RAG Chatbot (Local & Free)

A Retrieval-Augmented Generation chatbot that answers questions from your own documents.

• Vector search: FAISS + SentenceTransformers
• LLM: Ollama (local, free) or OpenAI (optional)
• UI: Streamlit

Quickstart

python -m venv .venv
# Windows
. .venv\Scripts\activate
# macOS/Linux
# source .venv/bin/activate

pip install -r requirements.txt

# Pull a local model once (Ollama must be installed and running)
ollama pull llama3.2:3b

# Build the vector index after adding PDFs to data/
python index.py

# Run the app
streamlit run app.py

Add Data

Put PDFs in data/. (Optional) Add data/urls.txt with URLs (one per line).

Why this project?

• Demonstrates end-to-end GenAI with RAG (hot in the market)
• No vendor lock-in, runs entirely local
• Clean, resume-ready code and UI