Quivr is a Python-based framework for building retrieval-augmented generation (RAG) systems that integrate generative AI capabilities into existing applications. The project positions itself as an opinionated RAG solution designed to abstract away the complexity of RAG implementation, allowing developers to focus on their product rather than infrastructure. The framework is available as quivr-core and can be installed and integrated into projects with minimal setup, requiring only Python 3.10 or newer.
The core functionality centers on flexible LLM and vector store support. Quivr works with any large language model including GPT-4, Groq, and Llama, and supports multiple vector stores such as PGVector and Faiss. The framework handles diverse file formats including PDF, TXT, and Markdown, with extensibility for custom parsers. Users can configure RAG workflows through YAML files, with a basic RAG setup requiring only five lines of code. The system supports customization through features like internet search integration and tool addition, with documentation available at core.quivr.com.
The project integrates with Megaparse, a companion tool for file ingestion, creating a complete pipeline from document processing to question-answering. The framework supports multiple API providers including Anthropic, OpenAI, and Mistral, as well as local models through Ollama. Configuration is handled through environment variables for API keys and YAML files for workflow definition.
Development activity shows significant engagement with 446 tracked issues and pull requests. The median response latency for issues and PRs is 0.0 hours, though the mean latency of 1292.0 hours indicates some items receive delayed attention. The most prevalent issue labels are Stale with 188 occurrences, bug with 148, and area: backend with 109, suggesting ongoing maintenance challenges and backend-focused development. StanGirard leads contributor activity with 241 tracked events, followed by jacopo-chevallard with 146 events and chloedia with 72 events.
The repository maintains connections with major open-source projects including microsoft/vscode, microsoft/typescript, and rust-lang/rust through overlapping contributors, indicating cross-pollination with significant developer communities. The project is backed by Y Combinator and Theodo, providing institutional support for development. The codebase is licensed under Apache 2.0, and the project actively solicits contributions through labeled good first issues and maintains a public project board for tracking development priorities. The framework emphasizes privacy and security as core topics, reflecting concerns relevant to applications handling sensitive data through AI systems.
