Metadata-Version: 2.4
Name: docling-ocr-mistral
Version: 0.1.1
Summary: Mistral OCR plugin for Docling
Project-URL: repository, https://github.com/geoHeil/docling-ocr-mistral
Project-URL: issues, https://github.com/geoHeil/docling-ocr-mistral/issues
Author: Georg Heiler
License-Expression: MIT
License-File: LICENSE
Keywords: docling,mistral,ocr,plugin
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: <4.0,>=3.10
Requires-Dist: docling<3.0.0,>=2.107.0
Requires-Dist: pillow<13.0.0,>=10.0.0
Requires-Dist: pydantic<3.0.0,>=2.0.0
Requires-Dist: requests<3.0.0,>=2.32.2
Provides-Extra: test
Requires-Dist: pytest>=8.0.0; extra == 'test'
Description-Content-Type: text/markdown

# docling-ocr-mistral

Mistral OCR plugin for [Docling](https://github.com/docling-project/docling).

## Install

```bash
pip install docling-ocr-mistral
```

## Use

```python
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling_ocr_mistral import MistralOcrOptions

pipeline_options = PdfPipelineOptions(
    allow_external_plugins=True,
    ocr_options=MistralOcrOptions(),
)

converter = DocumentConverter(
    format_options={
        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options),
    }
)
result = converter.convert("document.pdf")
```

Set `MISTRAL_API_KEY` or pass `MistralOcrOptions(api_key="...")`.

CLI:

```bash
docling --allow-external-plugins --ocr-engine mistral_ocr document.pdf
```
