RAG Chatbot

A Retrieval-Augmented Generation (RAG) chatbot built with FastAPI, Streamlit, FAISS, and Ollama.
This chatbot can read PDFs, create embeddings, and answer user queries with contextual memory.

---

Features

• Upload PDF documents and build a vector index
• FAISS-based semantic search for relevant chunks
• Conversational memory (remembers chat history)
• Powered by local Ollama LLM (llama3.2:3b by default)
• Frontend with Streamlit, backend with FastAPI
• Supports summarization, Q&A, multi-turn conversations

---

Project Structure

RAG_Chatbot/ │── backend/ │ ├── config.py │ ├── rag_qa.py │ ├── server.py │ ├── vector_store.py │ ├── faiss_index/ │ └── venv/ (ignored by git) │ │── frontend.py # Streamlit frontend │── requirements.txt │── .gitignore

---

🛠️ Installation

1. Clone the Repository

git clone https://github.com/yashas2604/RAG_Chatbot.git cd RAG_Chatbot

Project Structure

cd backend python3 -m venv venv source venv/bin/activate

Running the App

Start the Backend In one terminal: cd backend source venv/bin/activate uvicorn server:app --reload --port 8000 Backend will be running on: 👉 http://127.0.0.1:8000

Start the Frontend In another terminal: cd RAG_Chatbot source backend/venv/bin/activate streamlit run frontend.py Frontend will be running on: 👉 http://localhost:8501