The ultimate RAG for your monorepo
Han Language Processing
New family of code large language models (LLMs)
Standalone, small, language-neutral
Easy token price estimates for 400+ LLMs. TokenOps
LMDeploy is a toolkit for compressing, deploying, and serving LLMs
Qwen3-Coder is the code version of Qwen3
Build a large language model from 0 only with Python foundation
A Python Automated Machine Learning tool that optimizes ML
Language-model investigation agent with a terminal UI
GPU accelerated decision optimization
A modular graph-based Retrieval-Augmented Generation (RAG) system
Universal LLM Deployment Engine with ML Compilation
The agent that grows with you
High-performance inference framework for large language models
Model Context Protocol tool support for LangChain
Simple, Pythonic building blocks to evaluate LLM applications
Chat with your SQL database
Flower: A Friendly Federated Learning Framework
A text-to-speech, speech-to-text and speech-to-speech library
Interact with your documents using the power of GPT
A collection of machine learning examples and tutorials
Library for building type-safe natural language interfaces with LLMs
Chat with your documents using local AI
Official Repo for ICML 2024 paper