Welecome to FlexRAG Documentation

FlexRAG is a highly reproducible, easy-to-use, and high-performance RAG framework designed for both research and application scenarios. It supports text, multimodal, and web-based RAG, providing a complete RAG pipeline and evaluation process. With built-in asynchronous processing and persistent caching, it ensures efficiency and scalability. Easily load retrievers from Hugging Face and quickly build powerful RAG solutions out of the box.

Note

FlexRAG is under active development and is currently in the alpha stage. We welcome contributions from the community and are open to feedback and suggestions.

Getting Started:

• Installation
• Quickstart: Deploying and Evaluating RAG Assistant with FlexRAG
• Quickstart: Building your own RAG application

Tutorial:

• Preparing the Knowledge Base
• Preparing the Retriever
• Building Your Own RAG Assistant
• FlexRAG Entrypoints
• Using Registers
• Advance: Acquiring Information from the Web

API Reference Manual:

• Assistant
• Chunking
• Context Refiner
• Datasets
• Document Parser
• Encoders
• Generators
• Metrics
• Prompt
• Retrievers
• Rankers
• Tokenizer
• Text Processing
• Utils