🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance m…

A rate-limiting library for Rust (f.k.a. ratelimit_meter)

Generates OpenAPI 3.0 spec based on Rust code. Works with axum, actix-web, or any/no framework.

LLM Prompt Injection Detector

A code coverage tool for Rust projects

A programming framework for agentic AI 🤖

Automated Evaluation of RAG Systems

Fast ML inference & training for Rust with ONNX Runtime

Rust library to read, manipulate and write PDF files.

Rust SDK for Milvus.

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

A cloud-native vector database, storage for next generation AI applications

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

LLM Orchestrator built in Rust

Curated list of resources for Embedded and Low-level development in the Rust programming language

🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧

Calibration software for the Murchison Widefield Array (MWA) radio telescope

A curated list of Large Language Model (LLM) Interpretability resources.

A middleware for actix-web that provides rate-limiting backed by governor.

Simple, Fast, Code first and Compile time generated OpenAPI documentation for Rust

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers …

A demo of a webserver in Rust

Interact with your documents using the power of GPT, 100% privately, no data leaks

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A tool for generating function arguments and choosing what function to call with local LLMs

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Convert PDF to markdown quickly with high accuracy

Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