591 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:31:40,627 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:40,627 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:31:40 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:40 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:31:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:43 - docling.document_converter - Going to convert document batch... +INFO: 04:31:43 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:31:43 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:43 - docling.document_converter - Finished converting document file in 0.63 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:655: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:49:28 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:49:28 - docling_jobkit.convert.results - Processed 1 docs in 0.60 seconds. -INFO: 04:49:28 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 07f145bc-411c-487a-84e9-087fcc2974b9 in 0.60 seconds -INFO: 04:49:29 - uvicorn.access - 172.17.0.1:48756 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:49:29 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:49:29 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:49:29 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:49:29 - docling_serve.app - [TENANT_ID] Task a5c66db6-c275-4857-ad05-51f3ceb5d24a created with tenant_id='default' -INFO: 04:49:29 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task a5c66db6-c275-4857-ad05-51f3ceb5d24a -INFO: 04:49:29 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:49:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:49:29 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:49:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:49:29,380 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:29,381 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:49:29,430 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:29,430 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:49:29,480 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:29,480 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:49:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:49:29 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:49:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:49:30 - docling.document_converter - Going to convert document batch... -INFO: 04:49:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:49:30 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:49:30 - docling.document_converter - Finished converting document file in 0.51 sec. +WARNING: 04:31:43 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:31:43 - docling_jobkit.convert.results - Processed 1 docs in 0.67 seconds. +INFO: 04:31:43 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 73b0088e-5642-40bf-83f3-0b3f337aa831 in 0.67 seconds +INFO: 04:31:44 - uvicorn.access - 172.17.0.1:42434 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:44 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:31:44 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:31:44 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:31:44 - docling_serve.app - [TENANT_ID] Task e89171f5-e881-423e-b2f6-dcba6bf44dec created with tenant_id='default' +INFO: 04:31:44 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task e89171f5-e881-423e-b2f6-dcba6bf44dec +INFO: 04:31:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:44 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:31:44 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:31:44 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:31:44,668 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:44,668 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:31:44,700 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:44,700 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:31:44,768 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:44,768 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:31:44 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:44 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:31:44 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:45 - docling.document_converter - Going to convert document batch... +INFO: 04:31:45 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:31:45 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:45 - docling.document_converter - Finished converting document file in 0.41 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:655: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:49:30 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:49:30 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job a5c66db6-c275-4857-ad05-51f3ceb5d24a in 0.51 seconds -INFO: 04:49:31 - uvicorn.access - 172.17.0.1:48756 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:49:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:49:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:49:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:49:31 - docling_serve.app - [TENANT_ID] Task ba5711ec-9e34-4b1c-a181-30373d9f341a created with tenant_id='default' -INFO: 04:49:31 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ba5711ec-9e34-4b1c-a181-30373d9f341a -INFO: 04:49:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:49:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:49:31 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:49:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:49:31,395 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:31,396 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:49:31,441 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:31,441 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:49:31,480 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:49:31,480 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:49:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:49:31 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:49:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:49:32 - docling.document_converter - Going to convert document batch... -INFO: 04:49:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:49:32 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:49:32 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 04:31:45 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:31:45 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job e89171f5-e881-423e-b2f6-dcba6bf44dec in 0.41 seconds +INFO: 04:31:46 - uvicorn.access - 172.17.0.1:42434 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:46 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:31:46 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:31:46 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:31:46 - docling_serve.app - [TENANT_ID] Task 019a9395-71f8-4971-9494-20f3df723603 created with tenant_id='default' +INFO: 04:31:46 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 019a9395-71f8-4971-9494-20f3df723603 +INFO: 04:31:46 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:46 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:31:46 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:31:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:31:46,665 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:46,665 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:31:46,692 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:46,692 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:31:46,739 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:31:46,739 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:31:46 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:46 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:31:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:47 - docling.document_converter - Going to convert document batch... +INFO: 04:31:47 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:31:47 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:47 - docling.document_converter - Finished converting document file in 0.38 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:655: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:49:32 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. -INFO: 04:49:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ba5711ec-9e34-4b1c-a181-30373d9f341a in 0.40 seconds -INFO: 04:49:33 - uvicorn.access - 172.17.0.1:48756 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:49:33 - uvicorn.access - 172.17.0.1:48756 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:49:33 - uvicorn.access - 172.17.0.1:48756 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:31:47 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. +INFO: 04:31:47 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 019a9395-71f8-4971-9494-20f3df723603 in 0.40 seconds +INFO: 04:31:48 - uvicorn.access - 172.17.0.1:42434 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:48 - uvicorn.access - 172.17.0.1:42434 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:31:48 - uvicorn.access - 172.17.0.1:42434 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -979,151 +1299,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:47:22 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:22 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:47:22 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:47:23 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:47:23 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:47:23 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:47:23 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:47:23 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:47:23 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:47:23 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:47:23 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:47:23 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/healthz$,/health$,/ready$,/readyz$) -INFO: 04:47:23 - uvicorn.error - Started server process [1] -INFO: 04:47:23 - uvicorn.error - Waiting for application startup. -INFO: 04:47:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:26 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:47:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:26 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:47:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:47:26 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 019ac48c98c19d19127e62d9a66de678 -INFO: 04:47:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:26 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:47:26 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:47:26.792545719 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:47:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:47:27,043 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:27,044 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:47:27,097 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:27,097 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:47:27,145 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:27,146 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:47:27 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:47:27 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:47:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:47:30 - docling.document_converter - Going to convert document batch... -INFO: 04:47:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd -INFO: 04:47:30 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:47:30 - docling.document_converter - Finished converting document file in 0.56 sec. +INFO: 04:30:02 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:30:02 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:30:02 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:30:02 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:30:02 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:30:02 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:30:02 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:30:02 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:30:02 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:30:02 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:30:02 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:30:02 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/livez$,/metrics$,/health$,/ready$,/readyz$) +INFO: 04:30:02 - uvicorn.error - Started server process [1] +INFO: 04:30:02 - uvicorn.error - Waiting for application startup. +INFO: 04:30:04 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:30:05 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:30:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:30:05 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:30:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:30:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 019ac48c98c19d19127e62d9a66de678 +INFO: 04:30:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:30:05 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:30:05 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:30:05.103118872 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:30:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:30:05,232 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:05,233 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:30:05,264 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:05,265 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:30:05,292 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:05,292 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:30:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:30:05 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:30:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:30:07 - docling.document_converter - Going to convert document batch... +INFO: 04:30:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd +INFO: 04:30:07 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:30:07 - docling.document_converter - Finished converting document file in 0.60 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:645: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:47:30 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:47:30 - docling_jobkit.convert.results - Processed 1 docs in 0.63 seconds. -INFO: 04:47:30 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c938b083-6b91-424c-b1d9-82ea6806fdd6 in 0.63 seconds -INFO: 04:47:32 - uvicorn.access - 172.17.0.1:52834 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:47:32 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:47:32 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:47:32 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:47:32 - docling_serve.app - [TENANT_ID] Task 4b92fe8a-b912-480e-9734-e93e55cf98f9 created with tenant_id='default' -INFO: 04:47:32 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 4b92fe8a-b912-480e-9734-e93e55cf98f9 -INFO: 04:47:32 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:47:32 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd -INFO: 04:47:32 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:47:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:47:32,420 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:32,421 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:47:32,473 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:32,473 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:47:32,518 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:32,519 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:47:32 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:47:32 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:47:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:47:33 - docling.document_converter - Going to convert document batch... -INFO: 04:47:33 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd -INFO: 04:47:33 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:47:33 - docling.document_converter - Finished converting document file in 0.51 sec. +WARNING: 04:30:07 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:30:07 - docling_jobkit.convert.results - Processed 1 docs in 0.63 seconds. +INFO: 04:30:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f0c19d5f-5233-45d9-b63a-68383b3abebb in 0.63 seconds +INFO: 04:30:08 - uvicorn.access - 172.17.0.1:41566 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:30:08 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:30:08 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:30:08 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:30:08 - docling_serve.app - [TENANT_ID] Task b8a8a360-53e4-4ac2-a60a-7131665c8aed created with tenant_id='default' +INFO: 04:30:08 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b8a8a360-53e4-4ac2-a60a-7131665c8aed +INFO: 04:30:08 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:30:08 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd +INFO: 04:30:08 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:30:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:30:08,440 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:08,440 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:30:08,483 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:08,483 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:30:08,506 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:08,506 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:30:08 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:30:08 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:30:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:30:09 - docling.document_converter - Going to convert document batch... +INFO: 04:30:09 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd +INFO: 04:30:09 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:30:09 - docling.document_converter - Finished converting document file in 0.41 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:645: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:47:33 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 04:47:33 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 4b92fe8a-b912-480e-9734-e93e55cf98f9 in 0.52 seconds -INFO: 04:47:34 - uvicorn.access - 172.17.0.1:52834 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:47:34 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:47:34 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:47:34 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:47:34 - docling_serve.app - [TENANT_ID] Task c0b946f9-2b06-4186-a428-5c6e556bd296 created with tenant_id='default' -INFO: 04:47:34 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task c0b946f9-2b06-4186-a428-5c6e556bd296 -INFO: 04:47:34 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:47:34 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 345bf8d309571831952bb6d347d0f005 -INFO: 04:47:34 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:47:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:47:34,429 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:34,429 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:47:34,479 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:34,479 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:47:34,526 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:47:34,526 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:47:34 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:47:34 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:47:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:47:35 - docling.document_converter - Going to convert document batch... -INFO: 04:47:35 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 345bf8d309571831952bb6d347d0f005 -INFO: 04:47:35 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:47:36 - docling.document_converter - Finished converting document file in 0.69 sec. +INFO: 04:30:09 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:30:09 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b8a8a360-53e4-4ac2-a60a-7131665c8aed in 0.41 seconds +INFO: 04:30:10 - uvicorn.access - 172.17.0.1:41566 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:30:10 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:30:10 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:30:10 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:30:10 - docling_serve.app - [TENANT_ID] Task e08fa18b-3495-4cb5-a8ab-5594282862c4 created with tenant_id='default' +INFO: 04:30:10 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e08fa18b-3495-4cb5-a8ab-5594282862c4 +INFO: 04:30:10 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:30:10 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 345bf8d309571831952bb6d347d0f005 +INFO: 04:30:10 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:30:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:30:10,463 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:10,463 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:30:10,490 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:10,490 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:30:10,518 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:30:10,518 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:30:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:30:10 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:30:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:30:11 - docling.document_converter - Going to convert document batch... +INFO: 04:30:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 345bf8d309571831952bb6d347d0f005 +INFO: 04:30:11 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:30:11 - docling.document_converter - Finished converting document file in 0.38 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:645: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:47:36 - docling_jobkit.convert.results - Processed 1 docs in 0.73 seconds. -INFO: 04:47:36 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c0b946f9-2b06-4186-a428-5c6e556bd296 in 0.73 seconds -INFO: 04:47:36 - uvicorn.access - 172.17.0.1:52834 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:47:36 - uvicorn.access - 172.17.0.1:52834 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:47:36 - uvicorn.access - 172.17.0.1:52834 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:30:11 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. +INFO: 04:30:11 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e08fa18b-3495-4cb5-a8ab-5594282862c4 in 0.40 seconds +INFO: 04:30:12 - uvicorn.access - 172.17.0.1:41566 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:30:12 - uvicorn.access - 172.17.0.1:41566 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:30:12 - uvicorn.access - 172.17.0.1:41566 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1161,151 +1481,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:45:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:34 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:45:34 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:45:35 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:45:35 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:45:35 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:45:35 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:45:35 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:45:35 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:45:35 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:45:35 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:45:35 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/metrics$,/ready$,/health$,/healthz$) -INFO: 04:45:35 - uvicorn.error - Started server process [1] -INFO: 04:45:35 - uvicorn.error - Waiting for application startup. -INFO: 04:45:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:38 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:45:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:38 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:45:38 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:45:38 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9d06178a9f1c8aeb9889d1e46440f3fa -INFO: 04:45:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:38 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:45:38 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:45:38.964077769 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:45:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:45:39,207 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:39,209 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:45:39,265 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:39,265 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:45:39,320 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:39,320 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:45:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:45:39 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:45:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:45:42 - docling.document_converter - Going to convert document batch... -INFO: 04:45:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d -INFO: 04:45:42 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:45:42 - docling.document_converter - Finished converting document file in 0.54 sec. +INFO: 04:28:41 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:41 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:28:41 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:28:42 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:28:42 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:28:42 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:28:42 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:28:42 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:28:42 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:28:42 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:28:42 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:28:42 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/health$,/healthz$,/ready$,/readyz$) +INFO: 04:28:42 - uvicorn.error - Started server process [1] +INFO: 04:28:42 - uvicorn.error - Waiting for application startup. +INFO: 04:28:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:45 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:28:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:45 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:28:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9d06178a9f1c8aeb9889d1e46440f3fa +INFO: 04:28:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:45 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:28:45 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:28:45.760242676 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:28:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:28:45,948 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:45,949 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:28:45,978 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:45,978 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:28:46,032 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:46,035 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:28:46 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:46 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:28:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:48 - docling.document_converter - Going to convert document batch... +INFO: 04:28:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d +INFO: 04:28:48 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:49 - docling.document_converter - Finished converting document file in 0.42 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:641: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:45:42 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:45:42 - docling_jobkit.convert.results - Processed 1 docs in 0.62 seconds. -INFO: 04:45:42 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 1a071ad0-7c61-4329-bd7b-82c5c7946d87 in 0.62 seconds -INFO: 04:45:43 - uvicorn.access - 172.17.0.1:49886 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:45:43 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:45:43 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:45:43 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:45:43 - docling_serve.app - [TENANT_ID] Task d8652a1d-b2b7-4b33-b4bc-a734646020be created with tenant_id='default' -INFO: 04:45:43 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task d8652a1d-b2b7-4b33-b4bc-a734646020be -INFO: 04:45:43 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:45:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d -INFO: 04:45:43 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:45:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:45:43,167 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:43,167 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:45:43,218 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:43,218 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:45:43,276 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:43,276 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:45:43 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:45:43 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:45:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:45:44 - docling.document_converter - Going to convert document batch... -INFO: 04:45:44 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d -INFO: 04:45:44 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:45:44 - docling.document_converter - Finished converting document file in 0.49 sec. +WARNING: 04:28:49 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:28:49 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 04:28:49 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f5b8921a-adda-4814-a543-bd8a33b07de0 in 0.46 seconds +INFO: 04:28:49 - uvicorn.access - 172.17.0.1:45484 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:49 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:28:49 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:28:49 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:28:49 - docling_serve.app - [TENANT_ID] Task b23bac96-4487-4984-8a67-bdd31f749ea7 created with tenant_id='default' +INFO: 04:28:49 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b23bac96-4487-4984-8a67-bdd31f749ea7 +INFO: 04:28:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:49 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d +INFO: 04:28:49 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:28:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:28:49,980 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:49,980 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:28:50,030 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:50,030 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:28:50,088 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:50,088 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:28:50 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:50 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:28:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:50 - docling.document_converter - Going to convert document batch... +INFO: 04:28:50 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d +INFO: 04:28:50 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:51 - docling.document_converter - Finished converting document file in 0.41 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:641: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:45:44 - docling_jobkit.convert.results - Processed 1 docs in 0.49 seconds. -INFO: 04:45:44 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job d8652a1d-b2b7-4b33-b4bc-a734646020be in 0.49 seconds -INFO: 04:45:45 - uvicorn.access - 172.17.0.1:49886 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:45:45 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:45:45 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:45:45 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:45:45 - docling_serve.app - [TENANT_ID] Task 899bab13-986d-4885-88ac-3fc593ac2e37 created with tenant_id='default' -INFO: 04:45:45 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 899bab13-986d-4885-88ac-3fc593ac2e37 -INFO: 04:45:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:45:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 -INFO: 04:45:45 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:45:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:45:45,172 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:45,172 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:45:45,220 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:45,221 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:45:45,292 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:45:45,292 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:45:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:45:45 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:45:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:45:46 - docling.document_converter - Going to convert document batch... -INFO: 04:45:46 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 -INFO: 04:45:46 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:45:46 - docling.document_converter - Finished converting document file in 0.51 sec. +INFO: 04:28:51 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:28:51 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b23bac96-4487-4984-8a67-bdd31f749ea7 in 0.41 seconds +INFO: 04:28:51 - uvicorn.access - 172.17.0.1:45484 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:28:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:28:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:28:51 - docling_serve.app - [TENANT_ID] Task 4034a92c-a57d-409d-9034-5df32a01180c created with tenant_id='default' +INFO: 04:28:51 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 4034a92c-a57d-409d-9034-5df32a01180c +INFO: 04:28:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 +INFO: 04:28:51 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:28:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:28:51,985 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:51,985 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:28:52,040 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:52,040 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:28:52,094 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:28:52,094 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:28:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:52 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:28:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:53 - docling.document_converter - Going to convert document batch... +INFO: 04:28:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 +INFO: 04:28:53 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:53 - docling.document_converter - Finished converting document file in 0.27 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:641: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:45:46 - docling_jobkit.convert.results - Processed 1 docs in 0.55 seconds. -INFO: 04:45:46 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 899bab13-986d-4885-88ac-3fc593ac2e37 in 0.55 seconds -INFO: 04:45:47 - uvicorn.access - 172.17.0.1:49886 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:45:47 - uvicorn.access - 172.17.0.1:49886 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:45:47 - uvicorn.access - 172.17.0.1:49886 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:28:53 - docling_jobkit.convert.results - Processed 1 docs in 0.28 seconds. +INFO: 04:28:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4034a92c-a57d-409d-9034-5df32a01180c in 0.28 seconds +INFO: 04:28:53 - uvicorn.access - 172.17.0.1:45484 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:54 - uvicorn.access - 172.17.0.1:45484 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:28:54 - uvicorn.access - 172.17.0.1:45484 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1343,151 +1663,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:43:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:49 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:43:49 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:43:49 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:43:49 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:43:49 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:43:49 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:43:49 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:43:49 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:43:49 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:43:49 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/metrics$,/livez$,/health$,/readyz$,/healthz$) -INFO: 04:43:50 - uvicorn.error - Started server process [1] -INFO: 04:43:50 - uvicorn.error - Waiting for application startup. -INFO: 04:43:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:53 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:43:53 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:53 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:43:53 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:43:53 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e2db689ab35ca52a08b5b7fa25de8cc8 -INFO: 04:43:53 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:53 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:43:53 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:43:53.448676119 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:43:53 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:43:53,694 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:43:53,695 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:43:53,749 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:43:53,749 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:43:53,789 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:43:53,790 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:43:53 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:43:53 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:43:53 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:27:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:27:10 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:27:10 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:27:10 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:27:10 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:27:10 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:27:10 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:27:10 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:27:10 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:27:10 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:27:10 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/healthz$,/ready$,/health$,/readyz$,/metrics$) +INFO: 04:27:10 - uvicorn.error - Started server process [1] +INFO: 04:27:10 - uvicorn.error - Waiting for application startup. +INFO: 04:27:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:27:12 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:27:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:27:12 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:27:12 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:27:12 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e2db689ab35ca52a08b5b7fa25de8cc8 +INFO: 04:27:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:27:12 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:27:12 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:27:12.891947427 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:27:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:27:13,024 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:13,025 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:27:13,058 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:13,058 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:27:13,080 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:13,080 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:27:13 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:27:13 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:27:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' [transformers] `torch_dtype` is deprecated! Use `dtype` instead! - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:43:58 - docling.document_converter - Going to convert document batch... -INFO: 04:43:58 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d -INFO: 04:43:58 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:43:58 - docling.document_converter - Finished converting document file in 0.75 sec. + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:27:16 - docling.document_converter - Going to convert document batch... +INFO: 04:27:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d +INFO: 04:27:16 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:27:16 - docling.document_converter - Finished converting document file in 0.42 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:635: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:43:58 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:43:58 - docling_jobkit.convert.results - Processed 1 docs in 0.82 seconds. -INFO: 04:43:58 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 01840350-e4f9-4c8a-a6ae-2cce1f6d8eae in 0.82 seconds -INFO: 04:43:58 - uvicorn.access - 172.17.0.1:42600 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:43:58 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:43:58 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:43:58 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:43:58 - docling_serve.app - [TENANT_ID] Task 31882011-5829-48ac-86bd-ab1a3f0027d3 created with tenant_id='default' -INFO: 04:43:58 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 31882011-5829-48ac-86bd-ab1a3f0027d3 -INFO: 04:43:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:43:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d -INFO: 04:43:59 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:43:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:43:59,080 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:43:59,080 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:43:59,132 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:43:59,132 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:43:59,174 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:43:59,174 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:43:59 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:43:59 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:43:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:44:00 - docling.document_converter - Going to convert document batch... -INFO: 04:44:00 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d -INFO: 04:44:00 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:44:00 - docling.document_converter - Finished converting document file in 0.48 sec. +WARNING: 04:27:16 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:27:16 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. +INFO: 04:27:16 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 14d69cb1-ca07-4ab0-a32c-8c77f67074c4 in 0.45 seconds +INFO: 04:27:17 - uvicorn.access - 172.17.0.1:46506 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:27:17 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:27:17 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:27:17 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:27:17 - docling_serve.app - [TENANT_ID] Task 827098cc-90ee-4d06-aeaf-1d273b8892ed created with tenant_id='default' +INFO: 04:27:17 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 827098cc-90ee-4d06-aeaf-1d273b8892ed +INFO: 04:27:17 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:27:17 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d +INFO: 04:27:17 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:27:17 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:27:17,243 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:17,243 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:27:17,274 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:17,274 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:27:17,305 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:17,305 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:27:17 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:27:17 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:27:17 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:27:18 - docling.document_converter - Going to convert document batch... +INFO: 04:27:18 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d +INFO: 04:27:18 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:27:18 - docling.document_converter - Finished converting document file in 0.27 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:635: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:44:00 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. -INFO: 04:44:00 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 31882011-5829-48ac-86bd-ab1a3f0027d3 in 0.48 seconds -INFO: 04:44:00 - uvicorn.access - 172.17.0.1:42600 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:44:00 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:44:00 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:44:00 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:44:00 - docling_serve.app - [TENANT_ID] Task 13872adf-8afa-4460-a342-45997f0373b6 created with tenant_id='default' -INFO: 04:44:00 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 13872adf-8afa-4460-a342-45997f0373b6 -INFO: 04:44:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:44:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 -INFO: 04:44:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:44:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:44:01,103 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:44:01,103 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:44:01,155 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:44:01,156 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:44:01,197 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:44:01,198 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:44:01 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:44:01 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:44:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:44:02 - docling.document_converter - Going to convert document batch... -INFO: 04:44:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 -INFO: 04:44:02 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:44:02 - docling.document_converter - Finished converting document file in 0.72 sec. +INFO: 04:27:18 - docling_jobkit.convert.results - Processed 1 docs in 0.27 seconds. +INFO: 04:27:18 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 827098cc-90ee-4d06-aeaf-1d273b8892ed in 0.27 seconds +INFO: 04:27:19 - uvicorn.access - 172.17.0.1:46506 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:27:19 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:27:19 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:27:19 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:27:19 - docling_serve.app - [TENANT_ID] Task aad5e095-b669-45f0-a2a7-f64a394b39cb created with tenant_id='default' +INFO: 04:27:19 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task aad5e095-b669-45f0-a2a7-f64a394b39cb +INFO: 04:27:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:27:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 +INFO: 04:27:19 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:27:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:27:19,251 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:19,251 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:27:19,287 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:19,287 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:27:19,314 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:27:19,314 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:27:19 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:27:19 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:27:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:27:19 - docling.document_converter - Going to convert document batch... +INFO: 04:27:19 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 +INFO: 04:27:19 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:27:19 - docling.document_converter - Finished converting document file in 0.25 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:635: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:44:02 - docling_jobkit.convert.results - Processed 1 docs in 0.75 seconds. -INFO: 04:44:02 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 13872adf-8afa-4460-a342-45997f0373b6 in 0.75 seconds -INFO: 04:44:02 - uvicorn.access - 172.17.0.1:42600 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:44:03 - uvicorn.access - 172.17.0.1:42600 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:44:03 - uvicorn.access - 172.17.0.1:42600 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:27:19 - docling_jobkit.convert.results - Processed 1 docs in 0.27 seconds. +INFO: 04:27:19 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job aad5e095-b669-45f0-a2a7-f64a394b39cb in 0.27 seconds +INFO: 04:27:21 - uvicorn.access - 172.17.0.1:46506 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:27:21 - uvicorn.access - 172.17.0.1:46506 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:27:21 - uvicorn.access - 172.17.0.1:46506 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1525,139 +1845,139 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:42:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:01 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:42:01 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:42:01 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:42:01 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:42:01 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:42:01 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:42:01 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/ready$,/readyz$,/health$,/healthz$,/livez$) -INFO: 04:42:02 - uvicorn.error - Started server process [1] -INFO: 04:42:02 - uvicorn.error - Waiting for application startup. -INFO: 04:42:04 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:05 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:42:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:05 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:42:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:42:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash caff667a02b7f037838d32d34acfe0b0 -INFO: 04:42:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:05 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:42:05 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:42:05.576348270 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:42:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:42:05,837 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:05,838 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:42:05,890 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:05,891 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:42:05,934 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:05,934 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:42:06 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:42:06 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:42:09 - docling.document_converter - Going to convert document batch... -INFO: 04:42:09 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:42:09 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:42:09 - docling.document_converter - Finished converting document file in 0.61 sec. +INFO: 04:25:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:52 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:25:52 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:25:52 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:25:52 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:25:52 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:25:52 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:25:52 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/livez$,/metrics$,/ready$,/readyz$,/health$) +INFO: 04:25:53 - uvicorn.error - Started server process [1] +INFO: 04:25:53 - uvicorn.error - Waiting for application startup. +INFO: 04:25:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:55 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:25:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:55 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:25:55 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:55 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash caff667a02b7f037838d32d34acfe0b0 +INFO: 04:25:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:55 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:25:55 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:25:55.313989588 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:25:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:25:55,452 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:25:55,453 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:25:55,485 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:25:55,485 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:25:55,528 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:25:55,531 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:25:55 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:58 - docling.document_converter - Going to convert document batch... +INFO: 04:25:58 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:58 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:58 - docling.document_converter - Finished converting document file in 0.56 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:632: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:42:09 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:42:09 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. -INFO: 04:42:09 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job aee9dca3-c24f-4998-9982-061fb11995d3 in 0.70 seconds -INFO: 04:42:11 - uvicorn.access - 172.17.0.1:46366 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:42:11 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:42:11 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:42:11 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:42:11 - docling_serve.app - [TENANT_ID] Task ca44b472-5103-4c91-a63a-8c47f4baf52e created with tenant_id='default' -INFO: 04:42:11 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task ca44b472-5103-4c91-a63a-8c47f4baf52e -INFO: 04:42:11 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:42:11 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash ab12ef348c8fc273bf2be7a49773b303 -INFO: 04:42:11 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:42:11 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:42:11,857 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:11,857 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:42:11,908 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:11,908 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:42:11,957 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:11,957 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:42:12 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:42:12 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:42:13 - docling.document_converter - Going to convert document batch... -INFO: 04:42:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:42:13 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:42:13 - docling.document_converter - Finished converting document file in 0.51 sec. +WARNING: 04:25:58 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:25:58 - docling_jobkit.convert.results - Processed 1 docs in 0.62 seconds. +INFO: 04:25:58 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job a4cf2fd1-62fd-48ba-8406-713442806b87 in 0.62 seconds +INFO: 04:25:59 - uvicorn.access - 172.17.0.1:49842 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:59 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:25:59 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:25:59 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:25:59 - docling_serve.app - [TENANT_ID] Task 60b9917e-d23d-4f58-89be-54964b021f0c created with tenant_id='default' +INFO: 04:25:59 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 60b9917e-d23d-4f58-89be-54964b021f0c +INFO: 04:25:59 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash ab12ef348c8fc273bf2be7a49773b303 +INFO: 04:25:59 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:25:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:25:59,139 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:25:59,139 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:25:59,609 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:25:59,609 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:25:59,672 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:25:59,673 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:25:59 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:26:00 - docling.document_converter - Going to convert document batch... +INFO: 04:26:00 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:26:00 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:26:00 - docling.document_converter - Finished converting document file in 0.50 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:632: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:42:13 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:42:13 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job ca44b472-5103-4c91-a63a-8c47f4baf52e in 0.51 seconds -INFO: 04:42:13 - uvicorn.access - 172.17.0.1:46366 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:42:13 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:42:13 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:42:13 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:42:13 - docling_serve.app - [TENANT_ID] Task 50007ce5-7dc4-4ef7-84d2-b20a33b19d92 created with tenant_id='default' -INFO: 04:42:13 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 50007ce5-7dc4-4ef7-84d2-b20a33b19d92 -INFO: 04:42:13 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:42:13 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b3849eabdc7ecae5f3d54428a0162342 -INFO: 04:42:13 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:42:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:42:13,874 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:13,874 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:42:13,923 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:13,923 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:42:13,981 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:42:13,981 