Implement an End-to-End RAG Pipeline Using LangChain

Task: Implement an end-to-end Retrieval-Augmented Generation (RAG) pipeline using LangChain. Approach: Load and chunk source documents, embed chunks with an embedding model, store/index vectors (e.g. FAISS/Chroma via LangChain's vector store integrations), implement a retriever to fetch top-k relevant chunks for a query, and wire a LangChain chain that injects retrieved context into a prompt template before calling the LLM. Discuss chunking strategy, retrieval top-k tuning, and prompt construction to keep the LLM grounded in retrieved context.