colpali

A new novel multi-modality (Vision) RAG architecture

ColPali is vision based RAG (Retrieval Augmented Generation) which can capture visual data

LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing, optimized for cloud deployment.

REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

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

#3 Winner of Best Use of Zoom API at Stanford TreeHacks 2025! An AI-powered meeting assistant that captures video, audio and textual context from Zoom calls using multimodal RAG.

A multimodal RAG application using Qwen 2.5 VL, ColPali, and QdrantDB for text and image-based retrieval.

Tests of OCR and RAG with LLMs

OCR and Document Search Web Application

Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine

Fast, memory-efficient retrieval-augmented generation over visually rich documents. Powered by HPC-ColPali (Hierarchical Patch Compression for ColPali) and Janus-Pro.

Vision-based RAG

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

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.

LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.

Multimodal approach with memory and speed optimization for RAG systems

ColFastVLM: Towards low-latency indexing in visual document retrieval

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.

Engineering Homework solver using ColPali PDF retrieval, Qwen2.5-VL Multimodal analysis, and DeepSeek code generation with schemdraw to create step-by-step solutions with circuit diagrams.