HomeProjectsArticlesPK BoardAbout
Explore Projects

QAnything

Stale
GitHub Python AGPL-3.0

Description

QAnything is an open-source local knowledge base Q&A system by NetEase Youdao, supporting any file format with offline RAG capabilities for building private knowledge Q&A.

Key Features

  • Local knowledge base Q&A supporting PDF, Word, PPT, XLS, Markdown, images, CSV, and more
  • Two-stage vector retrieval with embedding + reranking for scalable accuracy
  • Full offline operation — supports air-gapped installation with no external network required
  • BCEmbedding bilingual retrieval with top MTEB semantic representation scores
  • One-click Docker Compose deployment with pure CPU support on Windows, Mac, and Linux
  • Customizable pipeline — OCR, embed, rerank components are modular and swappable

Use Cases

💡 Building private enterprise knowledge Q&A systems with sensitive document support
💡 Deploying offline RAG pipelines for industries requiring data sovereignty
💡 Processing multi-format documents for intelligent search and retrieval
💡 Creating custom chatbots powered by proprietary knowledge bases

Strengths & Limitations

✅ Strengths

  • • High community interest (14.1k stars)
  • • Established track record (2 years in production)

⚠️ Limitations

  • • No updates in over 17 months
  • • Restrictive license (AGPL-3.0)

Tags

rag qa knowledge-base python

Categories

📚 RAG Tools

Quick Start

git clone https://github.com/netease-youdao/QAnything.git && cd QAnything && docker compose up
Visit GitHub Visit Website

Related Projects

RAG-Anything

22.9k · Python
Active A+

All-in-one RAG framework supporting text, images, tables, equations and more document formats for retrieval-augmented generation with unified knowledge QA.

ragmultimodalknowledge-base +2
  • · End-to-end multimodal pipeline — Complete workflow from document ingestion to intelligent multimodal query answering
  • · Universal document support — Seamless processing of PDFs, Office documents, images and diverse file formats
  • · Specialized content analysis — Dedicated processors for images, tables, mathematical equations and heterogeneous content
View full details → View on GitHub

RAGFlow

88.6k · Go
Active A+

A leading open-source RAG engine that fuses cutting-edge retrieval-augmented generation with agent capabilities to create a superior context layer for LLMs.

ragdocument-understandingknowledge-base +3
  • · Deep document understanding - Extracts knowledge from complex unstructured data via deepdoc, supporting PDF, Word, PPT, Excel, images, and more
  • · Template-based chunking - Multiple intelligent chunking templates for explainable document segmentation and knowledge organization
  • · Traceable citations with reduced hallucinations - Visualizes text chunks for human intervention, answers include key reference sources
View full details → View on GitHub

RAGatouille

4.0k · Python
Stale C

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

ragpythonembedding +1
  • · ColBERT late-interaction retrieval: wraps advanced ColBERT models into simple APIs, enabling late-interaction retrieval methods in RAG pipelines without deep IR research knowledge
  • · End-to-end training and fine-tuning: built-in RAGTrainer and TrainingDataProcessor with automatic deduplication, positive/negative pairing and hard negative mining, supporting training from scratch or fine-tuning pretrained models
  • · Modular composable architecture: DataProcessor, NegativeMiner and other components can be used independently, with support for custom NegativeMiner integration into training pipelines
View on GitHub