Sandeep17022205/Doctor-AI

🏥 Healthcare RAG Chatbot

A minimal ChatGPT-like chatbot UI built with React + Tailwind (Vite) and a FastAPI backend that integrates with Google Gemini API for RAG (Retrieval Augmented Generation). All data (PDF/TXT uploads) are stored persistently in ChromaDB, per user session.

🚀 Features

• —🧠 RAG + LangChain: Context-aware answers from uploaded documents.
• —📂 File Upload: Supports PDF/TXT uploads.
• —💾 Persistent Memory: Saves conversation + embeddings in ChromaDB.
• —💡 Gemini API: Uses Google Gemini as the LLM.
• —🎨 Frontend: Minimal ChatGPT-like UI (React + Tailwind).
• —🔗 Single Hugging Face Space (Docker): Runs backend + frontend together.

⚙️ Environment Variables

Set the following inside Hugging Face → Settings → Variables & secrets:

🐳 Running on Hugging Face (Docker)

1. 1.Create a new Space → Docker template.
2. 2.Upload this repository as ZIP.
3. 3.Add your `GOOGLE_API_KEY` in Settings → Secrets.
4. 4.Hugging Face will automatically build & run both frontend and backend.

💻 Running Locally

# Clone repo
git clone <repo-url>
cd <repo>

# Backend
pip install -r requirements.txt
uvicorn app:app --reload --port 8000

# Frontend
cd frontend
npm install
npm run dev