From f885177268835d045856e1e6bd50bc59d76275a9 Mon Sep 17 00:00:00 2001 From: "docling-java-ops[bot]" <245010719+docling-java-ops[bot]@users.noreply.github.com> Date: Mon, 3 Aug 2026 05:22:02 +0000 Subject: [PATCH] docs: Update docling-serve compatibility table (from Version tests run # 62) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- .../docling-serve/serve-compatibility.md | 2933 +++++++++-------- 1 file changed, 1637 insertions(+), 1296 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 0a581a8..914251a 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 2026-07-27T05:21:16.757408873Z +# Results for ghcr.io/docling-project/docling-serve as of 2026-08-03T05:21:58.408167679Z Here are the results: | Tag | Result | Details | | --- | ------ | ------- | +| v1.29.0 | ✅ SUCCESS | [Click for run details](#v1.29.0-details) | +| v1.28.0 | ✅ SUCCESS | [Click for run details](#v1.28.0-details) | | v1.27.0 | ✅ SUCCESS | [Click for run details](#v1.27.0-details) | | v1.26.0 | ✅ SUCCESS | [Click for run details](#v1.26.0-details) | | v1.25.0 | ✅ SUCCESS | [Click for run details](#v1.25.0-details) | @@ -48,9 +50,9 @@ Here are the results: ## Details -### ghcr.io/docling-project/docling-serve:v1.27.0 +### ghcr.io/docling-project/docling-serve:v1.29.0 -
+
Click to expand #### Message @@ -59,7 +61,7 @@ Here are the results: Click to collapse ~~~markdown -Tag v1.27.0 is ok +Tag v1.29.0 is ok ~~~
@@ -78,136 +80,475 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:20:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:20:59 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:20:59 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:20:59 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:20:59 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/healthz$,/health$,/livez$,/metrics$,/readyz$) -INFO: 05:21:00 - uvicorn.error - Started server process [1] -INFO: 05:21:00 - uvicorn.error - Waiting for application startup. -INFO: 05:21:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:03 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:21:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:03 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:21:03 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 -INFO: 05:21:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:03 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 05:21:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-07-27 05:21:03.571250156 [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: 05:21:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:21:03,779 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:03,780 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-07-27 05:21:03,837 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:03,837 [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] 2026-07-27 05:21:03,882 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:03,882 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 05:21:03 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:21:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:51 - docling.document_converter - Going to convert document batch... +INFO: 05:21:51 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:51 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:51 - docling.document_converter - Finished converting document file in 0.39 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: 05:21:51 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:21:51 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 05:21:51 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 0ee427cf-5177-4c8e-9754-c900cb520787 in 0.43 seconds +INFO: 05:21:51 - uvicorn.access - 172.17.0.1:55888 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:21:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:21:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:21:51 - docling_serve.app - [TENANT_ID] Task b2598167-aa8d-46d1-950f-f7afe1ef7109 created with tenant_id='default' +INFO: 05:21:51 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b2598167-aa8d-46d1-950f-f7afe1ef7109 +INFO: 05:21:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:21:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash ab12ef348c8fc273bf2be7a49773b303 +INFO: 05:21:51 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:21:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:21:51,924 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:51,924 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:21:51,974 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:51,974 [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] 2026-08-03 05:21:52,013 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:52,013 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:21:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:21:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:52 - docling.document_converter - Going to convert document batch... +INFO: 05:21:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:52 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:52 - docling.document_converter - Finished converting document file in 0.24 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: 05:21:52 - docling_jobkit.convert.results - Processed 1 docs in 0.24 seconds. +INFO: 05:21:52 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b2598167-aa8d-46d1-950f-f7afe1ef7109 in 0.24 seconds +INFO: 05:21:53 - uvicorn.access - 172.17.0.1:55888 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:53 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:21:53 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:21:53 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:21:53 - docling_serve.app - [TENANT_ID] Task a49d8a5f-be97-4b69-b18f-bfda61e1cfbc created with tenant_id='default' +INFO: 05:21:53 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task a49d8a5f-be97-4b69-b18f-bfda61e1cfbc +INFO: 05:21:53 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:21:53 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b3849eabdc7ecae5f3d54428a0162342 +INFO: 05:21:53 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:21:53 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:21:53,932 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:53,933 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:21:53,980 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:53,980 [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] 2026-08-03 05:21:54,020 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:54,021 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:21:54 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:21:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:54 - docling.document_converter - Going to convert document batch... +INFO: 05:21:54 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:54 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:54 - docling.document_converter - Finished converting document file in 0.21 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: 05:21:54 - docling_jobkit.convert.results - Processed 1 docs in 0.23 seconds. +INFO: 05:21:54 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job a49d8a5f-be97-4b69-b18f-bfda61e1cfbc in 0.23 seconds +INFO: 05:21:55 - uvicorn.access - 172.17.0.1:55888 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:56 - uvicorn.access - 172.17.0.1:55888 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:21:56 - uvicorn.access - 172.17.0.1:55888 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 + +``` + +
+ + + +### ghcr.io/docling-project/docling-serve:v1.28.0 + +
+Click to expand + +#### Message + +
+Click to collapse + +~~~markdown +Tag v1.28.0 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: 05:20:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:20:49 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:20:49 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 05:20:50 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 05:20:50 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:20:50 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:20:50 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/metrics$,/ready$,/healthz$,/health$,/livez$) +INFO: 05:20:50 - uvicorn.error - Started server process [1] +INFO: 05:20:50 - uvicorn.error - Waiting for application startup. +INFO: 05:20:53 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:20:54 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:20:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:20:54 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:20:54 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:20:54 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 05:20:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:20:54 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 05:20:54 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-08-03 05:20:54.377505519 [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: 05:20:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:20:54,673 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:20:54,674 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:20:54,767 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:20:54,768 [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] 2026-08-03 05:20:54,852 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:20:54,852 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:20:55 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:20:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:20:59 - docling.document_converter - Going to convert document batch... +INFO: 05:20:59 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:20:59 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:20:59 - docling.document_converter - Finished converting document file in 0.64 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: 05:20:59 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:20:59 - docling_jobkit.convert.results - Processed 1 docs in 0.69 seconds. +INFO: 05:20:59 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 198b1270-88f6-4e9a-842e-6abebc3dd254 in 0.69 seconds +INFO: 05:21:01 - uvicorn.access - 172.17.0.1:53000 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:01 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:21:01 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:21:01 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:21:01 - docling_serve.app - [TENANT_ID] Task 3bfde75c-1148-4d85-8146-850afdd417fa created with tenant_id='default' +INFO: 05:21:01 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 3bfde75c-1148-4d85-8146-850afdd417fa +INFO: 05:21:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:21:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 05:21:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:21:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:21:01,349 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:01,349 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:21:01,411 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:01,411 [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] 2026-08-03 05:21:01,552 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:01,552 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:21:01 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:21:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:03 - docling.document_converter - Going to convert document batch... +INFO: 05:21:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:03 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:03 - docling.document_converter - Finished converting document file in 0.32 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: 05:21:03 - docling_jobkit.convert.results - Processed 1 docs in 0.32 seconds. +INFO: 05:21:03 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 3bfde75c-1148-4d85-8146-850afdd417fa in 0.32 seconds +INFO: 05:21:05 - uvicorn.access - 172.17.0.1:53000 - "POST /v1/convert/source HTTP/1.1" 200 INFO: 05:21:05 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') INFO: 05:21:05 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' INFO: 05:21:05 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:21:05 - docling_serve.app - [TENANT_ID] Task c021b464-0ec3-4c18-9a3f-0b4f407d9935 created with tenant_id='default' -INFO: 05:21:05 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task c021b464-0ec3-4c18-9a3f-0b4f407d9935 +INFO: 05:21:05 - docling_serve.app - [TENANT_ID] Task 86fc525a-040c-4a49-86dd-b347bf0687d8 created with tenant_id='default' +INFO: 05:21:05 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 86fc525a-040c-4a49-86dd-b347bf0687d8 INFO: 05:21:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 05:21:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc INFO: 05:21:05 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. INFO: 05:21:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:21:05,694 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:05,694 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-07-27 05:21:05,748 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:05,748 [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] 2026-07-27 05:21:05,793 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:05,793 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +[INFO] 2026-08-03 05:21:05,358 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:05,358 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:21:05,468 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:05,468 [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] 2026-08-03 05:21:05,528 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:21:05,528 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx INFO: 05:21:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. INFO: 05:21:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] INFO: 05:21:07 - docling.document_converter - Going to convert document batch... INFO: 05:21:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a INFO: 05:21:07 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:21:07 - docling.document_converter - Finished converting document file in 0.80 sec. +INFO: 05:21:07 - docling.document_converter - Finished converting document file in 0.35 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: 05:21:07 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 05:21:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 86fc525a-040c-4a49-86dd-b347bf0687d8 in 0.38 seconds +INFO: 05:21:09 - uvicorn.access - 172.17.0.1:53000 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:09 - uvicorn.access - 172.17.0.1:53000 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:21:09 - uvicorn.access - 172.17.0.1:53000 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 + +``` + +
+ +
+ +### ghcr.io/docling-project/docling-serve:v1.27.0 + +
+Click to expand + +#### Message + +
+Click to collapse + +~~~markdown +Tag v1.27.0 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: 05:19:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:24 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:19:24 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:19:24 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:19:24 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/ready$,/metrics$,/livez$,/healthz$,/readyz$) +INFO: 05:19:24 - uvicorn.error - Started server process [1] +INFO: 05:19:24 - uvicorn.error - Waiting for application startup. +INFO: 05:19:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:28 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:19:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:28 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:19:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:19:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 05:19:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:28 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 05:19:29 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-08-03 05:19:29.035405552 [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: 05:19:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:19:29,339 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:29,340 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:19:29,417 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:29,417 [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] 2026-08-03 05:19:29,504 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:29,505 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:19:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:19:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:19:32 - docling.document_converter - Going to convert document batch... +INFO: 05:19:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:19:32 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:19:32 - 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( -WARNING: 05:21:07 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:21:07 - docling_jobkit.convert.results - Processed 1 docs in 0.83 seconds. -INFO: 05:21:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c021b464-0ec3-4c18-9a3f-0b4f407d9935 in 0.83 seconds -INFO: 05:21:07 - uvicorn.access - 172.17.0.1:39382 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:21:07 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:21:07 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:21:07 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:21:07 - docling_serve.app - [TENANT_ID] Task ef84dead-7d15-4fb8-b6c3-6d084dbcf9a1 created with tenant_id='default' -INFO: 05:21:07 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task ef84dead-7d15-4fb8-b6c3-6d084dbcf9a1 -INFO: 05:21:07 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:07 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 -INFO: 05:21:07 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 05:21:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:21:07,709 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:07,709 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-07-27 05:21:07,759 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:07,760 [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] 2026-07-27 05:21:07,816 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:07,816 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 05:21:07 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:21:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:21:09 - docling.document_converter - Going to convert document batch... -INFO: 05:21:09 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:21:09 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:21:09 - docling.document_converter - Finished converting document file in 0.60 sec. +WARNING: 05:19:32 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:19:32 - docling_jobkit.convert.results - Processed 1 docs in 0.42 seconds. +INFO: 05:19:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7dc617e5-7c7e-4add-a1f8-dcdf59b358f0 in 0.42 seconds +INFO: 05:19:33 - uvicorn.access - 172.17.0.1:35210 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:19:33 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:19:33 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:19:33 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:19:33 - docling_serve.app - [TENANT_ID] Task 0757bfc0-3ef3-4e0e-a568-ac7f73849039 created with tenant_id='default' +INFO: 05:19:33 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 0757bfc0-3ef3-4e0e-a568-ac7f73849039 +INFO: 05:19:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:19:33 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 05:19:33 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:19:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:19:33,534 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:33,534 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:19:33,591 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:33,591 [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] 2026-08-03 05:19:33,721 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:33,721 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:19:33 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:19:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:19:35 - docling.document_converter - Going to convert document batch... +INFO: 05:19:35 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:19:35 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:19:35 - 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: 05:21:09 - docling_jobkit.convert.results - Processed 1 docs in 0.60 seconds. -INFO: 05:21:09 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job ef84dead-7d15-4fb8-b6c3-6d084dbcf9a1 in 0.60 seconds -INFO: 05:21:09 - uvicorn.access - 172.17.0.1:39382 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:21:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:21:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:21:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:21:09 - docling_serve.app - [TENANT_ID] Task 4aacc374-3dca-41a8-84e9-80632f602f54 created with tenant_id='default' -INFO: 05:21:09 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 4aacc374-3dca-41a8-84e9-80632f602f54 -INFO: 05:21:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc -INFO: 05:21:09 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 05:21:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:21:09,725 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:09,726 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-07-27 05:21:09,774 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:09,775 [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] 2026-07-27 05:21:09,821 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:21:09,821 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 05:21:09 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:21:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:21:11 - docling.document_converter - Going to convert document batch... -INFO: 05:21:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:21:11 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:21:11 - docling.document_converter - Finished converting document file in 0.62 sec. +INFO: 05:19:35 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 05:19:35 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 0757bfc0-3ef3-4e0e-a568-ac7f73849039 in 0.38 seconds +INFO: 05:19:35 - uvicorn.access - 172.17.0.1:35210 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:19:35 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:19:35 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:19:35 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:19:35 - docling_serve.app - [TENANT_ID] Task 772fa526-e719-4acf-95fa-ee8e5a6c50f6 created with tenant_id='default' +INFO: 05:19:35 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 772fa526-e719-4acf-95fa-ee8e5a6c50f6 +INFO: 05:19:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:19:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc +INFO: 05:19:35 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:19:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:19:35,529 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:35,529 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-08-03 05:19:35,634 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:35,634 [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] 2026-08-03 05:19:35,734 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:19:35,734 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:19:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:19:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:19:37 - docling.document_converter - Going to convert document batch... +INFO: 05:19:37 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:19:37 