Medical Diagnosis RAG

This is the FastAPI-based backend for the Medical Diagnosis Application, which provides authentication, PDF report upload, AI-powered medical diagnosis using LLaMA 3 via Groq API, and stores metadata in MongoDB with Pinecone for vector storage.

---

Core Features

✅ Role-based Authentication ( Doctor / Patient)

✅ PDF Report Upload

✅ Text Extraction & Chunking from PDFs

✅ AI Diagnosis Generation using Groq LLaMA 3

✅ Vector Storage with Pinecone for RAG retrieval

✅ MongoDB Integration for user, report, and diagnosis records

✅ Role-based Access Control for viewing and requesting diagnoses

---

Tech Stack

• Backend Framework: FastAPI
• Database: MongoDB
• Vector DB: Pinecone
• LLM API: Groq (LLaMA 3)
• PDF Processing: PyPDF2
• Environment Management: Python 3.10+

---

⚙️ Setup Instructions (Local)

1️⃣ Clone the Repository

git clone https://github.com/hit1403/Medic_chatBot.git
cd Medic_chatBot

2️⃣ Create Virtual Environment

python -m venv venv
source venv/bin/activate   # On Linux/Mac
venv\Scripts\activate      # On Windows

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Configure Environment Variables

Create a .env file and add:

MONGO_URI=
DB_NAME=
PINECONE_API_KEY=
PINECONE_INDEX_NAME=
PINECONE_ENV=
GROQ_API_KEY=
UPLOAD_DIR=
API_URL=

5️⃣ Run the Application

uvicorn server.main:app --reload

API will be available at: http://127.0.0.1:8000

---

▶️ API Endpoints

Method	Endpoint	Description
POST	/auth/signup	Register a new user
POST	/auth/login	Login user
POST	/reports/upload	Upload medical report
POST	/diagnosis/from_report	Request AI diagnosis
GET	/diagnosis/by_patient_name	View past diagnoses

---