The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
-
Updated
Jan 5, 2026 - Python
#
colsmol
Here are 2 public repositories matching this topic...
A high-performance RAG system for PDFs using multi-vector embeddings (ColPali / ColQwen / ColSmol) with vector search in Qdrant, prefetch optimization, and reranking for improved relevance. Designed for speed, accuracy, and scalability, this system is ideal for building intelligent search, document understanding, and QA applications.
-
Updated
Sep 12, 2025 - Python
Improve this page
Add a description, image, and links to the colsmol topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the colsmol topic, visit your repo's landing page and select "manage topics."