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:19:37 - docling.document_converter - Finished converting document file in 0.31 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: 05:21:11 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. -INFO: 05:21:11 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4aacc374-3dca-41a8-84e9-80632f602f54 in 0.64 seconds -INFO: 05:21:11 - uvicorn.access - 172.17.0.1:39382 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:21:11 - uvicorn.access - 172.17.0.1:39382 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:21:11 - uvicorn.access - 172.17.0.1:39382 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:19:37 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. +INFO: 05:19:37 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 772fa526-e719-4acf-95fa-ee8e5a6c50f6 in 0.34 seconds +INFO: 05:19:37 - uvicorn.access - 172.17.0.1:35210 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:19:37 - uvicorn.access - 172.17.0.1:35210 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:19:37 - uvicorn.access - 172.17.0.1:35210 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -245,136 +586,136 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:19:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:52 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:19:52 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:19:52 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:19:52 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/readyz$,/healthz$,/livez$,/metrics$,/health$) -INFO: 05:19:52 - uvicorn.error - Started server process [1] -INFO: 05:19:52 - uvicorn.error - Waiting for application startup. -INFO: 05:19:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:56 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:19:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:56 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:19:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:19:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 -INFO: 05:19:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:56 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 05:19:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-07-27 05:19:56.439706321 [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: 05:19:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:19:57,062 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:19:57,064 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:19:57,214 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:19:57,215 [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] 2026-07-27 05:19:57,305 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:19:57,305 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:19:57 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:19:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:20:01 - docling.document_converter - Going to convert document batch... -INFO: 05:20:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:20:01 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:20:01 - docling.document_converter - Finished converting document file in 0.38 sec. +INFO: 05:17:53 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:53 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:17:53 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:17:53 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:17:53 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/metrics$,/healthz$,/ready$,/livez$,/readyz$) +INFO: 05:17:53 - uvicorn.error - Started server process [1] +INFO: 05:17:53 - uvicorn.error - Waiting for application startup. +INFO: 05:17:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:56 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:17:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:56 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:17:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:17:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 +INFO: 05:17:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:56 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 05:17:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-08-03 05:17:57.033463411 [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: 05:17:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:17:57,450 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:17:57,452 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:17:57,561 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:17:57,562 [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] 2026-08-03 05:17:57,607 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:17:57,607 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:17:57 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:17:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:18:00 - docling.document_converter - Going to convert document batch... +INFO: 05:18:00 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:18:00 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:18:00 - docling.document_converter - Finished converting document file in 0.55 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: 05:20:01 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:20:01 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. -INFO: 05:20:01 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4931a440-7157-4e8b-9c47-314eef9c0cda in 0.43 seconds -INFO: 05:20:01 - uvicorn.access - 172.17.0.1:49246 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:20:01 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:20:01 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:20:01 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:20:01 - docling_serve.app - [TENANT_ID] Task 5b5f5280-9043-46f4-8d43-33f2051ae8d1 created with tenant_id='default' -INFO: 05:20:01 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5b5f5280-9043-46f4-8d43-33f2051ae8d1 -INFO: 05:20:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:20:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac -INFO: 05:20:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 05:20:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:20:01,709 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:20:01,709 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:20:01,884 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:20:01,885 [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] 2026-07-27 05:20:01,953 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:20:01,954 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:20:02 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:20:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:20:03 - docling.document_converter - Going to convert document batch... -INFO: 05:20:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:20:03 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:20:03 - docling.document_converter - Finished converting document file in 0.44 sec. +WARNING: 05:18:00 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:18:00 - docling_jobkit.convert.results - Processed 1 docs in 0.59 seconds. +INFO: 05:18:00 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ba8613e8-d220-4aad-927d-8dfd021a9f57 in 0.59 seconds +INFO: 05:18:01 - uvicorn.access - 172.17.0.1:36072 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:18:01 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:18:01 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:18:01 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:18:01 - docling_serve.app - [TENANT_ID] Task 6302cb3a-1ebc-4cea-9a64-75d48cbfd188 created with tenant_id='default' +INFO: 05:18:01 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 6302cb3a-1ebc-4cea-9a64-75d48cbfd188 +INFO: 05:18:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:18:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac +INFO: 05:18:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:18:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:18:01,117 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:18:01,117 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:18:01,209 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:18:01,209 [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] 2026-08-03 05:18:01,257 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:18:01,257 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:18:01 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:18:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:18:02 - docling.document_converter - Going to convert document batch... +INFO: 05:18:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:18:02 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:18:02 - 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: 05:20:03 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. -INFO: 05:20:03 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5b5f5280-9043-46f4-8d43-33f2051ae8d1 in 0.44 seconds -INFO: 05:20:03 - uvicorn.access - 172.17.0.1:49246 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:20:03 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:20:03 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:20:03 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:20:03 - docling_serve.app - [TENANT_ID] Task 09c78499-c469-4373-a3c9-8c414dbe994c created with tenant_id='default' -INFO: 05:20:03 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 09c78499-c469-4373-a3c9-8c414dbe994c -INFO: 05:20:03 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:20:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 -INFO: 05:20:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 05:20:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:20:03,725 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:20:03,726 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:20:03,836 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:20:03,836 [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] 2026-07-27 05:20:03,923 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:20:03,923 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:20:04 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:20:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:20:05 - docling.document_converter - Going to convert document batch... -INFO: 05:20:05 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:20:05 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:20:05 - docling.document_converter - Finished converting document file in 0.55 sec. +INFO: 05:18:02 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 05:18:02 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 6302cb3a-1ebc-4cea-9a64-75d48cbfd188 in 0.37 seconds +INFO: 05:18:03 - uvicorn.access - 172.17.0.1:36072 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:18:03 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:18:03 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:18:03 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:18:03 - docling_serve.app - [TENANT_ID] Task ee4a1ce6-f6ce-4cde-a534-f1a6f1eb596b created with tenant_id='default' +INFO: 05:18:03 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ee4a1ce6-f6ce-4cde-a534-f1a6f1eb596b +INFO: 05:18:03 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:18:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 +INFO: 05:18:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:18:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:18:03,128 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:18:03,128 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:18:03,212 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:18:03,212 [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] 2026-08-03 05:18:03,259 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:18:03,259 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:18:03 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:18:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:18:04 - docling.document_converter - Going to convert document batch... +INFO: 05:18:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:18:04 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:18:04 - docling.document_converter - Finished converting document file in 0.33 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: 05:20:05 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. -INFO: 05:20:05 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 09c78499-c469-4373-a3c9-8c414dbe994c in 0.58 seconds -INFO: 05:20:07 - uvicorn.access - 172.17.0.1:49246 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:20:08 - uvicorn.access - 172.17.0.1:49246 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:20:08 - uvicorn.access - 172.17.0.1:49246 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:18:04 - docling_jobkit.convert.results - Processed 1 docs in 0.35 seconds. +INFO: 05:18:04 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ee4a1ce6-f6ce-4cde-a534-f1a6f1eb596b in 0.35 seconds +INFO: 05:18:05 - uvicorn.access - 172.17.0.1:36072 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:18:05 - uvicorn.access - 172.17.0.1:36072 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:18:05 - uvicorn.access - 172.17.0.1:36072 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -412,120 +753,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:18:43 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:43 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:18:43 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:18:43 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:18:43 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/ready$,/livez$,/metrics$,/readyz$) -INFO: 05:18:44 - uvicorn.error - Started server process [1] -INFO: 05:18:44 - uvicorn.error - Waiting for application startup. -INFO: 05:18:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:49 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:18:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:49 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:18:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:18:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e -INFO: 05:18:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:50 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-27 05:18:50.164893945 [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: 05:18:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:18:50,609 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:18:50,611 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:18:50,751 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:18:50,752 [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] 2026-07-27 05:18:50,815 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:18:50,815 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:18:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:18:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:18:54 - docling.document_converter - Going to convert document batch... -INFO: 05:18:54 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:18:54 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:18:54 - docling.document_converter - Finished converting document file in 1.03 sec. -WARNING: 05:18:54 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:18:54 - docling_jobkit.convert.results - Processed 1 docs in 1.08 seconds. -INFO: 05:18:54 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 70775e7a-0a2b-4117-8207-7c8e16f0ee4f in 1.08 seconds -INFO: 05:18:56 - uvicorn.access - 172.17.0.1:36590 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:18:56 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:18:56 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:18:56 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:18:56 - docling_serve.app - [TENANT_ID] Task b25b520d-be0f-4473-82a5-d021fcc38f6e created with tenant_id='default' -INFO: 05:18:56 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b25b520d-be0f-4473-82a5-d021fcc38f6e -INFO: 05:18:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:18:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a -INFO: 05:18:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:18:56,533 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:18:56,533 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:18:56,653 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:18:56,654 [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] 2026-07-27 05:18:56,742 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:18:56,742 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:18:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:18:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:18:58 - docling.document_converter - Going to convert document batch... -INFO: 05:18:58 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:18:58 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:18:58 - docling.document_converter - Finished converting document file in 0.38 sec. -INFO: 05:18:58 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. -INFO: 05:18:58 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b25b520d-be0f-4473-82a5-d021fcc38f6e in 0.38 seconds -INFO: 05:19:00 - uvicorn.access - 172.17.0.1:36590 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:19:00 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:19:00 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:19:00 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:19:00 - docling_serve.app - [TENANT_ID] Task e3ef2c06-3f56-4a10-809b-799151e7be5b created with tenant_id='default' -INFO: 05:19:00 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e3ef2c06-3f56-4a10-809b-799151e7be5b -INFO: 05:19:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:19:00 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 -INFO: 05:19:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:19:00,555 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:19:00,555 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:19:00,710 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:19:00,711 [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] 2026-07-27 05:19:00,757 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:19:00,758 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:19:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:19:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:19:02 - docling.document_converter - Going to convert document batch... -INFO: 05:19:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:19:02 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:19:02 - docling.document_converter - Finished converting document file in 0.69 sec. -INFO: 05:19:02 - docling_jobkit.convert.results - Processed 1 docs in 0.71 seconds. -INFO: 05:19:02 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e3ef2c06-3f56-4a10-809b-799151e7be5b in 0.71 seconds -INFO: 05:19:04 - uvicorn.access - 172.17.0.1:36590 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:19:04 - uvicorn.access - 172.17.0.1:36590 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:19:04 - uvicorn.access - 172.17.0.1:36590 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:16:39 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:39 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:16:39 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:16:39 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:16:39 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/health$,/livez$,/ready$,/healthz$,/readyz$) +INFO: 05:16:39 - uvicorn.error - Started server process [1] +INFO: 05:16:39 - uvicorn.error - Waiting for application startup. +INFO: 05:16:43 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:43 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:16:43 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:43 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:16:43 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:16:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e +INFO: 05:16:43 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:43 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-08-03 05:16:43.122080895 [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: 05:16:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:16:43,397 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:43,398 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:16:43,494 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:43,494 [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] 2026-08-03 05:16:43,536 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:43,536 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:16:43 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:16:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:16:46 - docling.document_converter - Going to convert document batch... +INFO: 05:16:46 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:16:46 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:16:46 - docling.document_converter - Finished converting document file in 0.43 sec. +WARNING: 05:16:46 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:16:46 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. +INFO: 05:16:46 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c31e2555-d63a-44d8-a069-5b20ac7587c5 in 0.48 seconds +INFO: 05:16:46 - uvicorn.access - 172.17.0.1:48976 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:16:46 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:16:46 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:16:46 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:16:46 - docling_serve.app - [TENANT_ID] Task 7cc7908f-b194-4967-8e9e-cd03db30222a created with tenant_id='default' +INFO: 05:16:46 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 7cc7908f-b194-4967-8e9e-cd03db30222a +INFO: 05:16:46 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:16:46 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a +INFO: 05:16:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:16:46,709 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:46,709 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:16:46,826 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:46,826 [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] 2026-08-03 05:16:46,911 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:46,911 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:16:47 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:16:47 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:16:48 - docling.document_converter - Going to convert document batch... +INFO: 05:16:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:16:48 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:16:48 - docling.document_converter - Finished converting document file in 0.58 sec. +INFO: 05:16:48 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. +INFO: 05:16:48 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 7cc7908f-b194-4967-8e9e-cd03db30222a in 0.58 seconds +INFO: 05:16:50 - uvicorn.access - 172.17.0.1:48976 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:16:50 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:16:50 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:16:50 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:16:50 - docling_serve.app - [TENANT_ID] Task b9200fef-cc36-4a09-8eb0-0c5b8b91c987 created with tenant_id='default' +INFO: 05:16:50 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task b9200fef-cc36-4a09-8eb0-0c5b8b91c987 +INFO: 05:16:50 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:16:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 +INFO: 05:16:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:16:50,680 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:50,680 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:16:50,810 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:50,810 [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] 2026-08-03 05:16:50,860 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:16:50,861 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:16:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:16:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:16:52 - docling.document_converter - Going to convert document batch... +INFO: 05:16:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:16:52 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:16:52 - docling.document_converter - Finished converting document file in 0.40 sec. +INFO: 05:16:52 - docling_jobkit.convert.results - Processed 1 docs in 0.42 seconds. +INFO: 05:16:52 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b9200fef-cc36-4a09-8eb0-0c5b8b91c987 in 0.42 seconds +INFO: 05:16:52 - uvicorn.access - 172.17.0.1:48976 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:16:52 - uvicorn.access - 172.17.0.1:48976 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:16:52 - uvicorn.access - 172.17.0.1:48976 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -563,120 +904,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:17:13 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:17:13 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:17:13 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:17:13 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:17:13 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/livez$,/readyz$,/metrics$,/healthz$,/health$) -INFO: 05:17:14 - uvicorn.error - Started server process [1] -INFO: 05:17:14 - uvicorn.error - Waiting for application startup. -INFO: 05:17:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:17:18 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:17:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:17:18 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:17:18 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:17:18 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 05:17:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:17:18 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-27 05:17:18.400430280 [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: 05:17:18 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:17:18,728 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:18,730 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:17:18,857 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:18,857 [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] 2026-07-27 05:17:18,945 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:18,946 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:17:19 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:17:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:17:22 - docling.document_converter - Going to convert document batch... -INFO: 05:17:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:17:22 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:17:22 - docling.document_converter - Finished converting document file in 0.86 sec. -WARNING: 05:17:22 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:17:22 - docling_jobkit.convert.results - Processed 1 docs in 0.90 seconds. -INFO: 05:17:22 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 208998fc-b062-4ab9-9c58-076a87a73c7b in 0.90 seconds -INFO: 05:17:24 - uvicorn.access - 172.17.0.1:45596 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:17:24 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:17:24 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:17:24 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:17:24 - docling_serve.app - [TENANT_ID] Task 97b272d3-3b90-4bf1-af2e-91c2e1fef929 created with tenant_id='default' -INFO: 05:17:24 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 97b272d3-3b90-4bf1-af2e-91c2e1fef929 -INFO: 05:17:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:17:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 05:17:24 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:17:24,597 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:24,597 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:17:24,758 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:24,758 [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] 2026-07-27 05:17:24,809 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:24,809 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:17:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:17:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:17:26 - docling.document_converter - Going to convert document batch... -INFO: 05:17:26 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:17:26 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:17:26 - docling.document_converter - Finished converting document file in 0.36 sec. -INFO: 05:17:26 - docling_jobkit.convert.results - Processed 1 docs in 0.36 seconds. -INFO: 05:17:26 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 97b272d3-3b90-4bf1-af2e-91c2e1fef929 in 0.36 seconds -INFO: 05:17:28 - uvicorn.access - 172.17.0.1:45596 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:17:28 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:17:28 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:17:28 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:17:28 - docling_serve.app - [TENANT_ID] Task 14f8bb7b-6ec9-4938-8beb-73346f7982c9 created with tenant_id='default' -INFO: 05:17:28 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 14f8bb7b-6ec9-4938-8beb-73346f7982c9 -INFO: 05:17:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:17:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 05:17:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:17:28,631 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:28,631 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:17:28,744 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:28,744 [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] 2026-07-27 05:17:28,829 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:17:28,829 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:17:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:17:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:17:30 - docling.document_converter - Going to convert document batch... -INFO: 05:17:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:17:30 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:17:30 - docling.document_converter - Finished converting document file in 0.61 sec. -INFO: 05:17:30 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. -INFO: 05:17:30 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 14f8bb7b-6ec9-4938-8beb-73346f7982c9 in 0.64 seconds -INFO: 05:17:32 - uvicorn.access - 172.17.0.1:45596 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:17:33 - uvicorn.access - 172.17.0.1:45596 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:17:33 - uvicorn.access - 172.17.0.1:45596 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:15:16 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:15:16 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:15:16 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:15:16 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:15:16 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/healthz$,/readyz$,/livez$,/health$,/ready$) +INFO: 05:15:16 - uvicorn.error - Started server process [1] +INFO: 05:15:16 - uvicorn.error - Waiting for application startup. +INFO: 05:15:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:15:19 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:15:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:15:19 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:15:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:15:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 05:15:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:15:19 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-08-03 05:15:20.000182693 [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: 05:15:20 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:15:20,285 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:20,286 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:15:20,383 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:20,383 [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] 2026-08-03 05:15:20,429 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:20,429 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:15:20 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:15:20 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:15:22 - docling.document_converter - Going to convert document batch... +INFO: 05:15:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:15:22 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:15:22 - docling.document_converter - Finished converting document file in 0.38 sec. +WARNING: 05:15:22 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:15:22 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 05:15:22 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 69b8b682-08a5-44fe-be03-5cdebc43ac60 in 0.41 seconds +INFO: 05:15:23 - uvicorn.access - 172.17.0.1:44444 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:15:23 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:15:23 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:15:23 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:15:23 - docling_serve.app - [TENANT_ID] Task e40ed713-5ec2-4d84-b136-3fcded81f6b6 created with tenant_id='default' +INFO: 05:15:23 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task e40ed713-5ec2-4d84-b136-3fcded81f6b6 +INFO: 05:15:23 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:15:23 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 05:15:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:15:23,546 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:23,546 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:15:23,633 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:23,633 [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] 2026-08-03 05:15:23,679 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:23,679 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:15:23 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:15:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:15:24 - docling.document_converter - Going to convert document batch... +INFO: 05:15:24 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:15:24 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:15:24 - docling.document_converter - Finished converting document file in 0.21 sec. +INFO: 05:15:24 - docling_jobkit.convert.results - Processed 1 docs in 0.21 seconds. +INFO: 05:15:24 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job e40ed713-5ec2-4d84-b136-3fcded81f6b6 in 0.21 seconds +INFO: 05:15:25 - uvicorn.access - 172.17.0.1:44444 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:15:25 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:15:25 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:15:25 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:15:25 - docling_serve.app - [TENANT_ID] Task 4be5e046-7eb6-4adf-8ca5-99eaf61ea61c created with tenant_id='default' +INFO: 05:15:25 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 4be5e046-7eb6-4adf-8ca5-99eaf61ea61c +INFO: 05:15:25 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:15:25 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 05:15:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:15:25,562 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:25,562 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:15:25,648 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:25,649 [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] 2026-08-03 05:15:25,695 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:15:25,695 