agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
What is agentic-rag-for-dummies?
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
Overview of agentic-rag-for-dummies
What it is
This repository demonstrates how to build an Agentic RAG (Retrieval-Augmented Generation) system using LangGraph with minimal code. It provides both learning materials and an extensible architecture for building modular, agent-driven RAG systems.
Key features
- Hierarchical Indexing: searches small chunks for precision and retrieves large Parent chunks for context - Conversation Memory: maintains context across questions for natural dialogue - Query Clarification: rewrites ambiguous queries or pauses to ask the user for details - Agent Orchestration: LangGraph coordinates the full retrieval and reasoning workflow - Multi-Agent Map-Reduce: decomposes complex queries into parallel sub-queries - Self-Correction: re-queries automatically if initial results are insufficient - Context Compression: keeps working memory lean across long retrieval loops - Observability: tracks LLM calls, tool usage, and graph execution with Langfuse - Evaluation: evaluates retrieval and answer quality with RAGAS metrics
Use cases
The project offers two ways to use it: a Learning Path with an interactive notebook for understanding core concepts, and a Building Path with a modular project where each component can be independently adapted. It is suitable for anyone who wants to learn or build an Agentic RAG system with conversation memory and human-in-the-loop query clarification.
Getting started
See the repository README for installation and usage instructions.
License and pricing
The license is MIT. The project is open source.
Based on the project's public README and repository metadata.