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:42:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:42:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:42:15 - docling.document_converter - Going to convert document batch... -INFO: 04:42:15 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:42:15 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:42:15 - docling.document_converter - Finished converting document file in 0.49 sec. +INFO: 04:26:00 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. +INFO: 04:26:00 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 60b9917e-d23d-4f58-89be-54964b021f0c in 0.50 seconds +INFO: 04:26:01 - uvicorn.access - 172.17.0.1:49842 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:26:01 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:26:01 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:26:01 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:26:01 - docling_serve.app - [TENANT_ID] Task 707568d6-1ff3-4cee-9a11-d281f3f35107 created with tenant_id='default' +INFO: 04:26:01 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 707568d6-1ff3-4cee-9a11-d281f3f35107 +INFO: 04:26:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:26:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b3849eabdc7ecae5f3d54428a0162342 +INFO: 04:26:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:26:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:26:01,160 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:26:01,160 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:26:01,191 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:26:01,191 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:26:01,253 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:26:01,253 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:26:01 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:26:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:26:02 - docling.document_converter - Going to convert document batch... +INFO: 04:26:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:26:02 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:26:02 - docling.document_converter - Finished converting document file in 0.43 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:632: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:42:15 - docling_jobkit.convert.results - Processed 1 docs in 0.53 seconds. -INFO: 04:42:15 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 50007ce5-7dc4-4ef7-84d2-b20a33b19d92 in 0.53 seconds -INFO: 04:42:15 - uvicorn.access - 172.17.0.1:46366 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:42:16 - uvicorn.access - 172.17.0.1:46366 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:42:16 - uvicorn.access - 172.17.0.1:46366 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:26:02 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. +INFO: 04:26:02 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 707568d6-1ff3-4cee-9a11-d281f3f35107 in 0.45 seconds +INFO: 04:26:03 - uvicorn.access - 172.17.0.1:49842 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:26:03 - uvicorn.access - 172.17.0.1:49842 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:26:03 - uvicorn.access - 172.17.0.1:49842 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1695,138 +2015,138 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:40:15 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:15 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:40:15 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:40:16 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:40:16 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:40:16 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:40:16 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/metrics$,/healthz$,/health$,/ready$,/livez$) -INFO: 04:40:16 - uvicorn.error - Started server process [1] -INFO: 04:40:16 - uvicorn.error - Waiting for application startup. -INFO: 04:40:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:19 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:40:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:19 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:40:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:40:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 -INFO: 04:40:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:19 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:40:19 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:40:19.658229802 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:40:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:40:19,909 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:19,910 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:40:19,969 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:19,969 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:40:20,037 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:20,037 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:40:20 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:40:20 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:40:23 - docling.document_converter - Going to convert document batch... -INFO: 04:40:23 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:40:23 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:40:24 - docling.document_converter - Finished converting document file in 0.85 sec. +INFO: 04:24:23 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:24:23 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:24:23 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:24:23 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:24:23 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:24:23 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:24:23 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/healthz$,/ready$,/livez$,/readyz$,/health$) +INFO: 04:24:23 - uvicorn.error - Started server process [1] +INFO: 04:24:23 - uvicorn.error - Waiting for application startup. +INFO: 04:24:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:24:25 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:24:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:24:25 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:24:25 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:24:25 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 04:24:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:24:25 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:24:25 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:24:25.799081582 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:24:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:24:25,938 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:25,938 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:24:25,974 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:25,974 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:24:26,002 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:26,002 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:24:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:24:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:24:28 - docling.document_converter - Going to convert document batch... +INFO: 04:24:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:24:28 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:24:28 - docling.document_converter - Finished converting document file in 0.39 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:611: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:40:24 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:40:24 - docling_jobkit.convert.results - Processed 1 docs in 0.92 seconds. -INFO: 04:40:24 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job da29f4fb-3aaa-4223-acde-b93995b77205 in 0.92 seconds -INFO: 04:40:25 - uvicorn.access - 172.17.0.1:41494 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:40:25 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:40:25 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:40:25 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:40:25 - docling_serve.app - [TENANT_ID] Task 96eba1d7-a4f0-49d2-beb6-5ca898195b67 created with tenant_id='default' -INFO: 04:40:25 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 96eba1d7-a4f0-49d2-beb6-5ca898195b67 -INFO: 04:40:25 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:40:26 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 -INFO: 04:40:26 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:40:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:40:26,062 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:26,062 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:40:26,117 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:26,118 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:40:26,164 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:26,164 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:40:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:40:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:40:27 - docling.document_converter - Going to convert document batch... -INFO: 04:40:27 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:40:27 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:40:27 - docling.document_converter - Finished converting document file in 0.63 sec. +WARNING: 04:24:28 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:24:28 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:24:28 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8b96da42-b428-4d37-8710-d0f68d007672 in 0.43 seconds +INFO: 04:24:29 - uvicorn.access - 172.17.0.1:48480 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:24:29 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:24:29 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:24:29 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:24:29 - docling_serve.app - [TENANT_ID] Task 19c1528a-279e-49ce-bf89-3cfea37e37de created with tenant_id='default' +INFO: 04:24:29 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 19c1528a-279e-49ce-bf89-3cfea37e37de +INFO: 04:24:29 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:24:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 04:24:29 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:24:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:24:29,157 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:29,157 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:24:29,190 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:29,190 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:24:29,237 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:29,237 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:24:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:24:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:24:29 - docling.document_converter - Going to convert document batch... +INFO: 04:24:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:24:29 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:24:29 - docling.document_converter - Finished converting document file in 0.37 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:611: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:40:27 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. -INFO: 04:40:27 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 96eba1d7-a4f0-49d2-beb6-5ca898195b67 in 0.64 seconds -INFO: 04:40:27 - uvicorn.access - 172.17.0.1:41494 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:40:27 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:40:27 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:40:27 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:40:27 - docling_serve.app - [TENANT_ID] Task eacf4893-b4f7-4196-9d9a-c32b58488201 created with tenant_id='default' -INFO: 04:40:27 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task eacf4893-b4f7-4196-9d9a-c32b58488201 -INFO: 04:40:27 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:40:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc -INFO: 04:40:28 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:40:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:40:28,064 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:28,065 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:40:28,116 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:28,116 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:40:28,184 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:40:28,184 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:40:28 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:40:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:40:29 - docling.document_converter - Going to convert document batch... -INFO: 04:40:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:40:29 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:40:29 - docling.document_converter - Finished converting document file in 0.37 sec. +INFO: 04:24:30 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:24:30 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 19c1528a-279e-49ce-bf89-3cfea37e37de in 0.37 seconds +INFO: 04:24:31 - uvicorn.access - 172.17.0.1:48480 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:24:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:24:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:24:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:24:31 - docling_serve.app - [TENANT_ID] Task 6ecf8904-8eaa-4508-8a8a-574af0b6f214 created with tenant_id='default' +INFO: 04:24:31 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 6ecf8904-8eaa-4508-8a8a-574af0b6f214 +INFO: 04:24:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:24:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc +INFO: 04:24:31 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:24:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:24:31,161 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:31,161 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:24:31,195 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:31,199 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:24:31,240 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:24:31,240 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:24:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:24:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:24:31 - docling.document_converter - Going to convert document batch... +INFO: 04:24:31 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:24:31 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:24:31 - docling.document_converter - Finished converting document file in 0.37 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:611: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:40:29 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. -INFO: 04:40:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job eacf4893-b4f7-4196-9d9a-c32b58488201 in 0.41 seconds -INFO: 04:40:29 - uvicorn.access - 172.17.0.1:41494 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:40:30 - uvicorn.access - 172.17.0.1:41494 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:40:30 - uvicorn.access - 172.17.0.1:41494 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:24:31 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:24:31 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 6ecf8904-8eaa-4508-8a8a-574af0b6f214 in 0.38 seconds +INFO: 04:24:33 - uvicorn.access - 172.17.0.1:48480 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:24:33 - uvicorn.access - 172.17.0.1:48480 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:24:33 - uvicorn.access - 172.17.0.1:48480 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1864,136 +2184,136 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:38:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:33 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:38:33 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:38:33 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:38:33 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/ready$,/readyz$,/health$,/metrics$,/livez$) -INFO: 04:38:33 - uvicorn.error - Started server process [1] -INFO: 04:38:33 - uvicorn.error - Waiting for application startup. -INFO: 04:38:36 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:36 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:38:36 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:36 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:38:36 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:38:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 -INFO: 04:38:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:37 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:38:37 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:38:37.144364215 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:38:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:38:37,389 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:37,390 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:38:37,450 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:37,451 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:38:37,507 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:37,507 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:38:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:38:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:38:40 - docling.document_converter - Going to convert document batch... -INFO: 04:38:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:38:40 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:38:40 - docling.document_converter - Finished converting document file in 0.68 sec. +INFO: 04:23:07 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:23:07 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:23:07 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:23:07 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:23:07 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/healthz$,/health$,/metrics$,/ready$) +INFO: 04:23:07 - uvicorn.error - Started server process [1] +INFO: 04:23:07 - uvicorn.error - Waiting for application startup. +INFO: 04:23:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:23:10 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:23:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:23:10 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:23:10 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:23:10 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 04:23:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:23:10 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:23:10 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:23:10.345534576 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:23:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:23:10,503 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:10,504 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:23:10,540 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:10,540 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:23:10,609 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:10,609 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:23:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:23:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:23:12 - docling.document_converter - Going to convert document batch... +INFO: 04:23:12 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:23:12 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:23:12 - docling.document_converter - Finished converting document file in 0.47 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:588: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:38:40 