Get your documents ready for gen AI

Dynamiq is an orchestration framework for agentic AI and LLM applications

AutoML tool for RAG

Cost tracker that logs OpenAI requests using opentelemetry

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

SQL databases in Python, designed for simplicity, compatibility, and robustness.

A simple, easy-to-hack GraphRAG implementation

Incremental Knowledge Graphs Constructor Using Large Language Models

A rate limiter for Starlette and FastAPI

Build and query dynamic, temporally-aware Knowledge Graphs

Chat first code editor. To download the packaged app:

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

Lightning-fast serving engine for any AI model of any size. Flexible. Easy. Enterprise-scale.

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction

A modular graph-based Retrieval-Augmented Generation (RAG) system

Run PyTorch LLMs locally on servers, desktop and mobile

Implementation of focal loss in pytorch for unbalanced classification.

Company Information Tracker

BERT for hierarchical text classification on Amazon product reviews and DBpedia.

Resource list for generating JSON using LLMs via function calling, tools, CFG. Libraries, Models, Notebooks, etc.

Implementation for MatMul-free LM.

Benchmarks of request throughput of vllm and NVIDIA NIM

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

🎉 performant confetti animation in the browser

Custom fastapi server packaged as docker image for Huggingface inference endpoints deployment

LLM inference in C/C++

Distribute and run LLMs with a single file.

Interactive JSON filter using jq