Cette page est affichée en anglais. Une traduction française est en cours.
ScriptsApr 1, 2026·1 min de lecture

Quivr — Opinionated RAG Framework for Any LLM

Quivr is an opinionated RAG framework supporting any LLM, multiple file types, and customizable retrieval. 39.1K+ stars. Apache 2.0.

Introduction

Quivr is an opinionated RAG framework that simplifies integrating generative AI into applications. With 39,100+ GitHub stars and Apache 2.0 license, it works with any LLM (OpenAI, Anthropic, Mistral, Groq), supports multiple file types (PDF, TXT, Markdown, custom parsers), provides customizable RAG workflows with reranking and history management, and configures via YAML.

Best for: Developers building RAG applications with minimal setup Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf


Key Features

  • Any LLM (OpenAI, Anthropic, Mistral, Groq)
  • Multiple file types (PDF, TXT, Markdown)
  • Customizable retrieval with reranking
  • YAML configuration
  • Megaparse for advanced file processing
  • History management

FAQ

Q: What is Quivr? A: Opinionated RAG framework with 39.1K+ stars. Any LLM, multiple file types, customizable retrieval. Apache 2.0.

Q: How do I install Quivr? A: pip install quivr-core. Brain.from_files() to start.


🙏

Source et remerciements

QuivrHQ/quivr — 39,100+ GitHub stars

Discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires