# GiovanniPasq/agentic-rag-for-dummies

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Repository: https://github.com/GiovanniPasq/agentic-rag-for-dummies
Canonical: https://ross.abutalabs.com/products/agentic-rag-for-dummies
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: agentic-ai, agentic-rag, agents, rag, agent, bm25, rag-chatbot, rag-pipeline, langgraph, llm, retrieval-augmented-generation, retrieval-augmented-generation-rag, gradio, langchain, qdrant, ollama, ai-agents, generative-ai, rag-agents
Last push: 2026-07-25T11:33:02+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 89, longevity 23
- inputs: {"age_days": 324, "days_push": 39, "days_rel": 73, "gap_med": 23, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3969, forks 514 (observed 2026-08-28T04:08:30.776974+00:00)

## What it is
A tutorial-style repository and modular reference implementation for building Agentic RAG systems with LangGraph. It combines learning materials (notebooks, Colab) with an extensible architecture featuring hierarchical indexing, conversation memory, query clarification, and multi-agent map-reduce.

## Use cases
- learn how to build an agentic RAG system
- build a RAG chatbot with conversation memory
- implement parent-document retrieval with Qdrant
- run RAG locally with Ollama
- add human-in-the-loop query clarification to a RAG pipeline
- decompose complex queries into parallel sub-queries with LangGraph
- understand hybrid BM25 and vector retrieval

## When to choose
- you want a hands-on, well-documented introduction to agentic RAG with LangGraph
- you need a modular, extensible RAG architecture to adapt for your own project
- you prefer running LLMs locally with Ollama or swapping providers (OpenAI, Anthropic, Google)
- you want runnable notebooks plus a production-style pipeline in one repo

## When to avoid
- you need a battle-tested production RAG service rather than a learning-oriented reference
- you want a framework-agnostic solution without LangChain/LangGraph dependencies
- you need a no-code or hosted RAG product
- your stack is not Python 3.11+

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, agent-framework, llm-inference, search-engine, chatbot
- domain: large-language-models, machine-learning, tutorials
- platform: python, cross-platform, self-hosted
- tags: langgraph, langchain, qdrant, ollama, gradio, bm25, agentic-rag, jupyter-notebook, parent-document-retrieval, conversation-memory, human-in-the-loop, map-reduce, self-correction, retrieval-augmented-generation, ai-agents, docker

## Member repositories
- GiovanniPasq/agentic-rag-for-dummies (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.776974+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:22.648542+00:00, confidence not recorded.
  - readme: https://github.com/GiovanniPasq/agentic-rag-for-dummies (fetched 2026-08-28T04:08:30.776974+00:00, sha 3af116c55d6d)
- Data as of 2026-08-30T08:39:29.467469+00:00.