
Docs & PDF Q&A
quivr
A RAG toolkit for building products that answer from your own documents
★ 39k
July 2025
Not stated
Docs & PDF Q&A
What it does
Components for ingesting your own files - PDF, text, Markdown and more - and having an LLM answer from them, so you can build a document-grounded assistant into your own product. Works with OpenAI, Anthropic, Mistral and others, and the retrieval pipeline can be customised with web search or extra tools. This is a developer library, not a finished app: if you just want to drop in documents and start asking questions, look elsewhere. You pay for the LLM calls.
Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.
Screenshots & visuals

Before you start
- Setup difficultySome setup needed
- Command lineRequired
- API keyRequired
- Sends data onlineYes
Judged automatically from the project's own metadata. Always confirm on the official page.
quivr FAQ
- Is quivr free?
- quivr itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.
- Do I need to install anything or write code to use quivr?
- It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
- Does quivr work on a phone?
- No. It needs a computer.
- Can I use quivr commercially?
- The project does not state a clear licence, so commercial use cannot be confirmed here. Check the official page or ask the author before using it at work.