netease-youdao/QAnything

Health v2 · maintenance only

Adoption not part of the score

14078 stars · 1343 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

QAnything is a local knowledge base question-answering system by NetEase Youdao that supports uploading and querying various document formats. It uses a two-stage retrieval pipeline with embedding reranking and LLM-based answer generation, deployable via Docker with offline support.

Use cases

• build a chatbot over my own documents
• ask questions about pdfs and word docs locally
• self-hosted knowledge base Q&A
• deploy an offline RAG system
• search internal documentation with natural language
• create a customer support knowledge assistant

When to choose

• you need a self-hosted, offline-capable RAG knowledge base
• you want document parsing plus two-stage retrieval out of the box
• you need a ready-made web UI and API for document Q&A

When to avoid

• you need a lightweight library to embed RAG in your own app
• AGPL-3.0 copyleft licensing is incompatible with your product
• you want to customize every retrieval pipeline component heavily

Facets

application · maturity active

rag llm-inference search-engine vector-database chatbot web-framework large-language-models artificial-intelligence self-hosted self-hosted python local-knowledge-base question-answering document-parsing two-stage-retrieval offline-deployment agpl retrieval-augmented-generation natural-language-processing knowledge-management docker linux web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="netease-youdao/QAnything")