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:15:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:15:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:15:26 - docling.document_converter - Going to convert document batch... +INFO: 05:15:26 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:15:26 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:15:26 - docling.document_converter - Finished converting document file in 0.21 sec. +INFO: 05:15:26 - docling_jobkit.convert.results - Processed 1 docs in 0.22 seconds. +INFO: 05:15:26 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4be5e046-7eb6-4adf-8ca5-99eaf61ea61c in 0.22 seconds +INFO: 05:15:27 - uvicorn.access - 172.17.0.1:44444 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:15:27 - uvicorn.access - 172.17.0.1:44444 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:15:27 - uvicorn.access - 172.17.0.1:44444 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -714,120 +1055,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:16:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:16:19 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:16:19 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:16:19 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:16:19 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/health$,/healthz$,/metrics$,/ready$,/livez$) -INFO: 05:16:19 - uvicorn.error - Started server process [1] -INFO: 05:16:19 - uvicorn.error - Waiting for application startup. -INFO: 05:16:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:16:24 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:16:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:16:24 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:16:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:16:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 05:16:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:16:24 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-27 05:16:24.867381595 [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: 05:16:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:16:25,207 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:25,209 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:16:25,371 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:25,371 [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] 2026-07-27 05:16:25,462 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:25,462 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:16:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:16:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:16:29 - docling.document_converter - Going to convert document batch... -INFO: 05:16:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:16:29 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:16:29 - docling.document_converter - Finished converting document file in 0.73 sec. -WARNING: 05:16:29 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:16:29 - docling_jobkit.convert.results - Processed 1 docs in 0.78 seconds. -INFO: 05:16:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2ec89373-2896-4972-8166-ae1ca4df8a9c in 0.78 seconds -INFO: 05:16:31 - uvicorn.access - 172.17.0.1:57308 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:16:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:16:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:16:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:16:31 - docling_serve.app - [TENANT_ID] Task 7c190721-d2b3-41e5-932c-4bec850b632b created with tenant_id='default' -INFO: 05:16:31 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 7c190721-d2b3-41e5-932c-4bec850b632b -INFO: 05:16:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:16:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 05:16:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:16:31,487 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:31,487 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:16:31,650 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:31,650 [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] 2026-07-27 05:16:31,722 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:31,722 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:16:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:16:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:16:34 - docling.document_converter - Going to convert document batch... -INFO: 05:16:34 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:16:34 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:16:34 - docling.document_converter - Finished converting document file in 1.19 sec. -INFO: 05:16:34 - docling_jobkit.convert.results - Processed 1 docs in 1.19 seconds. -INFO: 05:16:34 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 7c190721-d2b3-41e5-932c-4bec850b632b in 1.19 seconds -INFO: 05:16:35 - uvicorn.access - 172.17.0.1:57308 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:16:35 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:16:35 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:16:35 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:16:35 - docling_serve.app - [TENANT_ID] Task 44fb0d52-ea01-483e-9133-602fd226433c created with tenant_id='default' -INFO: 05:16:35 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 44fb0d52-ea01-483e-9133-602fd226433c -INFO: 05:16:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:16:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 05:16:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:16:35,506 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:35,507 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:16:35,645 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:35,645 [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] 2026-07-27 05:16:35,727 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:16:35,728 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:16:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:16:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:16:37 - docling.document_converter - Going to convert document batch... -INFO: 05:16:37 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:16:37 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:16:37 - docling.document_converter - Finished converting document file in 0.84 sec. -INFO: 05:16:37 - docling_jobkit.convert.results - Processed 1 docs in 0.86 seconds. -INFO: 05:16:37 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 44fb0d52-ea01-483e-9133-602fd226433c in 0.86 seconds -INFO: 05:16:39 - uvicorn.access - 172.17.0.1:57308 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:16:39 - uvicorn.access - 172.17.0.1:57308 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:16:39 - uvicorn.access - 172.17.0.1:57308 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:14:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:01 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:14:01 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:14:01 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:14:01 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/healthz$,/metrics$,/health$,/ready$) +INFO: 05:14:01 - uvicorn.error - Started server process [1] +INFO: 05:14:01 - uvicorn.error - Waiting for application startup. +INFO: 05:14:04 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:04 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:14:04 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:04 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:14:04 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:04 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 05:14:04 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:04 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-08-03 05:14:04.466457342 [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: 05:14:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:14:04,727 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:04,729 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:14:04,815 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:04,816 [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] 2026-08-03 05:14:04,863 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:04,863 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:04 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:07 - docling.document_converter - Going to convert document batch... +INFO: 05:14:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:07 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:07 - docling.document_converter - Finished converting document file in 0.39 sec. +WARNING: 05:14:07 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:14:07 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 05:14:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8d0b937f-b877-4082-8666-078f59278d17 in 0.43 seconds +INFO: 05:14:07 - uvicorn.access - 172.17.0.1:40062 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:07 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:14:07 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:14:07 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:14:07 - docling_serve.app - [TENANT_ID] Task c967807d-2a75-4f28-98e4-0c998e55f8d3 created with tenant_id='default' +INFO: 05:14:07 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task c967807d-2a75-4f28-98e4-0c998e55f8d3 +INFO: 05:14:07 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:07 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 05:14:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:14:07,933 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:07,933 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:14:08,050 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:08,050 [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] 2026-08-03 05:14:08,100 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:08,100 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:08 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:09 - docling.document_converter - Going to convert document batch... +INFO: 05:14:09 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:09 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:09 - docling.document_converter - Finished converting document file in 0.35 sec. +INFO: 05:14:09 - docling_jobkit.convert.results - Processed 1 docs in 0.35 seconds. +INFO: 05:14:09 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job c967807d-2a75-4f28-98e4-0c998e55f8d3 in 0.35 seconds +INFO: 05:14:09 - uvicorn.access - 172.17.0.1:40062 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Task 6a35a727-f94d-4942-af5d-d2bead917836 created with tenant_id='default' +INFO: 05:14:09 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 6a35a727-f94d-4942-af5d-d2bead917836 +INFO: 05:14:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 05:14:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:14:09,947 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:09,947 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:14:10,086 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:10,086 [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] 2026-08-03 05:14:10,136 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:14:10,136 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:11 - docling.document_converter - Going to convert document batch... +INFO: 05:14:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:11 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:11 - docling.document_converter - Finished converting document file in 0.44 sec. +INFO: 05:14:11 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 05:14:11 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 6a35a727-f94d-4942-af5d-d2bead917836 in 0.46 seconds +INFO: 05:14:11 - uvicorn.access - 172.17.0.1:40062 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:12 - uvicorn.access - 172.17.0.1:40062 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:14:12 - uvicorn.access - 172.17.0.1:40062 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -865,120 +1206,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:14:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:14:40 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:14:40 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:14:40 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:14:40 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/metrics$,/livez$,/ready$,/readyz$,/healthz$) -INFO: 05:14:40 - uvicorn.error - Started server process [1] -INFO: 05:14:40 - uvicorn.error - Waiting for application startup. -INFO: 05:14:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:14:44 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:14:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:14:44 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:14:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:14:44 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 05:14:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:14:44 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-27 05:14:44.771474330 [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: 05:14:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:14:45,282 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:45,283 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:14:45,390 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:45,390 [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] 2026-07-27 05:14:45,436 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:45,436 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:14:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:14:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:14:48 - docling.document_converter - Going to convert document batch... -INFO: 05:14:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:14:48 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:14:48 - docling.document_converter - Finished converting document file in 0.75 sec. -WARNING: 05:14:48 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:14:48 - docling_jobkit.convert.results - Processed 1 docs in 0.79 seconds. -INFO: 05:14:48 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8b2bf131-d0ec-4716-a26d-12b6689a9b30 in 0.79 seconds -INFO: 05:14:48 - uvicorn.access - 172.17.0.1:45852 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:14:48 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:14:48 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:14:48 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:14:48 - docling_serve.app - [TENANT_ID] Task 90b8336b-f42d-46c5-b291-dac3eb6ace44 created with tenant_id='default' -INFO: 05:14:48 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 90b8336b-f42d-46c5-b291-dac3eb6ace44 -INFO: 05:14:48 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:14:48 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 -INFO: 05:14:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:14:48,490 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:48,490 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:14:48,592 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:48,593 [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] 2026-07-27 05:14:48,639 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:48,639 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:14:48 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:14:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:14:50 - docling.document_converter - Going to convert document batch... -INFO: 05:14:50 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:14:50 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:14:50 - docling.document_converter - Finished converting document file in 0.69 sec. -INFO: 05:14:50 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. -INFO: 05:14:50 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 90b8336b-f42d-46c5-b291-dac3eb6ace44 in 0.70 seconds -INFO: 05:14:52 - uvicorn.access - 172.17.0.1:45852 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:14:52 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:14:52 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:14:52 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:14:52 - docling_serve.app - [TENANT_ID] Task ff805c2c-dc60-4036-8baf-0a7051e8eb82 created with tenant_id='default' -INFO: 05:14:52 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ff805c2c-dc60-4036-8baf-0a7051e8eb82 -INFO: 05:14:52 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:14:52 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 -INFO: 05:14:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:14:52,506 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:52,506 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:14:52,618 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:52,619 [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] 2026-07-27 05:14:52,666 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:52,666 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:14:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:14:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:14:53 - docling.document_converter - Going to convert document batch... -INFO: 05:14:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:14:53 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:14:53 - docling.document_converter - Finished converting document file in 0.44 sec. -INFO: 05:14:53 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. -INFO: 05:14:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ff805c2c-dc60-4036-8baf-0a7051e8eb82 in 0.46 seconds -INFO: 05:14:54 - uvicorn.access - 172.17.0.1:45852 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:14:54 - uvicorn.access - 172.17.0.1:45852 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:14:54 - uvicorn.access - 172.17.0.1:45852 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:12:42 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:12:42 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:12:42 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:12:42 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:12:42 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/healthz$,/health$,/livez$,/readyz$,/metrics$) +INFO: 05:12:42 - uvicorn.error - Started server process [1] +INFO: 05:12:42 - uvicorn.error - Waiting for application startup. +INFO: 05:12:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:12:45 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:12:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:12:45 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:12:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:12:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 05:12:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:12:45 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-08-03 05:12:45.456696598 [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: 05:12:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:12:45,725 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:45,726 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:12:45,812 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:45,812 [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] 2026-08-03 05:12:45,858 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:45,859 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:12:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:12:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:12:48 - docling.document_converter - Going to convert document batch... +INFO: 05:12:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:12:48 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:12:48 - docling.document_converter - Finished converting document file in 0.36 sec. +WARNING: 05:12:48 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:12:48 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 05:12:48 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b9c007ff-65fa-4cb0-ab19-0979d5cc508a in 0.39 seconds +INFO: 05:12:49 - uvicorn.access - 172.17.0.1:57648 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:12:49 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:12:49 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:12:49 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:12:49 - docling_serve.app - [TENANT_ID] Task b88a9136-9075-4f1b-8571-f3e88592078d created with tenant_id='default' +INFO: 05:12:49 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b88a9136-9075-4f1b-8571-f3e88592078d +INFO: 05:12:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:12:49 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 +INFO: 05:12:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:12:49,399 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:49,399 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:12:49,490 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:49,490 [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] 2026-08-03 05:12:49,543 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:49,543 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:12:49 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:12:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:12:50 - docling.document_converter - Going to convert document batch... +INFO: 05:12:50 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:12:50 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:12:50 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 05:12:50 - docling_jobkit.convert.results - Processed 1 docs in 0.36 seconds. +INFO: 05:12:50 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b88a9136-9075-4f1b-8571-f3e88592078d in 0.36 seconds +INFO: 05:12:51 - uvicorn.access - 172.17.0.1:57648 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:12:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:12:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:12:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:12:51 - docling_serve.app - [TENANT_ID] Task e4df515c-1f1e-4780-bf70-badbaf91bb88 created with tenant_id='default' +INFO: 05:12:51 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e4df515c-1f1e-4780-bf70-badbaf91bb88 +INFO: 05:12:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:12:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 +INFO: 05:12:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:12:51,418 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:51,418 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:12:51,506 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:51,507 [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] 2026-08-03 05:12:51,555 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:12:51,556 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:12:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:12:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:12:52 - docling.document_converter - Going to convert document batch... +INFO: 05:12:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:12:52 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:12:52 - docling.document_converter - Finished converting document file in 0.24 sec. +INFO: 05:12:52 - docling_jobkit.convert.results - Processed 1 docs in 0.26 seconds. +INFO: 05:12:52 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e4df515c-1f1e-4780-bf70-badbaf91bb88 in 0.26 seconds +INFO: 05:12:53 - uvicorn.access - 172.17.0.1:57648 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:12:53 - uvicorn.access - 172.17.0.1:57648 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:12:53 - uvicorn.access - 172.17.0.1:57648 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1016,120 +1357,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:13:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:13:54 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:13:54 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:13:54 