A library for efficient similarity search and clustering of dense vectors.

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

MTEB: Massive Text Embedding Benchmark

Fast and memory-efficient exact kmeans

Late Interaction Models Training & Retrieval

High-Performance Engine for Multi-Vector Search

ASTChunk is a Python toolkit for code chunking using Abstract Syntax Trees (ASTs), designed to create structurally sound and meaningful code segments.

Website for Joseph E. Gonzalez's group at Berkeley (created by his procrastinating student)

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

Geo-Agent-Eval

Yichuan Wang Homepage

Generative Representational Instruction Tuning

State-of-the-Art Text Embeddings

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Official repository for paper "ReasonIR Training Retrievers for Reasoning Tasks".

Autonomous framework for LLMs to play GeoGuessr

Materials for learning SGLang

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search sc…

Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

Header-only C++/python library for fast approximate nearest neighbors

A high-throughput and memory-efficient inference and serving engine for LLMs