Skip to content

Latest commit

 

History

History
17 lines (12 loc) · 819 Bytes

README.md

File metadata and controls

17 lines (12 loc) · 819 Bytes

RAG_app

A Retrieval-Augmented Generation (RAG) application built with LangChain that enhances Large Language Model responses with relevant context from your documents. This application combines the power of:

  • Document Processing: Efficiently splits and processes your text documents
  • Vector Storage: Uses Chroma DB for semantic search and retrieval
  • Embeddings: Leverages HuggingFace's sentence-transformers for document embeddings
  • Custom LLM Integration: Flexible integration with any LLM API endpoint
  • RAG Pipeline: Combines document retrieval with LLM generation for accurate, context-aware responses

Quick Start

To download and run the installation script:

curl -fsSL https://raw.githubusercontent.com/AkkhilCodingHub/RAG_app/refs/heads/main/install_rag.py | python3