Simple API for deploying any RAG or LLM that you want adding plugins.

Harness LLMs with Multi-Agent Programming

A high-throughput and low-latency inference and serving framework for LLMs and VLs

Lightweight alternative to LangChain for composing LLMs

Nvidia Framework for LLM Inference

Build your own conversational search engine using less than 500 lines of code by LeptonAI.