Stars
A curated list of resources dedicated to retrieval-augmented generation (RAG).
Open-source vector similarity search for Postgres
Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba
Joplin plugin to combine one or more notes to a new one.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.
A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL
PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.
A Python Library for Standardized and Reproducible Data Management in Recommender Systems
The KIMERA infrastructure for IR systems evaluation
An extremely fast Python package and project manager, written in Rust.
Fast and Flexible Neural Click Models in JAX
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Long context killed RAG - or, did it?
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
Make awesome display tables using Python
Python tool for converting files and office documents to Markdown.
🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techn…
A Collection of BM25 Algorithms in Python
Fast BM25 search in Python, powered by Numpy and Numba
A link to frameworks useful for the evaluation and reproducibility of recorecommendation algorithms