RAG Chatbot for Document Q&A System (LangChain + Vector Search)

A Retrieval-Augmented Generation (RAG) chatbot that lets you ask natural-language questions over your own documents and data: PDFs and structured/tabular files (CSV) and get grounded answers instead of generic AI guesses.

How it works:

Documents are loaded and converted into a structured format

Content is embedded and stored in a vector database (ChromaDB)

When a question is asked, the system retrieves the most relevant content via similarity search

An LLM generates an answer using only the retrieved context keeping answers grounded in the actual source material rather than relying on the model's general knowledge.

This architecture works with any document set, swap in different PDFs/CSVs and the system builds a new knowledge base automatically, without retraining or fine-tuning.