Welcome to XRAG’s documentation!

XRAG is a benchmarking framework designed to evaluate the foundational components of advanced Retrieval-Augmented Generation (RAG) systems. By dissecting and analyzing each core module, XRAG provides insights into how different configurations and components impact the overall performance of RAG systems.

Documentation:

• Getting Started
  • Subpackages
    • Installation
    • QuickStart
• Data
  • Subpackages
    • XRAG_Data_Schema
    • Load XRAG Data
    • Prepare Your Data
• Index
  • Subpackages
    • EmbeddingModule
    • VectorIndex
• Config
  • Subpackages
    • API_KEYS
    • Parameters_Setting
    • XRAG_Prompts
    • XRAG_Lanucher
• Advanced modules
  • Subpackages
    • Pre-retrieval
    • Retrieval
    • Post-retrieval
    • Generator
• Evaluation
  • Subpackages
    • ConR_Evaluation
    • ConG_Evaluation
    • CogL_Evaluation
• Serving
  • Subpackages
    • Interactive Web UI
    • Ollama
    • XRAG APIs
    • XRAG Cli
• API reference
  • Subpackages
    • xrag.data package
    • xrag.embs package
    • xrag.eval package
    • xrag.index package
    • xrag.launcher package
    • xrag.llms package
    • xrag.process package
    • xrag.retrievers package
    • xrag.webui package
  • Submodules
    • xrag.cli module
    • xrag.config module
  • Module contents