Open, Multi-modal Catalog for Data & AI

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

🥷 Run AI-agents with an API

This code sets up a simple yet robust server using FastAPI for handling asynchronous requests for embedding generation and reranking tasks using the BAAI M3 multilingual model.

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

Drag & drop UI to build your customized LLM flow

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

DSPy: The framework for programming—not prompting—foundation models

⛓️ Langflow is a visual framework for building multi-agent and RAG applications. It's open-source, Python-powered, fully customizable, model and vector store agnostic.

Tools for merging pretrained large language models.

OpenAGI: When LLM Meets Domain Experts

AIOS: LLM Agent Operating System

OpenAI Assistants API quickstart with Next.js.

Open Source Text Embedding Models with OpenAI Compatible API

Drop in replacement for OpenAI's embedding API. Self Hosted.

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.

TinyAgent: Function Calling at the Edge!

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Drop in replacement for the OpenAI Assistants API

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

Monte Carlo tree search in JAX

RustGPT is a ChatGPT UI built with Rust + HTMX: the power of Rust coupled with the simplicity of HTMX 💚

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Code release for SLIP Self-supervision meets Language-Image Pre-training

TigerBot: A multi-language multi-task LLM

Lightning Network Daemon ⚡️

Lightning Network node software