- San Francisco, CA
Stars
scikit-learn: machine learning in Python
An open-source alternative to Ngrok, designed to serve production traffic and be simple to host (particularly on Kubernetes)
Free TailwindCSS HTML UI Components - built to create landing pages and websites. Easyfrontend UI components are free and open-source. show your support and love, don't forget to give us a star 🌟
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C…
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
Self-hosted version of OpenAI’s new stateful Assistants API
IDE style command line auto complete
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Rust bindings for the C++ api of PyTorch.
RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.
DSPy: The framework for programming—not prompting—language models
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
📋 A list of open LLMs available for commercial use.