docling-project / docling-project/docling

Failed to convert file

Open
#1,153 3 comments 1 reaction 1 assignee Claimed by @cau-git View on GitHub
bug reading_order
Dominant language
Python
Stars
66.4k
Forks
4.8k
Avg merge
3d 4h
Merged PRs (30d)
98

Description

### Bug
The conversion failed with
```
INFO:docling.document_converter:Going to convert document batch...
INFO:docling.utils.accelerator_utils:Accelerator device: 'cpu'
INFO:docling.utils.accelerator_utils:Accelerator device: 'cpu'
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 1265
DEBUG:docling_ibm_models.layoutmodel.layout_predictor:LayoutPredictor settings: {'safe_tensors_file': '/home/jinhongyi/.cache/huggingface/hub/models--ds4sd--docling-models/snapshots/36bebf56681740529abd09f5473a93a69373fbf0/model_artifacts/layout/model.safetensors', 'device': 'cpu', 'num_threads': 4, 'image_size': 640, 'threshold': 0.3}
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /api/models/ds4sd/docling-models/revision/v2.1.0 HTTP/1.1" 200 1265
INFO:docling.utils.accelerator_utils:Accelerator device: 'cpu'
INFO:docling.utils.accelerator_utils:Accelerator device: 'cpu'
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "GET /api/models/ds4sd/CodeFormula/revision/v1.0.1 HTTP/1.1" 200 1194
DEBUG:docling_ibm_models.code_formula_model.code_formula_predictor:CodeFormulaModel settings: {'device': 'cpu', 'num_threads': 4}
INFO:docling.pipeline.base_pipeline:Processing document paper_1.pdf
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638070.947
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638108.480
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638143.904
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638172.381
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638200.698
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638227.374
DEBUG:docling.pipeline.base_pipeline:Finished converting page batch time=2638231.846
INFO:docling.document_converter:Finished converting document paper_1.pdf in 176.67 sec.
WARNING:docling.cli.main:Document /tmp/tmpdnmndurs/paper_1.pdf failed to convert.
INFO:docling.cli.main:Processed 1 docs, of which 1 failed
INFO:docling.cli.main:All documents were converted in 176.68 seconds.
```

### Steps to reproduce
run `docling --device cpu --enrich-formula --to md -vv paper_1.pdf `
[paper_1.pdf](https://github.com/user-attachments/files/19221247/paper_1.pdf)

I've successfully converted many pdfs, and I don't see how this one is different.

### Docling version
Docling version: 2.25.0
Docling Core version: 2.21.1
Docling IBM Models version: 3.4.1
Docling Parse version: 3.4.0
Python: cpython-310 (3.10.16)
Platform: Linux-5.15.0-131-generic-x86_64-with-glibc2.35

### Python version
Python 3.10.16

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.