jolibrain/colette
Multimodal RAG to search and interact locally with technical documents of any kind
Implements a Vision-RAG system that converts documents to images for retrieval, preserving visual layouts and figures alongside text, then pairs retrieved content with Vision Language Models for inference. Supports dual text-based RAG pipelines, multi-model embedders and LLMs, and integrates image generation via diffusers. Fully self-hosted with Docker containerization and Python API, designed for technical document corpuses where external API leakage is prohibited.
284 stars.
Stars
284
Forks
31
Language
HTML
License
—
Category
Last pushed
Jan 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/jolibrain/colette"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
AnswerDotAI/byaldi
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
illuin-tech/colpali
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
nannib/nbmultirag
Un framework in Italiano ed Inglese, che permette di chattare con i propri documenti in RAG,...
OpenBMB/VisRAG
Parsing-free RAG supported by VLMs
chiang-yuan/llamp
[EMNLP '25] A web app and Python API for multi-modal RAG framework to ground LLMs on...