louisbrulenaudet/ragoon
High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡
Supports multi-model embeddings production with GPU acceleration and multiple quantization strategies (int8, ubinary) for efficient index creation via FAISS and USearch. Combines vector similarity search with dynamic web scraping and LLM integration (OpenAI, Groq) to augment RAG systems with real-time contextual information. Includes dimensionality reduction visualization (PCA, t-SNE) and seamless Hugging Face dataset integration for end-to-end NLP pipelines.
Stars
70
Forks
7
Language
Jupyter Notebook
License
Apache-2.0
Last pushed
Nov 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/louisbrulenaudet/ragoon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Siddhant-K-code/distill
Reliable LLM outputs start with clean context. Deterministic deduplication, compression, and...
pesu-dev/ask-pesu
A RAG pipeline for question answering about PES University
namtroi/RAGBase
Open Source RAG ETL Platform. Turns PDFs, Docs & Slides into queryable vectors. Features a...
B-A-M-N/FlockParser
Distributed document RAG system with intelligent GPU/CPU orchestration. Auto-discovers...
aws-samples/rag-with-amazon-postgresql-using-pgvector-and-sagemaker
Question Answering application with Large Language Models (LLMs) and Amazon Postgresql using pgvector