jolibrain/colette
Multimodal RAG to search and interact locally with technical documents of any kind
Colette helps engineers, scientists, and technical professionals understand and extract information from complex technical documents like manuals, research papers, and blueprints. It takes your local PDFs and other technical files and lets you ask questions about their content, even about diagrams, charts, and visual layouts. The output is answers to your questions, drawing directly from your documents without sending any data to external services.
284 stars.
Use this if you need to quickly find answers or summarize information from a large collection of technical documents, especially those containing important visual data like diagrams, and require strict data privacy by keeping all your information on your own systems.
Not ideal if your primary need is for general knowledge or creative writing, or if you don't have access to a powerful GPU for processing documents locally.
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
illuin-tech/colpali
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
AnswerDotAI/byaldi
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
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...