Skip to content

FOR-sight-ai/FORetrieval

 
 

Repository files navigation

Getting started

Currently, we support all models supported by the underlying colpali-engine, including the newer, and better, ColQwen2 checkpoints, such as vidore/colqwen2-v1.0.

Additional backends will be supported in future updates. As byaldi exists to facilitate the adoption of multi-modal retrievers, we intend to also add support for models such as VisRAG.

Pre-requisites

Poppler

To convert pdf to images with a friendly license, we use the pdf2image library. This library requires poppler to be installed on your system. Poppler is very easy to install by following the instructions on their website. The tl;dr is:

MacOS with homebrew

brew install poppler

Debian/Ubuntu

sudo apt-get install -y poppler-utils

Flash-Attention

Gemma uses a recent version of flash attention. To make things run as smoothly as possible, we'd recommend that you install it after installing the library:

pip install flash-attn

Hardware

ColPali uses multi-billion parameter models to encode documents. We recommend using a GPU for smooth operations, though weak/older GPUs are perfectly fine! Encoding your collection would suffer from poor performance on CPU or MPS.

Acknowledgements

FORetrieval was forked from Byaldi, RAGatouille's mini sister project. It is a simple wrapper around the ColPali repository to make it easy to use late-interaction multi-modal models such as ColPALI with a familiar API.

About

Colpali-based retriever

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.0%
  • Rich Text Format 2.7%
  • HTML 0.3%