docling-project / docling-project/docling

Document pipeline fails when `enrich-picture` options are enabled

Open
#1,418 2 comments 0 reactions 1 assignee Claimed by @dolfim-ibm View on GitHub
bug priority:low
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
2d 21h
Merged PRs (30d)
84

Description

### Bug

Pipeline fails when i add `--enrich-picture-classes --enrich-picture-description` options.
There are no warnings or errors.

### Steps to reproduce

`docling Minority_Veterans_2012.pdf --table-mode accurate --pdf-backend dlparse_v4 --to md --num-threads 8 --image-export-mode placeholder -vv --enrich-picture-classes --enrich-picture-description`

```
INFO:docling.document_converter:Going to convert document batch...
INFO:docling.document_converter:Initializing pipeline for StandardPdfPipeline with options hash dfd4da576f83ca77af305e43973cae7b
INFO:docling.utils.accelerator_utils:Accelerator device: 'mps'
INFO:docling.utils.accelerator_utils:Accelerator device: 'mps'
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): huggingface.co:443
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /api/models/ds4sd/docling-models/revision/v2.1.0 HTTP/1.1" 200 1266
DEBUG:docling_ibm_models.layoutmodel.layout_predictor:LayoutPredictor settings: {'safe_tensors_file': '/Users/e3/.cache/huggingface/hub/models--ds4sd--docling-models/snapshots/36bebf56681740529abd09f5473a93a69373fbf0/model_artifacts/layout/model.safetensors', 'device': 'mps', 'num_threads': 8, 'image_size': 640, 'threshold': 0.3}
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /api/models/ds4sd/docling-models/revision/v2.2.0 HTTP/1.1" 200 1266
INFO:docling.utils.accelerator_utils:Accelerator device: 'mps'
INFO:docling.models.factories.base_factory:Loading plugin 'docling_defaults'
INFO:docling.models.factories:Registered picture descriptions: ['vlm', 'api']
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /api/models/HuggingFaceTB/SmolVLM-256M-Instruct/revision/main HTTP/1.1" 200 4588
INFO:docling.utils.accelerator_utils:Accelerator device: 'mps'
INFO:docling.utils.accelerator_utils:Accelerator device: 'mps'
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /api/models/ds4sd/DocumentFigureClassifier/revision/v1.0.1 HTTP/1.1" 200 911
DEBUG:docling_ibm_models.document_figure_classifier_model.document_figure_classifier_predictor:CodeFormulaModel settings: {'device': 'mps', 'num_threads': 8, 'classes': ['bar_chart', 'bar_code', 'chemistry_markush_structure', 'chemistry_molecular_structure', 'flow_chart', 'icon', 'line_chart', 'logo', 'map', 'other', 'pie_chart', 'qr_code', 'remote_sensing', 'screenshot', 'signature', 'stamp']}
INFO:docling.pipeline.base_pipeline:Processing document Minority_Veterans_2012.pdf
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=132005.053
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=132007.596
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=132012.604
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=132015.678
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=132017.144
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=132017.690
INFO:docling.document_converter:Finished converting document Minority_Veterans_2012.pdf in 23.15 sec.
WARNING:docling.cli.main:Document /var/folders/sl/1rb8x28n155bpxq5sg87ccv80000gn/T/tmpnzpzdlit/Minority_Veterans_2012.pdf failed to convert.
INFO:docling.cli.main:Processed 1 docs, of which 1 failed
INFO:docling.cli.main:All documents were converted in 23.15 seconds.
```

### Docling version

```
$ docling --version
Docling version: 2.30.0
Docling Core version: 2.27.0
Docling IBM Models version: 3.4.1
Docling Parse version: 4.0.1
Python: cpython-312 (3.12.7)
Platform: macOS-15.3.1-arm64-arm-64bit
```

### Python version

`Python 3.12.7`

[Minority_Veterans_2012.pdf](https://github.com/user-attachments/files/19815292/Minority_Veterans_2012.pdf)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.