A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search sc…

Automate code reviews, patching and documentation with self-hosted LLM workflows.

An extremely fast Python package and project manager, written in Rust.

Fast and accurate automatic speech recognition (ASR) for edge devices

Entropy Based Sampling and Parallel CoT Decoding

A simple screen parsing tool towards pure vision based GUI agent

TypeSchema is a JSON format to describe data models in a language neutral format

Temporian is an open-source Python library for preprocessing ⚡ and feature engineering 🛠 temporal data 📈 for machine learning applications 🤖

🪄 Create rich visualizations with AI

Official inference framework for 1-bit LLMs

Hydrological modeling

Water resources modeling

Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

Grandmaster-Level Chess Without Search

Automated, smooth, N'th order derivatives of non-uniformly sampled time series data

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

GCAM -- The Global Change Analysis Model

Multilingual Voice Understanding Model

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

A lightning-fast search API that fits effortlessly into your apps, websites, and workflow

Distributed Training Over-The-Internet

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Integrated Assessment Modeling Framework

A reading list on LLM based Synthetic Data Generation 🔥

Compositional Linear Algebra

Hybrid search engine, combining best features of text and semantic search worlds

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.