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:38:40 - docling_jobkit.convert.results - Processed 1 docs in 0.77 seconds. -INFO: 04:38:40 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f692fad0-8b31-4631-ac08-6ee6ff87009d in 0.77 seconds -INFO: 04:38:40 - uvicorn.access - 172.17.0.1:54102 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:38:40 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:38:40 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:38:40 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:38:40 - docling_serve.app - [TENANT_ID] Task dfb2702b-51db-4e6b-b22c-67f2d9424e3d created with tenant_id='default' -INFO: 04:38:40 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task dfb2702b-51db-4e6b-b22c-67f2d9424e3d -INFO: 04:38:40 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:38:40 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 -INFO: 04:38:40 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:38:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:38:40,645 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:40,645 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:38:40,704 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:40,704 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:38:40,764 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:40,764 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:38:40 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:38:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:38:42 - docling.document_converter - Going to convert document batch... -INFO: 04:38:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:38:42 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:38:42 - docling.document_converter - Finished converting document file in 0.38 sec. +WARNING: 04:23:12 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:23:12 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. +INFO: 04:23:12 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 1584e4a4-1809-47b4-ba30-63134d31f19b in 0.52 seconds +INFO: 04:23:13 - uvicorn.access - 172.17.0.1:40106 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:23:13 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:23:13 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:23:13 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:23:13 - docling_serve.app - [TENANT_ID] Task fe2e5edb-8a49-40c5-8926-348523f22c91 created with tenant_id='default' +INFO: 04:23:13 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task fe2e5edb-8a49-40c5-8926-348523f22c91 +INFO: 04:23:13 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:23:13 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 04:23:13 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:23:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:23:13,590 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:13,590 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:23:13,637 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:13,638 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:23:13,690 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:13,690 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:23:13 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:23:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:23:14 - docling.document_converter - Going to convert document batch... +INFO: 04:23:14 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:23:14 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:23:14 - docling.document_converter - Finished converting document file in 0.37 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:588: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:38:42 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. -INFO: 04:38:42 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job dfb2702b-51db-4e6b-b22c-67f2d9424e3d in 0.38 seconds -INFO: 04:38:42 - uvicorn.access - 172.17.0.1:54102 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] Task 2ae4462d-d263-400e-8cdd-e8dea069b9e5 created with tenant_id='default' -INFO: 04:38:42 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 2ae4462d-d263-400e-8cdd-e8dea069b9e5 -INFO: 04:38:42 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:38:42 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc -INFO: 04:38:42 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:38:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:38:42,653 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:42,653 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-10-19 04:38:42,719 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:42,720 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:38:42,771 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:38:42,771 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:38:42 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:38:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:38:43 - docling.document_converter - Going to convert document batch... -INFO: 04:38:43 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:38:43 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:38:44 - docling.document_converter - Finished converting document file in 0.48 sec. +INFO: 04:23:14 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:23:14 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job fe2e5edb-8a49-40c5-8926-348523f22c91 in 0.37 seconds +INFO: 04:23:15 - uvicorn.access - 172.17.0.1:40106 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:23:15 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:23:15 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:23:15 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:23:15 - docling_serve.app - [TENANT_ID] Task 72c70633-d875-48cc-bb3f-e86ec8fc890d created with tenant_id='default' +INFO: 04:23:15 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 72c70633-d875-48cc-bb3f-e86ec8fc890d +INFO: 04:23:15 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:23:15 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc +INFO: 04:23:15 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:23:15 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:23:15,591 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:15,592 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-10-26 04:23:15,648 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:15,649 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:23:15,714 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:23:15,714 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:23:15 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:23:15 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:23:16 - docling.document_converter - Going to convert document batch... +INFO: 04:23:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:23:16 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:23:16 - docling.document_converter - Finished converting document file in 0.17 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:588: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:38:44 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 04:38:44 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2ae4462d-d263-400e-8cdd-e8dea069b9e5 in 0.52 seconds -INFO: 04:38:44 - uvicorn.access - 172.17.0.1:54102 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:38:44 - uvicorn.access - 172.17.0.1:54102 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:38:44 - uvicorn.access - 172.17.0.1:54102 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:23:16 - docling_jobkit.convert.results - Processed 1 docs in 0.19 seconds. +INFO: 04:23:16 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 72c70633-d875-48cc-bb3f-e86ec8fc890d in 0.19 seconds +INFO: 04:23:17 - uvicorn.access - 172.17.0.1:40106 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:23:17 - uvicorn.access - 172.17.0.1:40106 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:23:17 - uvicorn.access - 172.17.0.1:40106 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2031,136 +2351,136 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:36:42 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:36:42 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:36:42 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:36:42 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:36:42 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/healthz$,/metrics$,/health$,/livez$,/readyz$) -INFO: 04:36:42 - uvicorn.error - Started server process [1] -INFO: 04:36:42 - uvicorn.error - Waiting for application startup. -INFO: 04:36:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:36:46 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:36:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:36:46 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:36:46 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:36:46 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 -INFO: 04:36:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:36:46 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:36:46 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-10-19 04:36:46.281657020 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:36:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:36:46,517 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:46,518 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:36:46,611 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:46,612 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:36:46,657 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:46,658 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:36:46 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:36:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:36:49 - docling.document_converter - Going to convert document batch... -INFO: 04:36:49 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:36:49 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:36:50 - docling.document_converter - Finished converting document file in 0.53 sec. +INFO: 04:21:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:21:35 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:21:35 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:21:35 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:21:35 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/metrics$,/livez$,/healthz$,/ready$,/health$) +INFO: 04:21:35 - uvicorn.error - Started server process [1] +INFO: 04:21:35 - uvicorn.error - Waiting for application startup. +INFO: 04:21:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:21:38 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:21:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:21:38 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:21:38 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:21:38 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 +INFO: 04:21:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:21:38 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:21:38 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-10-26 04:21:38.373329599 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:21:38 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:21:38,498 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:38,499 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:21:38,553 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:38,553 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:21:38,577 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:38,578 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:21:38 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:21:38 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:21:40 - docling.document_converter - Going to convert document batch... +INFO: 04:21:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:21:40 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:21:40 - docling.document_converter - Finished converting document file in 0.38 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:556: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:36:50 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:36:50 - docling_jobkit.convert.results - Processed 1 docs in 0.61 seconds. -INFO: 04:36:50 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 451a18bb-06a9-498a-a4c6-47b29dd08c99 in 0.61 seconds -INFO: 04:36:50 - uvicorn.access - 172.17.0.1:38934 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:36:50 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:36:50 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:36:50 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:36:50 - docling_serve.app - [TENANT_ID] Task a0ffff3a-e548-4f5a-a066-9080962da095 created with tenant_id='default' -INFO: 04:36:50 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task a0ffff3a-e548-4f5a-a066-9080962da095 -INFO: 04:36:50 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:36:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac -INFO: 04:36:50 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:36:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:36:50,555 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:50,555 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:36:50,651 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:50,651 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:36:50,719 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:50,719 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:36:50 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:36:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:36:52 - docling.document_converter - Going to convert document batch... -INFO: 04:36:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:36:52 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:36:52 - docling.document_converter - Finished converting document file in 0.51 sec. +WARNING: 04:21:40 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:21:40 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:21:40 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 5abdd47c-5f88-41b7-a89a-7d9387be0dd0 in 0.41 seconds +INFO: 04:21:41 - uvicorn.access - 172.17.0.1:47558 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:21:41 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:21:41 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:21:41 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:21:41 - docling_serve.app - [TENANT_ID] Task 5bcfbd71-7887-473a-a505-65febf3c511a created with tenant_id='default' +INFO: 04:21:41 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5bcfbd71-7887-473a-a505-65febf3c511a +INFO: 04:21:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:21:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac +INFO: 04:21:41 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:21:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:21:41,995 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:41,995 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:21:42,049 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:42,049 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:21:42,074 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:42,074 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:21:42 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:21:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:21:43 - docling.document_converter - Going to convert document batch... +INFO: 04:21:43 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:21:43 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:21:43 - docling.document_converter - Finished converting document file in 0.35 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:556: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:36:52 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:36:52 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job a0ffff3a-e548-4f5a-a066-9080962da095 in 0.51 seconds -INFO: 04:36:52 - uvicorn.access - 172.17.0.1:38934 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:36:52 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:36:52 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:36:52 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:36:52 - docling_serve.app - [TENANT_ID] Task f7fda1a5-df5f-4fe1-9eab-993111a5ec5c created with tenant_id='default' -INFO: 04:36:52 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task f7fda1a5-df5f-4fe1-9eab-993111a5ec5c -INFO: 04:36:52 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:36:52 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 -INFO: 04:36:52 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:36:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:36:52,567 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:52,567 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:36:52,656 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:52,656 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:36:52,703 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:36:52,703 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:36:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:36:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:36:53 - docling.document_converter - Going to convert document batch... -INFO: 04:36:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:36:53 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:36:53 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 04:21:43 - docling_jobkit.convert.results - Processed 1 docs in 0.36 seconds. +INFO: 04:21:43 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5bcfbd71-7887-473a-a505-65febf3c511a in 0.36 seconds +INFO: 04:21:43 - uvicorn.access - 172.17.0.1:47558 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:21:43 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:21:43 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:21:43 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:21:43 - docling_serve.app - [TENANT_ID] Task bfba13c7-0735-4f74-b0dd-be7c6982f11d created with tenant_id='default' +INFO: 04:21:43 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task bfba13c7-0735-4f74-b0dd-be7c6982f11d +INFO: 04:21:43 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:21:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 +INFO: 04:21:43 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:21:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:21:44,007 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:44,007 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:21:44,060 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:44,060 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:21:44,084 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:21:44,084 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:21:44 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:21:44 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:21:44 - docling.document_converter - Going to convert document batch... +INFO: 04:21:44 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:21:44 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:21:44 - docling.document_converter - Finished converting document file in 0.37 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:556: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:36:53 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. -INFO: 04:36:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f7fda1a5-df5f-4fe1-9eab-993111a5ec5c in 0.40 seconds -INFO: 04:36:54 - uvicorn.access - 172.17.0.1:38934 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:36:54 - uvicorn.access - 172.17.0.1:38934 