Neura Market
Quivr logo

Quivr

Free

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.

FreeFree tier
Inputs: text, fileOutputs: text
Type
Open Source
Visit Website GitHub (39.2k stars)

About Quivr

Quivr is an open-source, opinionated RAG (Retrieval-Augmented Generation) framework that helps developers build a 'second brain' and integrate Generative AI into their applications. It is designed to be fast, efficient, and customizable, allowing users to focus on their product rather than the underlying RAG infrastructure. Quivr supports any LLM (e.g., OpenAI, Anthropic, Mistral, Gemma), any file type (PDF, TXT, Markdown), and can be extended with custom parsers, internet search, and other tools. It integrates seamlessly with Megaparse for file ingestion and offers easy 5-line code setup. With over 39,000 GitHub stars, Quivr is a popular choice for adding GenAI capabilities to existing products.

Key Features

Opinionated RAG that is fast and efficient
Works with any LLM (OpenAI, Anthropic, Mistral, Gemma, etc.)
Supports any file type (PDF, TXT, Markdown, etc.) with custom parsers
Customizable RAG with internet search and tool integration
Integration with Megaparse for file ingestion
Simple 5-line code setup to create a brain and ask questions
Open source with Python 3.10+ support

Pros & Cons

Pros
  • Opinionated design saves development time on RAG infrastructure
  • Supports a wide variety of LLMs and file types out of the box
  • Easy to integrate with just 5 lines of code
  • Customizable with parsers, internet search, and additional tools
  • Open source with active community and 39k+ stars
  • Works with Megaparse for advanced file parsing

Best For

Building a personal second brain and assistantIntegrating GenAI into existing products with minimal effortDocument question answering and file ingestionCustom RAG applications with any LLM and vector store

FAQ

What is Quivr?
Quivr is an open-source, opinionated RAG framework that helps build a second brain using GenerativeAI. It acts as a personal assistant and allows you to ingest files and ask questions.
How do I install Quivr?
Install Quivr via pip: `pip install quivr-core`. Requires Python 3.10 or newer.
How do I create a RAG with Quivr?
You can create a RAG in 5 lines of code using the `Brain.from_files()` method, then call `brain.ask()` to ask questions.