Skip to content

A multi-stage RAG (Retrieval-Augmented Generation) system featuring local LLMs (Ollama/Gemma), hybrid search, and semantic re-ranking with Cross-Encoders.

Notifications You must be signed in to change notification settings

adithyanum/RAG-Projects

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Multi-Stage RAG Assistant 🚀

Project Overview

This project demonstrates the evolution of a RAG system, from basic retrieval to advanced re-ranking and agentic reasoning.

Versions

  • V1: Naive RAG (rag_pdf/, rag_obsidian/): Basic vector search implementation.
  • V2: Advanced RAG (rag_multi/): Integrated Hybrid Search and Cross-Encoder Re-Ranking.
  • V3: Agentic RAG (agentic_rag/): (In Progress) Implementing a ReAct Agent for autonomous tool use.

About

A multi-stage RAG (Retrieval-Augmented Generation) system featuring local LLMs (Ollama/Gemma), hybrid search, and semantic re-ranking with Cross-Encoders.

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages