Home Projects colpali
colpali
Python

colpali

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

by illuin-tech · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
colpalicolqwen2colsmolMITPython
View on GitHub
In plain words

Train and use visual document retrieval models to find information in images and documents.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
colpali — GitHub preview card
📈 Star history
2.70k2.69k
2026-07-072026-08-31
📈 Track colpali

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

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

colpali has 2.7k stars on GitHub. It has been forked 256 times. colpali is written mainly in Python. It has been in active development since 2024. colpali is available under the MIT license. Its main topics are colpali, colqwen2, colsmol, information-retrieval.

Frequently asked questions

What is colpali?

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

Is colpali open source?

colpali is an open-source project. It is released under the MIT license.

Is colpali free?

Yes. colpali is free and open source — you can use, modify and self-host it.

What license does colpali use?

colpali is available under the MIT license.

What language is colpali written in?

colpali is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — colpali

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=illuin-tech-colpali)](https://olud.ai/project/illuin-tech-colpali.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.