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:13:54 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/metrics$,/healthz$,/ready$,/health$) -INFO: 05:13:54 - uvicorn.error - Started server process [1] -INFO: 05:13:54 - uvicorn.error - Waiting for application startup. -INFO: 05:13:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:13:59 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:13:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:13:59 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:13:59 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:13:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf -INFO: 05:13:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:13:59 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-27 05:13:59.484703381 [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: 05:13:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:13:59,860 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:13:59,862 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:14:00,010 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:00,011 [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] 2026-07-27 05:14:00,080 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:00,080 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:14:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:14:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:14:03 - docling.document_converter - Going to convert document batch... -INFO: 05:14:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:14:03 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:14:03 - docling.document_converter - Finished converting document file in 0.89 sec. -WARNING: 05:14:03 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:14:03 - docling_jobkit.convert.results - Processed 1 docs in 0.96 seconds. -INFO: 05:14:03 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7fb50f4b-5965-41da-b3cf-c630f20fbb78 in 0.96 seconds -INFO: 05:14:05 - uvicorn.access - 172.17.0.1:49452 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:14:05 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:14:05 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:14:05 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:14:05 - docling_serve.app - [TENANT_ID] Task bfbe5087-37c6-4196-bf63-474fe13ff6e9 created with tenant_id='default' -INFO: 05:14:05 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task bfbe5087-37c6-4196-bf63-474fe13ff6e9 -INFO: 05:14:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:14:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b -INFO: 05:14:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:14:05,601 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:05,601 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:14:05,722 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:05,723 [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] 2026-07-27 05:14:05,769 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:05,769 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:14:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:14:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:14:07 - docling.document_converter - Going to convert document batch... -INFO: 05:14:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:14:07 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:14:07 - docling.document_converter - Finished converting document file in 0.72 sec. -INFO: 05:14:07 - docling_jobkit.convert.results - Processed 1 docs in 0.73 seconds. -INFO: 05:14:07 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job bfbe5087-37c6-4196-bf63-474fe13ff6e9 in 0.73 seconds -INFO: 05:14:09 - uvicorn.access - 172.17.0.1:49452 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:14:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Task 7524822a-e738-4004-bff1-aed3ea04cea6 created with tenant_id='default' -INFO: 05:14:09 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 7524822a-e738-4004-bff1-aed3ea04cea6 -INFO: 05:14:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:14:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb -INFO: 05:14:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-27 05:14:09,620 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:09,621 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:14:09,759 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:09,759 [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] 2026-07-27 05:14:09,870 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:14:09,871 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:14:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:14:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:14:11 - docling.document_converter - Going to convert document batch... -INFO: 05:14:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:14:11 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:14:11 - docling.document_converter - Finished converting document file in 0.44 sec. -INFO: 05:14:11 - docling_jobkit.convert.results - Processed 1 docs in 0.47 seconds. -INFO: 05:14:11 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7524822a-e738-4004-bff1-aed3ea04cea6 in 0.47 seconds -INFO: 05:14:11 - uvicorn.access - 172.17.0.1:49452 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:14:11 - uvicorn.access - 172.17.0.1:49452 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:14:11 - uvicorn.access - 172.17.0.1:49452 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:11:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:11:33 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:11:33 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:11:33 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:11:33 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/health$,/livez$,/metrics$,/readyz$,/healthz$) +INFO: 05:11:33 - uvicorn.error - Started server process [1] +INFO: 05:11:33 - uvicorn.error - Waiting for application startup. +INFO: 05:11:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:11:37 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:11:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:11:37 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:11:37 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:11:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf +INFO: 05:11:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:11:37 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-08-03 05:11:37.169986153 [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: 05:11:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:11:37,520 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:37,521 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:11:37,640 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:37,640 [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] 2026-08-03 05:11:37,710 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:37,710 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:11:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:11:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:11:41 - docling.document_converter - Going to convert document batch... +INFO: 05:11:41 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:11:41 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:11:41 - docling.document_converter - Finished converting document file in 0.67 sec. +WARNING: 05:11:41 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:11:41 - docling_jobkit.convert.results - Processed 1 docs in 0.72 seconds. +INFO: 05:11:41 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8a6352da-eff1-4936-92a4-1bcfbb9c9b2f in 0.72 seconds +INFO: 05:11:41 - uvicorn.access - 172.17.0.1:55238 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:11:41 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:11:41 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:11:41 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:11:41 - docling_serve.app - [TENANT_ID] Task 6eded513-2bc2-49f4-a8f8-30dfe68b2c55 created with tenant_id='default' +INFO: 05:11:41 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 6eded513-2bc2-49f4-a8f8-30dfe68b2c55 +INFO: 05:11:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:11:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b +INFO: 05:11:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:11:41,857 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:41,857 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:11:41,972 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:41,973 [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] 2026-08-03 05:11:42,036 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:42,036 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:11:42 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:11:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:11:43 - docling.document_converter - Going to convert document batch... +INFO: 05:11:43 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:11:43 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:11:43 - docling.document_converter - Finished converting document file in 0.44 sec. +INFO: 05:11:43 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. +INFO: 05:11:43 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 6eded513-2bc2-49f4-a8f8-30dfe68b2c55 in 0.45 seconds +INFO: 05:11:43 - uvicorn.access - 172.17.0.1:55238 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:11:43 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:11:43 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:11:43 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:11:43 - docling_serve.app - [TENANT_ID] Task ffcdfaf6-58f1-45be-b996-773c317c8ffe created with tenant_id='default' +INFO: 05:11:43 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ffcdfaf6-58f1-45be-b996-773c317c8ffe +INFO: 05:11:43 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:11:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb +INFO: 05:11:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-08-03 05:11:43,887 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:43,887 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-08-03 05:11:44,045 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:44,045 [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] 2026-08-03 05:11:44,194 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-08-03 05:11:44,194 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:11:44 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:11:44 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:11:45 - docling.document_converter - Going to convert document batch... +INFO: 05:11:45 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:11:45 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:11:45 - docling.document_converter - Finished converting document file in 0.26 sec. +INFO: 05:11:45 - docling_jobkit.convert.results - Processed 1 docs in 0.28 seconds. +INFO: 05:11:45 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ffcdfaf6-58f1-45be-b996-773c317c8ffe in 0.28 seconds +INFO: 05:11:45 - uvicorn.access - 172.17.0.1:55238 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:11:46 - uvicorn.access - 172.17.0.1:55238 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:11:46 - uvicorn.access - 172.17.0.1:55238 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1167,37 +1508,37 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -2026-07-27 05:12:17.787234199 [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] 2026-07-27 05:12:18,071 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:12:18,072 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-27 05:12:18,175 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:12:18,176 [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] 2026-07-27 05:12:18,220 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-27 05:12:18,220 [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