Mistral OCR Wrapper

A minimal Mistral API wrapper to OCR images and PDF with images embedded in the resultant markdown.

Setup

1. Install dependencies

pip install -r requirements.txt

2. Setup environment variables

Create a .env file in the project root and paste the following:

# Put your Mistral API key here
MISTRAL_API_KEY=YOUR_API_KEY_HERE

# Optional: override model name
MISTRAL_OCR_MODEL=mistral-ocr-latest

3. Run the example script

python src/main.py

Files

• main.py — example usage. The output is stored in .md file.
• mistral_ai.py — contains the MistralClient.

Official Resources

• Documentation: https://docs.mistral.ai/capabilities/document_ai/basic_ocr/
• API Reference: https://docs.mistral.ai/api/#tag/ocr

Source of sample files

• PDF: https://github.com/mistralai/cookbook/blob/main/mistral/ocr/mistral7b.pdf
• Image: https://gallica.bnf.fr/ark:/12148/bpt6k850660r/f26.item

---

Author: Mayank 'DerperDoing' Bagchi