This repository teaches how real-world RAG systems and LangGraph workflows are built.
✔ How documents → embeddings → vector DB
✔ How retrieval works
✔ How LLM uses context to answer
✔ How to modularize RAG properly
✔ How LangGraph orchestrates pipelines
- Build RAG from scratch
- Understand vector search
- Modularize RAG pipeline
- Integrate with LangGraph
pip install -r requirements.txt
# Running Example
Run from project root:
python langgraph_rag_pipeline/example.py