AskMyDoc — RAG-Powered PDF Chatbot

Upload any PDF and ask questions about it in plain English. Answers are generated using retrieval-augmented generation (RAG), grounded directly in the document's content rather than the model's general knowledge.

How it works

1. Document ingestion — uploaded PDF is parsed and split into chunks
2. Embedding — each chunk is converted into a vector embedding
3. Retrieval — on a user query, the most relevant chunks are retrieved via similarity search using FAISS
4. Generation — retrieved context is passed to an LLM, which generates an answer grounded in the document

Tech stack

• Python
• LangChain — orchestrates the RAG pipeline
• FAISS — vector similarity search
• Groq — LLM inference

Run it locally

pip install -r requirements.txt
python app.py

Why I built this

Built to understand how RAG pipelines work end-to-end — chunking strategy, embedding, retrieval, and grounded generation — rather than just calling an LLM API directly.