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:36:54 - uvicorn.access - 172.17.0.1:38934 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:21:44 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:21:44 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job bfba13c7-0735-4f74-b0dd-be7c6982f11d in 0.38 seconds +INFO: 04:21:45 - uvicorn.access - 172.17.0.1:47558 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:21:46 - uvicorn.access - 172.17.0.1:47558 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:21:46 - uvicorn.access - 172.17.0.1:47558 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2198,120 +2518,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:34:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:34:56 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:34:56 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:34:56 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:34:56 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/metrics$,/health$,/livez$,/ready$,/healthz$) -INFO: 04:34:56 - uvicorn.error - Started server process [1] -INFO: 04:34:56 - uvicorn.error - Waiting for application startup. -INFO: 04:34:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:34:59 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:34:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:34:59 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:34:59 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:34:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e -INFO: 04:34:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:34:59 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-10-19 04:34:59.961209875 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:35:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:35:00,265 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:00,266 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:35:00,370 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:00,370 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:35:00,416 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:00,417 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:35:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:35:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:35:04 - docling.document_converter - Going to convert document batch... -INFO: 04:35:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:35:04 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:35:04 - docling.document_converter - Finished converting document file in 0.93 sec. -WARNING: 04:35:04 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:35:04 - docling_jobkit.convert.results - Processed 1 docs in 1.00 seconds. -INFO: 04:35:04 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 64107365-9bff-4a58-a4eb-da6da9517598 in 1.00 seconds -INFO: 04:35:06 - uvicorn.access - 172.17.0.1:47162 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:35:06 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:35:06 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:35:06 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:35:06 - docling_serve.app - [TENANT_ID] Task d77396c0-360d-4a52-a392-a1422640b399 created with tenant_id='default' -INFO: 04:35:06 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task d77396c0-360d-4a52-a392-a1422640b399 -INFO: 04:35:06 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:35:06 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a -INFO: 04:35:06 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:35:06,381 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:06,381 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:35:06,471 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:06,471 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:35:06,521 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:06,521 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:35:06 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:35:06 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:35:08 - docling.document_converter - Going to convert document batch... -INFO: 04:35:08 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:35:08 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:35:08 - docling.document_converter - Finished converting document file in 0.50 sec. -INFO: 04:35:08 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:35:08 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job d77396c0-360d-4a52-a392-a1422640b399 in 0.50 seconds -INFO: 04:35:08 - uvicorn.access - 172.17.0.1:47162 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:35:08 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:35:08 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:35:08 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:35:08 - docling_serve.app - [TENANT_ID] Task 4ad0e138-3a3c-4dfb-abd2-d7b26017a6e8 created with tenant_id='default' -INFO: 04:35:08 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 4ad0e138-3a3c-4dfb-abd2-d7b26017a6e8 -INFO: 04:35:08 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:35:08 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 -INFO: 04:35:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:35:08,387 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:08,387 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:35:08,482 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:08,482 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:35:08,533 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:35:08,533 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:35:08 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:35:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:35:10 - docling.document_converter - Going to convert document batch... -INFO: 04:35:10 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:35:10 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:35:10 - docling.document_converter - Finished converting document file in 0.90 sec. -INFO: 04:35:10 - docling_jobkit.convert.results - Processed 1 docs in 0.94 seconds. -INFO: 04:35:10 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4ad0e138-3a3c-4dfb-abd2-d7b26017a6e8 in 0.94 seconds -INFO: 04:35:10 - uvicorn.access - 172.17.0.1:47162 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:35:10 - uvicorn.access - 172.17.0.1:47162 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:35:10 - uvicorn.access - 172.17.0.1:47162 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:20:23 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:20:23 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:20:23 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:20:23 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:20:23 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/readyz$,/metrics$,/ready$,/livez$,/healthz$) +INFO: 04:20:23 - uvicorn.error - Started server process [1] +INFO: 04:20:23 - uvicorn.error - Waiting for application startup. +INFO: 04:20:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:20:26 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:20:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:20:26 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:20:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:20:26 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e +INFO: 04:20:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:20:26 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-10-26 04:20:26.187879825 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:20:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:20:26,397 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:26,398 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:20:26,460 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:26,460 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:20:26,485 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:26,485 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:20:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:20:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:20:28 - docling.document_converter - Going to convert document batch... +INFO: 04:20:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:20:28 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:20:28 - docling.document_converter - Finished converting document file in 0.70 sec. +WARNING: 04:20:28 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:20:28 - docling_jobkit.convert.results - Processed 1 docs in 0.73 seconds. +INFO: 04:20:28 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b88c8a2f-aed7-4bd0-8281-8ab124b62d48 in 0.73 seconds +INFO: 04:20:29 - uvicorn.access - 172.17.0.1:33932 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:20:29 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:20:29 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:20:29 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:20:29 - docling_serve.app - [TENANT_ID] Task 145b0079-6b2d-4930-82cf-6091b3ca94f8 created with tenant_id='default' +INFO: 04:20:29 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 145b0079-6b2d-4930-82cf-6091b3ca94f8 +INFO: 04:20:29 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:20:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a +INFO: 04:20:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:20:29,450 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:29,450 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:20:29,508 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:29,508 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:20:29,541 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:29,541 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:20:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:20:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:20:30 - docling.document_converter - Going to convert document batch... +INFO: 04:20:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:20:30 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:20:30 - docling.document_converter - Finished converting document file in 0.38 sec. +INFO: 04:20:30 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:20:30 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 145b0079-6b2d-4930-82cf-6091b3ca94f8 in 0.38 seconds +INFO: 04:20:31 - uvicorn.access - 172.17.0.1:33932 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:20:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:20:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:20:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:20:31 - docling_serve.app - [TENANT_ID] Task 65416e9a-6a1e-472e-8fdf-2628cdd3f2b0 created with tenant_id='default' +INFO: 04:20:31 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 65416e9a-6a1e-472e-8fdf-2628cdd3f2b0 +INFO: 04:20:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:20:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 +INFO: 04:20:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:20:31,468 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:31,469 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:20:31,559 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:31,559 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:20:31,612 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:20:31,613 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:20:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:20:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:20:32 - docling.document_converter - Going to convert document batch... +INFO: 04:20:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:20:32 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:20:32 - docling.document_converter - Finished converting document file in 0.39 sec. +INFO: 04:20:32 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:20:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 65416e9a-6a1e-472e-8fdf-2628cdd3f2b0 in 0.41 seconds +INFO: 04:20:33 - uvicorn.access - 172.17.0.1:33932 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:20:33 - uvicorn.access - 172.17.0.1:33932 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:20:33 - uvicorn.access - 172.17.0.1:33932 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2349,120 +2669,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:33:13 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:13 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:33:13 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:33:13 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:33:13 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/ready$,/readyz$,/livez$,/healthz$,/health$) -INFO: 04:33:13 - uvicorn.error - Started server process [1] -INFO: 04:33:13 - uvicorn.error - Waiting for application startup. -INFO: 04:33:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:17 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:33:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:17 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:33:17 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:33:17 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 04:33:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:17 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-10-19 04:33:17.336730028 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:33:17 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:33:17,647 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:17,649 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:33:17,752 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:17,752 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:33:17,800 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:17,800 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:33:17 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:33:17 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:33:20 - docling.document_converter - Going to convert document batch... -INFO: 04:33:20 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:33:20 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:33:21 - docling.document_converter - Finished converting document file in 0.80 sec. -WARNING: 04:33:21 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:33:21 - docling_jobkit.convert.results - Processed 1 docs in 0.87 seconds. -INFO: 04:33:21 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job a8e6f59f-264a-4bf8-9840-449cad9a247b in 0.87 seconds -INFO: 04:33:21 - uvicorn.access - 172.17.0.1:55062 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:33:21 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:33:21 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:33:21 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:33:21 - docling_serve.app - [TENANT_ID] Task 48bacae6-b705-41c5-adef-1bf2e05f2b12 created with tenant_id='default' -INFO: 04:33:21 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 48bacae6-b705-41c5-adef-1bf2e05f2b12 -INFO: 04:33:21 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:33:21 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 04:33:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:33:21,292 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:21,293 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:33:21,386 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:21,386 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:33:21,433 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:21,433 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:33:21 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:33:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:33:22 - docling.document_converter - Going to convert document batch... -INFO: 04:33:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:33:22 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:33:22 - docling.document_converter - Finished converting document file in 0.56 sec. -INFO: 04:33:22 - docling_jobkit.convert.results - Processed 1 docs in 0.56 seconds. -INFO: 04:33:22 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 48bacae6-b705-41c5-adef-1bf2e05f2b12 in 0.56 seconds -INFO: 04:33:23 - uvicorn.access - 172.17.0.1:55062 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:33:23 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:33:23 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:33:23 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:33:23 - docling_serve.app - [TENANT_ID] Task cc957ec9-91a6-46a8-ac43-a259a1af8e9d created with tenant_id='default' -INFO: 04:33:23 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task cc957ec9-91a6-46a8-ac43-a259a1af8e9d -INFO: 04:33:23 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:33:23 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 04:33:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:33:23,296 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:23,296 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:33:23,393 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:23,394 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:33:23,442 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:33:23,442 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:33:23 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:33:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:33:24 - docling.document_converter - Going to convert document batch... -INFO: 04:33:24 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:33:24 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:33:24 - docling.document_converter - Finished converting document file in 0.51 sec. -INFO: 04:33:24 - docling_jobkit.convert.results - Processed 1 docs in 0.55 seconds. -INFO: 04:33:24 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job cc957ec9-91a6-46a8-ac43-a259a1af8e9d in 0.55 seconds -INFO: 04:33:25 - uvicorn.access - 172.17.0.1:55062 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:33:25 - uvicorn.access - 172.17.0.1:55062 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:33:25 - uvicorn.access - 172.17.0.1:55062 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:18:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:18:56 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:18:56 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:18:56 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:18:56 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/readyz$,/health$,/livez$,/ready$,/metrics$) +INFO: 04:18:56 - uvicorn.error - Started server process [1] +INFO: 04:18:56 - uvicorn.error - Waiting for application startup. +INFO: 04:18:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:18:58 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:18:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:18:58 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:18:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:18:58 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 04:18:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:18:58 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-10-26 04:18:58.951123245 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:18:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:18:59,130 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:18:59,130 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:18:59,186 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:18:59,186 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:18:59,210 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:18:59,210 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:18:59 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:18:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:01 - docling.document_converter - Going to convert