Skip to content

prdp1137/agentic-rag

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Agentic RAG

A high-performance, multi-agent Retrieval-Augmented Generation system built with LangGraph and Qdrant. This architecture supports adaptive routing, self-correction, and hybrid search with advanced re-ranking.

Key Features

Cyclic graph architecture using LangGraph for complex reasoning loops. Combines Dense (Vector) and Sparse (BM25/SPLADE) retrieval using Qdrant. Implements "Corrective RAG" (CRAG) where agents grade retrieved documents and rewrite queries if necessary. Configured for Binary Quantization to handle 10M+ vectors efficiently. PostgreSQL persistence layer for state recovery and Human-in-the-Loop workflows.

About

Multi-agent Retrieval-Augmented Generation (RAG) system built with LangGraph and Qdrant supporting adaptive routing, self-correction, and hybrid search with re-ranking.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages