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

The PyQt6 application using ColPali and OpenAI to show Efficient Document Retrieval with Vision Language Models

The repo provides the code for Qdrant for efficient image indexing and retrieval using models such as ColPali, ColQwen, and VDR-2B-Multi-V1, jina embeddings v4 etc enhancing multimodal search capabilities across various applications.

ColQwen2 local Vespa DB deploy and feed and Open-Webui retrieval function

Python library for MUVERA multi-vector retrieval via Fixed Dimensional Encodings. ColBERT / ColQwen2 / ColQwen3.5 compatible.

Vignemale is a powerful AI assistant build to help you study patent law , He can be adapted to study any topics

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.

Visual RAG system for financial document analysis using ColQwen2.5, Qdrant, Claude Sonnet/Opus

VisRAG playground for finding your perfect embedding + VLM combo. Index PDFs with multimodal models, compare responses side-by-side.

ColQwen2 via infinity embedding api and local vespa db sample

local vlm-rag w/ Qdrant, colQwen2.5 and Qwen3-VL