document batch... +INFO: 04:19:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:01 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:01 - docling.document_converter - Finished converting document file in 0.74 sec. +WARNING: 04:19:01 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:19:01 - docling_jobkit.convert.results - Processed 1 docs in 0.77 seconds. +INFO: 04:19:01 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 80617c7c-babe-4c20-8ec9-b939444330ff in 0.77 seconds +INFO: 04:19:02 - uvicorn.access - 172.17.0.1:47612 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:02 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:19:02 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:19:02 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:19:02 - docling_serve.app - [TENANT_ID] Task 6efb6b65-5211-4da7-8310-ba2ceff8296a created with tenant_id='default' +INFO: 04:19:02 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 6efb6b65-5211-4da7-8310-ba2ceff8296a +INFO: 04:19:02 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:02 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 04:19:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:19:02,176 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:19:02,176 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:19:02,230 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:19:02,230 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:19:02,259 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:19:02,259 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:02 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:02 - docling.document_converter - Going to convert document batch... +INFO: 04:19:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:02 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:03 - docling.document_converter - Finished converting document file in 0.37 sec. +INFO: 04:19:03 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:19:03 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 6efb6b65-5211-4da7-8310-ba2ceff8296a in 0.37 seconds +INFO: 04:19:04 - uvicorn.access - 172.17.0.1:47612 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:04 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:19:04 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:19:04 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:19:04 - docling_serve.app - [TENANT_ID] Task 278cf101-464d-4bff-a1ea-a946a1d79715 created with tenant_id='default' +INFO: 04:19:04 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 278cf101-464d-4bff-a1ea-a946a1d79715 +INFO: 04:19:04 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:04 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 04:19:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:19:04,190 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:19:04,190 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:19:04,243 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:19:04,243 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:19:04,282 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:19:04,282 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:04 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:04 - docling.document_converter - Going to convert document batch... +INFO: 04:19:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:04 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:05 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 04:19:05 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:19:05 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 278cf101-464d-4bff-a1ea-a946a1d79715 in 0.38 seconds +INFO: 04:19:06 - uvicorn.access - 172.17.0.1:47612 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:06 - uvicorn.access - 172.17.0.1:47612 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:19:06 - uvicorn.access - 172.17.0.1:47612 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2500,120 +2820,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:31:23 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:31:23 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:31:23 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:31:23 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:31:23 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/healthz$,/health$,/metrics$,/ready$,/livez$) -INFO: 04:31:23 - uvicorn.error - Started server process [1] -INFO: 04:31:23 - uvicorn.error - Waiting for application startup. -INFO: 04:31:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:31:26 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:31:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:31:26 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:31:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:31:26 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 04:31:26 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:31:26 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-10-19 04:31:27.022644647 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:31:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:31:27,318 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:27,319 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:31:27,426 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:27,426 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:31:27,478 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:27,478 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:31:27 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:31:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:31:31 - docling.document_converter - Going to convert document batch... -INFO: 04:31:31 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:31:31 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:31:31 - docling.document_converter - Finished converting document file in 0.83 sec. -WARNING: 04:31:31 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:31:31 - docling_jobkit.convert.results - Processed 1 docs in 0.90 seconds. -INFO: 04:31:31 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e49348a3-e478-458e-981f-ea98527bbc33 in 0.90 seconds -INFO: 04:31:31 - uvicorn.access - 172.17.0.1:49568 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:31:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:31:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:31:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:31:31 - docling_serve.app - [TENANT_ID] Task 56a3a2ef-942e-409e-86c2-48030ad3ea5a created with tenant_id='default' -INFO: 04:31:31 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 56a3a2ef-942e-409e-86c2-48030ad3ea5a -INFO: 04:31:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:31:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 04:31:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:31:31,531 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:31,531 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:31:31,624 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:31,624 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:31:31,670 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:31,670 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:31:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:31:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:31:32 - docling.document_converter - Going to convert document batch... -INFO: 04:31:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:31:32 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:31:32 - docling.document_converter - Finished converting document file in 0.48 sec. -INFO: 04:31:32 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. -INFO: 04:31:32 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 56a3a2ef-942e-409e-86c2-48030ad3ea5a in 0.48 seconds -INFO: 04:31:33 - uvicorn.access - 172.17.0.1:49568 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:31:33 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:31:33 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:31:33 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:31:33 - docling_serve.app - [TENANT_ID] Task 67e63e08-3c52-41ad-afbc-1736d4099e78 created with tenant_id='default' -INFO: 04:31:33 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 67e63e08-3c52-41ad-afbc-1736d4099e78 -INFO: 04:31:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:31:33 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 04:31:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:31:33,536 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:33,537 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:31:33,631 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:33,631 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:31:33,678 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:31:33,679 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:31:33 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:31:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:31:34 - docling.document_converter - Going to convert document batch... -INFO: 04:31:34 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:31:34 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:31:34 - docling.document_converter - Finished converting document file in 0.40 sec. -INFO: 04:31:34 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. -INFO: 04:31:34 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 67e63e08-3c52-41ad-afbc-1736d4099e78 in 0.45 seconds -INFO: 04:31:35 - uvicorn.access - 172.17.0.1:49568 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:31:35 - uvicorn.access - 172.17.0.1:49568 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:31:35 - uvicorn.access - 172.17.0.1:49568 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:17:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:17:45 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:17:45 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:17:45 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:17:45 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/metrics$,/livez$,/ready$,/healthz$,/health$) +INFO: 04:17:46 - uvicorn.error - Started server process [1] +INFO: 04:17:46 - uvicorn.error - Waiting for application startup. +INFO: 04:17:48 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:17:48 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:17:48 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:17:48 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:17:48 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:17:48 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 04:17:48 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:17:48 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-10-26 04:17:48.455861177 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:17:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:17:48,641 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:48,642 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:17:48,700 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:48,700 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:17:48,725 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:48,725 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:17:48 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:17:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:17:50 - docling.document_converter - Going to convert document batch... +INFO: 04:17:50 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:17:50 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:17:50 - docling.document_converter - Finished converting document file in 0.72 sec. +WARNING: 04:17:51 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:17:51 - docling_jobkit.convert.results - Processed 1 docs in 0.75 seconds. +INFO: 04:17:51 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job aae0a93b-e729-4893-9542-210b23b5ed1a in 0.75 seconds +INFO: 04:17:51 - uvicorn.access - 172.17.0.1:55160 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:17:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:17:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:17:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:17:51 - docling_serve.app - [TENANT_ID] Task 9138bcd0-e531-4571-a15c-e6f6853ddccc created with tenant_id='default' +INFO: 04:17:51 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 9138bcd0-e531-4571-a15c-e6f6853ddccc +INFO: 04:17:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:17:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 04:17:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:17:51,803 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:51,803 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:17:51,859 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:51,859 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:17:51,883 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:51,883 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:17:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:17:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:17:52 - docling.document_converter - Going to convert document batch... +INFO: 04:17:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:17:52 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:17:52 - docling.document_converter - Finished converting document file in 0.39 sec. +INFO: 04:17:52 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:17:52 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 9138bcd0-e531-4571-a15c-e6f6853ddccc in 0.39 seconds +INFO: 04:17:53 - uvicorn.access - 172.17.0.1:55160 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:17:53 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:17:53 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:17:53 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:17:53 - docling_serve.app - [TENANT_ID] Task 03b35cae-bf13-46bc-bd82-437c499f6e3d created with tenant_id='default' +INFO: 04:17:53 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 03b35cae-bf13-46bc-bd82-437c499f6e3d +INFO: 04:17:53 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:17:53 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 04:17:53 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:17:53,818 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:53,818 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:17:53,894 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:53,894 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:17:53,919 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:17:53,919 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:17:54 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:17:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:17:54 - docling.document_converter - Going to convert document batch... +INFO: 04:17:54 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:17:54 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:17:54 - docling.document_converter - Finished converting document file in 0.40 sec. +INFO: 04:17:54 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:17:54 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 03b35cae-bf13-46bc-bd82-437c499f6e3d in 0.43 seconds +INFO: 04:17:55 - uvicorn.access - 172.17.0.1:55160 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:17:56 - uvicorn.access - 172.17.0.1:55160 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:17:56 - uvicorn.access - 172.17.0.1:55160 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2651,120 +2971,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:29:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:55 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:29:55 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:29:55 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:29:55 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/healthz$,/health$,/livez$,/ready$,/metrics$) -INFO: 04:29:55 - uvicorn.error - Started server process [1] -INFO: 04:29:55 - uvicorn.error - Waiting for application startup. -INFO: 04:29:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:58 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:29:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:58 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:29:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:29:58 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 04:29:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:58 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-10-19 04:29:58.796408841 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:29:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:29:59,068 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:29:59,070 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:29:59,166 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:29:59,166 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:29:59,212 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:29:59,212 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:29:59 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:29:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:30:02 - docling.document_converter - Going to convert document batch... -INFO: 04:30:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:30:02 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:30:02 - docling.document_converter - Finished converting document file in 0.81 sec. -WARNING: 04:30:02 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:30:02 - docling_jobkit.convert.results - Processed 1 docs in 0.89 seconds. -INFO: 04:30:02 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ca25e21d-91d4-43ce-9b42-9ad96f9e1630 in 0.89 seconds -INFO: 04:30:02 - uvicorn.access - 172.17.0.1:59142 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:30:02 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:30:02 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:30:02 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:30:02 - docling_serve.app - [TENANT_ID] Task 6ef2b0d6-4c69-45d4-a097-113df0091000 created with tenant_id='default' -INFO: 04:30:02 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 6ef2b0d6-4c69-45d4-a097-113df0091000 -INFO: 04:30:02 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:30:02 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 -INFO: 04:30:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:30:02,883 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:30:02,883 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:30:02,976 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:30:02,977 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:30:03,024 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:30:03,025 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:30:03 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:30:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:30:04 - docling.document_converter - Going to convert document batch... -INFO: 04:30:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:30:04 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:30:04 - docling.document_converter - Finished converting document file in 0.49 sec. -INFO: 04:30:04 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:30:04 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 6ef2b0d6-4c69-45d4-a097-113df0091000 in 0.50 seconds -INFO: 04:30:04 - uvicorn.access - 172.17.0.1:59142 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:30:04 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:30:04 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:30:04 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:30:04 - docling_serve.app - [TENANT_ID] Task 0373e9a1-5219-479a-a969-3d8276a02ff4 