colbert

Open-source inference server and production cluster for all the models your agent needs.

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Efficient Retrieval Augmentation and Generation Framework

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Late Interaction Models Training & Retrieval

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

Neural Search

High-Performance Engine for Multi-Vector Search

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

Vector Database with support for late interaction and token level embeddings.