Everything about the SmolLM2 and SmolVLM family of models

Fully open reproduction of DeepSeek-R1

A generative world for general-purpose robotics & embodied AI learning.

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Efficient, Flexible and Portable Structured Generation

An open-source RAG-based tool for chatting with your documents.

Simple and fast low-bit matmul kernels in CUDA

Server for the ListenBrainz project, including the front-end (javascript/react) code that it serves and all of the data processing components that LB uses.

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…

Work-in-progress vector search SQLite extension that runs anywhere.

nanoGPT style version of Llama 3.1

A family of compressed models obtained via pruning and knowledge distillation

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

Parse files for optimal RAG

Developer APIs to Accelerate LLM Projects

ClickHouse® is a real-time analytics DBMS

Python scraper based on AI

LLM training in simple, raw C/CUDA

Vision agent

Command your browser with GPT

A natural language interface for computers.

Web Scraping with GPT-4 Vision API and Puppeteer

Useful tools for matching metadata to and from MusicBrainz.

This sample shows how to create two AKS-hosted chat applications that use OpenAI, LangChain, ChromaDB, and Chainlit using Python and deploy them to an AKS environment built in Terraform.

A open source implementation of Chainlit's cloud

Domain Adapted Language Modeling Toolkit - E2E RAG

[CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

A plugin to enable AutoGPT to interact with websites.

experiments with inference on llama

An AutoGPT agent that controls Chrome on your desktop