Welcome to GRAG’s documentation!

GRAG is a simple python package that provides an easy end-to-end solution for implementing Retrieval Augmented Generation (RAG).

The package offers an easy way for running various LLMs locally, Thanks to LlamaCpp and also supports vector stores like Chroma and DeepLake. It also makes it easy to integrage support to any vector stores easy.

Contents:

• Get Started
  • GRAG Overview
  • Installation
  • Parse PDF
  • LLMs
  • Vector Stores
  • Configuration
• GRAG
  • Components
  • Prompts
  • Quantize
  • RAG
  • Module contents
• Cookbooks
  • Basic-RAG Cookbooks
  • Retriever-GUI Cookbooks
  • RAG-GUI Cookbooks

Indices and tables

• Index

• Module Index

• Search Page