illuin-tech/colpali

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

59
/ 100
Established

This project helps you find specific documents quickly by understanding both their text and visual layout. You feed it a collection of documents and your search query, and it outputs the most relevant documents, even considering elements like charts and diagrams. It's designed for anyone who needs to retrieve information from visually rich documents, like legal professionals, researchers, or data analysts.

2,555 stars. Actively maintained with 4 commits in the last 30 days.

Use this if you need to efficiently search and retrieve information from documents where visual layout, images, or charts are as important as the text itself.

Not ideal if your documents are purely text-based and you do not need to consider visual information for retrieval.

document-retrieval information-extraction legal-research academic-research knowledge-management
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

2,555

Forks

236

Language

Python

License

MIT

Last pushed

Mar 01, 2026

Commits (30d)

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/illuin-tech/colpali"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.