Quivr

Quivr is an opinionated Retrieval-Augmented Generation framework that integrates Generative AI functionality into software applications.

Quivr is an opinionated, fast, and efficient Retrieval-Augmented Generation (RAG) framework designed for developers to incorporate into existing software products. Users install the quivr-core package to handle data ingestion and file processing, enabling them to focus on their specific product logic. The system supports various file formats including PDF, TXT, and Markdown, and allows for the addition of custom parsers. It is compatible with multiple LLMs such as OpenAI, Anthropic, Mistral, and Gemma. Integration with Megaparse is supported for file ingestion, and users can customize their RAG implementation by adding internet search or specific tools.

Quivr at a glance

Best for: Software engineer
Runs on: Python
Pricing: Free
Released: May 2023
Category: AI coding tool
Website: core.quivr.com

Key features

Opinionated RAG architecture for fast implementation
Support for multiple LLMs including OpenAI, Anthropic, Mistral, and Gemma
Compatibility with diverse file formats like PDF, TXT, and Markdown
Customizable RAG pipelines with tools and internet search
Integration with Megaparse for file ingestion
Support for custom file parsers

Use it for

Building a personal assistant application
Adding document-based Q&A to software products
Ingesting and querying data from various file types

Alternatives to Quivr

RAG Evaluation Starter — Runs five metrics locally with no SaaS signup or mandatory API key required.
My RAG — Compare Python and Java implementations sharing identical data.
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
DeepEval — Provides over fifty research-backed metrics and pytest-native execution.
Genkit — Provides unified APIs and local developer tools for AI application workflows.
RAGFlow — Provides an integrated platform combining data processing with agent workflows.
Qdrant — Fast filtered vector search, self-hosted or in a managed cloud
llmware — Build private, local RAG pipelines with 300+ prepackaged models and integrated document parsing.
seekdb — Unifies relational, vector, and text data for production-grade AI agents.
fal — Access 1,000+ generative models and high-performance serverless GPUs.
Weaviate — Stores data objects and vectors for semantic and hybrid search capabilities.
Jevcrawl — Finds answer pages more often and cheaper than letting Claude crawl.

All Quivr alternatives