langchain-rag-tutorial

Why we included this project

This tutorial works best as a self-teaching reference for retrieval-augmented generation with LangChain. It shows the whole pipeline on a small scale: install the dependencies, turn Alice in Wonderland into an embedded Chroma vector store, then ask questions through an OpenAI-backed LangChain chain. Because the scope stays small, it is easy to see how embeddings, vector search, and the LLM call fit together without a full application layer getting in the way. Teams unsure whether RAG suits their data can treat it as a quick sandbox to test the flow before adopting a bigger framework. It is a learning artifact, not deployable software, which is what makes it useful as a worked example.