#5353rd of 110 in Learning and cookbooks
agentic-rag-for-dummies
LangGraph agentic RAG tutorial notebook and modular app with Qdrant hybrid search
- Stars
- 4.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Jupyter Notebook
Missed the latest GitHub check; these facts may be older.
Overview
Python reference implementation of agentic RAG built on LangGraph. It indexes PDFs (converted to Markdown) into Qdrant with parent/child chunking and hybrid dense plus BM25 search, then answers queries with parallel per-sub-query agents, query clarification with human-in-the-loop pauses, and conversation memory. Ships as an interactive Colab notebook and a modular Ollama-first project, with examples for OpenAI, Anthropic and Google.
Who it is for: Engineers learning to build agentic RAG pipelines with LangGraph
Strengths
- Parent/child chunking: searches 500-char child chunks, returns 2000-4000-char parent sections
- Hybrid retrieval in Qdrant with Qwen3-Embedding-0.6B dense and BM25 sparse vectors
- Map-reduce subgraphs run one agent per sub-query, with self-correction and context compression
- Includes Langfuse tracing and a RAGAS evaluation notebook
Weaknesses
- Reference code and notebooks, not a packaged app with accounts or a deployment setup
- No Docker or compose files detected
- Runnable app is Ollama-first; cloud providers require adapting code from examples
- Models under 8B may ignore retrieval instructions or hallucinate, per README
What it needs
- Needs Qdrant, Ollama, LangGraph, LangChain, Langfuse (optional), RAGAS (optional)
- Models: Ollama (granite4.1:8b default), OpenAI, Anthropic, Google Gemini, Qwen3-Embedding-0.6B embeddings
Also in Learning and cookbooks
See all 110| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 92 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 82 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 82 out of 100 |
| #5 | agents-towards-productionJupyter tutorials for taking LLM agents from prototype to production | 82 out of 100 |