QuivrHQ/quivr

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: PGVector, Faiss. Any Files. Anyway you want.

48
/ 100
Emerging

Implements a modular workflow-based architecture using YAML configuration for composable RAG pipelines, enabling users to define custom node graphs with built-in components like query rewriting, retrieval, and generation stages. Integrates with Megaparse for advanced document parsing and supports external rerankers (e.g., Cohere) plus conversation history filtering to refine retrieval quality. Ships as a lightweight Python library (`quivr-core`) designed for embedding directly into applications with minimal boilerplate.

38,997 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

38,997

Forks

3,727

Language

Python

License

Last pushed

Jul 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/QuivrHQ/quivr"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.