created with tenant_id='default' -INFO: 04:30:04 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 0373e9a1-5219-479a-a969-3d8276a02ff4 -INFO: 04:30:04 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:30:04 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 -INFO: 04:30:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:30:04,910 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:30:04,910 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:30:05,014 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:30:05,014 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:30:05,062 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:30:05,062 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:30:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:30:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:30:06 - docling.document_converter - Going to convert document batch... -INFO: 04:30:06 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:30:06 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:30:06 - docling.document_converter - Finished converting document file in 0.55 sec. -INFO: 04:30:06 - docling_jobkit.convert.results - Processed 1 docs in 0.60 seconds. -INFO: 04:30:06 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 0373e9a1-5219-479a-a969-3d8276a02ff4 in 0.60 seconds -INFO: 04:30:06 - uvicorn.access - 172.17.0.1:59142 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:30:07 - uvicorn.access - 172.17.0.1:59142 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:30:07 - uvicorn.access - 172.17.0.1:59142 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:16:23 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:16:23 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:16:23 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:16:23 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:16:23 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/ready$,/livez$,/metrics$,/healthz$,/readyz$) +INFO: 04:16:23 - uvicorn.error - Started server process [1] +INFO: 04:16:23 - uvicorn.error - Waiting for application startup. +INFO: 04:16:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:16:25 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:16:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:16:25 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:16:25 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:16:25 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 04:16:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:16:25 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-10-26 04:16:25.717399371 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:16:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:16:25,872 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:25,873 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:16:25,928 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:25,928 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:16:25,953 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:25,954 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:16:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:16:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:16:28 - docling.document_converter - Going to convert document batch... +INFO: 04:16:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:16:28 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:16:28 - docling.document_converter - Finished converting document file in 0.72 sec. +WARNING: 04:16:28 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:16:28 - docling_jobkit.convert.results - Processed 1 docs in 0.75 seconds. +INFO: 04:16:28 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 54e9451f-978b-48ad-a535-e5002976c6dd in 0.75 seconds +INFO: 04:16:29 - uvicorn.access - 172.17.0.1:47512 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:16:29 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:16:29 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:16:29 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:16:29 - docling_serve.app - [TENANT_ID] Task 625b6da2-911b-4e62-bd1c-7c9d1be952da created with tenant_id='default' +INFO: 04:16:29 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 625b6da2-911b-4e62-bd1c-7c9d1be952da +INFO: 04:16:29 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:16:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 +INFO: 04:16:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:16:29,279 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:29,280 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:16:29,336 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:29,337 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:16:29,362 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:29,362 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:16:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:16:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:16:30 - docling.document_converter - Going to convert document batch... +INFO: 04:16:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:16:30 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:16:30 - docling.document_converter - Finished converting document file in 0.38 sec. +INFO: 04:16:30 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:16:30 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 625b6da2-911b-4e62-bd1c-7c9d1be952da in 0.38 seconds +INFO: 04:16:31 - uvicorn.access - 172.17.0.1:47512 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:16:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:16:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:16:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:16:31 - docling_serve.app - [TENANT_ID] Task 86fe0471-fba5-4992-a905-fb31e778de84 created with tenant_id='default' +INFO: 04:16:31 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 86fe0471-fba5-4992-a905-fb31e778de84 +INFO: 04:16:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:16:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 +INFO: 04:16:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:16:31,296 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:31,297 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:16:31,351 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:31,351 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:16:31,376 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:16:31,376 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:16:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:16:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:16:32 - docling.document_converter - Going to convert document batch... +INFO: 04:16:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:16:32 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:16:32 - docling.document_converter - Finished converting document file in 0.35 sec. +INFO: 04:16:32 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:16:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 86fe0471-fba5-4992-a905-fb31e778de84 in 0.37 seconds +INFO: 04:16:33 - uvicorn.access - 172.17.0.1:47512 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:16:33 - uvicorn.access - 172.17.0.1:47512 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:16:33 - uvicorn.access - 172.17.0.1:47512 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2802,120 +3122,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:28:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:28:12 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:28:12 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:28:12 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:28:12 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/health$,/ready$,/healthz$,/readyz$) -INFO: 04:28:12 - uvicorn.error - Started server process [1] -INFO: 04:28:12 - uvicorn.error - Waiting for application startup. -INFO: 04:28:15 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:28:15 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:28:15 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:28:15 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:28:15 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:28:15 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf -INFO: 04:28:15 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:28:15 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-10-19 04:28:15.908922764 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:28:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:28:16,213 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:16,215 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:28:16,310 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:16,310 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:28:16,356 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:16,356 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:28:16 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:28:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:28:19 - docling.document_converter - Going to convert document batch... -INFO: 04:28:19 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:28:19 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:28:19 - docling.document_converter - Finished converting document file in 0.53 sec. -WARNING: 04:28:19 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:28:19 - docling_jobkit.convert.results - Processed 1 docs in 0.87 seconds. -INFO: 04:28:19 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b4c6c8bd-94c3-48b5-85c2-b72e9897efc3 in 0.87 seconds -INFO: 04:28:19 - uvicorn.access - 172.17.0.1:52166 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:28:19 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:28:19 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:28:19 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:28:19 - docling_serve.app - [TENANT_ID] Task 632cdded-0b23-457f-af7d-940468ccc310 created with tenant_id='default' -INFO: 04:28:19 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 632cdded-0b23-457f-af7d-940468ccc310 -INFO: 04:28:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:28:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b -INFO: 04:28:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:28:19,732 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:19,733 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:28:19,852 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:19,852 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:28:19,900 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:19,900 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:28:20 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:28:20 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:28:21 - docling.document_converter - Going to convert document batch... -INFO: 04:28:21 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:28:21 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:28:21 - docling.document_converter - Finished converting document file in 0.71 sec. -INFO: 04:28:21 - docling_jobkit.convert.results - Processed 1 docs in 0.72 seconds. -INFO: 04:28:21 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 632cdded-0b23-457f-af7d-940468ccc310 in 0.72 seconds -INFO: 04:28:21 - uvicorn.access - 172.17.0.1:52166 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:28:21 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:28:21 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:28:21 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:28:21 - docling_serve.app - [TENANT_ID] Task ccafa3ab-576e-423a-86cc-2f85ba37ec69 created with tenant_id='default' -INFO: 04:28:21 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ccafa3ab-576e-423a-86cc-2f85ba37ec69 -INFO: 04:28:21 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:28:21 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb -INFO: 04:28:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-10-19 04:28:21,745 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:21,745 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:28:21,847 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:21,847 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:28:21,895 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:28:21,896 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:28:22 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:28:22 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:28:23 - docling.document_converter - Going to convert document batch... -INFO: 04:28:23 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:28:23 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:28:23 - docling.document_converter - Finished converting document file in 0.48 sec. -INFO: 04:28:23 - docling_jobkit.convert.results - Processed 1 docs in 0.53 seconds. -INFO: 04:28:23 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ccafa3ab-576e-423a-86cc-2f85ba37ec69 in 0.53 seconds -INFO: 04:28:23 - uvicorn.access - 172.17.0.1:52166 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:28:23 - uvicorn.access - 172.17.0.1:52166 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:28:23 - uvicorn.access - 172.17.0.1:52166 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:15:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:15:17 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:15:17 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:15:17 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:15:17 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/healthz$,/livez$,/ready$,/readyz$,/metrics$) +INFO: 04:15:17 - uvicorn.error - Started server process [1] +INFO: 04:15:17 - uvicorn.error - Waiting for application startup. +INFO: 04:15:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:15:19 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:15:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:15:19 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:15:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:15:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf +INFO: 04:15:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:15:19 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-10-26 04:15:19.742192006 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:15:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:15:19,917 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:19,918 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:15:19,972 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:19,972 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:15:19,996 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:19,996 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:15:20 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:15:20 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:15:22 - docling.document_converter - Going to convert document batch... +INFO: 04:15:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:15:22 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:15:22 - docling.document_converter - Finished converting document file in 0.37 sec. +WARNING: 04:15:22 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:15:22 - docling_jobkit.convert.results - Processed 1 docs in 0.72 seconds. +INFO: 04:15:22 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job cfbd23f8-e801-4124-b605-8516ecfbc71e in 0.72 seconds +INFO: 04:15:23 - uvicorn.access - 172.17.0.1:36100 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:15:23 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:15:23 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:15:23 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:15:23 - docling_serve.app - [TENANT_ID] Task 312f1b7f-8443-480c-8296-dab475a17cea created with tenant_id='default' +INFO: 04:15:23 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 312f1b7f-8443-480c-8296-dab475a17cea +INFO: 04:15:23 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:15:23 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b +INFO: 04:15:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:15:23,241 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:23,241 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:15:23,293 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:23,293 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:15:23,318 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:23,318 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:15:23 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:15:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:15:23 - docling.document_converter - Going to convert document batch... +INFO: 04:15:23 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:15:23 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:15:23 - docling.document_converter - Finished converting document file in 0.26 sec. +INFO: 04:15:23 - docling_jobkit.convert.results - Processed 1 docs in 0.26 seconds. +INFO: 04:15:23 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 312f1b7f-8443-480c-8296-dab475a17cea in 0.26 seconds +INFO: 04:15:25 - uvicorn.access - 172.17.0.1:36100 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:15:25 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:15:25 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:15:25 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:15:25 - docling_serve.app - [TENANT_ID] Task b54608f1-adaf-44d9-875f-015cda2fa2b6 created with tenant_id='default' +INFO: 04:15:25 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task b54608f1-adaf-44d9-875f-015cda2fa2b6 +INFO: 04:15:25 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:15:25 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb +INFO: 04:15:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-10-26 04:15:25,255 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:25,255 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-10-26 04:15:25,308 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:25,308 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-10-26 04:15:25,332 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-10-26 04:15:25,332 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:15:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:15:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:15:26 - docling.document_converter - Going to convert document batch... +INFO: 04:15:26 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:15:26 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:15:26 - docling.document_converter - Finished converting document file in 0.35 sec. +INFO: 04:15:26 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:15:26 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b54608f1-adaf-44d9-875f-015cda2fa2b6 in 0.37 seconds +INFO: 04:15:27 - uvicorn.access - 172.17.0.1:36100 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:15:27 - uvicorn.access - 172.17.0.1:36100 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:15:27 - uvicorn.access - 172.17.0.1:36100 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2953,37 +3273,37 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -2026-10-19 04:26:28.062780940 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -[INFO] 2026-10-19 04:26:28,361 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:26:28,363 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-10-19 04:26:28,456 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:26:28,457 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-10-19 04:26:28,504 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-10-19 04:26:28,504 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx - Loading weights: 0%| | 0/770 [00:00