The code used to train and run inference with the ColPali architecture.
-
Updated
Dec 24, 2024 - Python
The code used to train and run inference with the ColPali architecture.
Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine
A minimalist yet highly performant, lightweight, lightning fast, multisource, multimodal and local Ingestion, Inference and Indexing solution, built in Rust.
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing, optimized for cloud deployment.
A new novel multi-modality (Vision) RAG architecture
REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model
ColPali is vision based RAG (Retrieval Augmented Generation) which can capture visual data
OCR and Document Search Web Application
Add a description, image, and links to the colpali topic page so that developers can more easily learn about it.
To associate your repository with the colpali topic, visit your repo's landing page and select "manage topics."