---
title: rag_ielts
app_file: app.py
sdk: streamlit
emoji: 📚
colorFrom: green
colorTo: indigo
pinned: true
sdk_version: 1.41.1
---
# Exam Content Management System

A Streamlit application for managing and generating exam content using Azure OpenAI and Supabase.

## Features

- Upload and process PDF files containing exam content
- Generate questions based on exam type (SAT, IELTS, TOEFL)
- Store and manage exam content in Supabase
- View and manage questions with filtering capabilities
- Analytics dashboard with detailed metrics
- Question rewriting and fixing capabilities

## Prerequisites

- Python 3.8+
- Supabase database
- Azure OpenAI API access

## Installation

1. Clone the repository:
```bash
git clone <repository-url>
cd <repository-directory>
```

2. Install dependencies:
```bash
pip install -r requirements.txt
```

3. Set up environment variables:
Create a `.env` file with the following variables:
```
AZURE_OPENAI_KEY=your_azure_openai_key
AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint
AZURE_OPENAI_DEPLOYMENT_NAME=your_deployment_name
SUPABASE_DB_URL=your_supabase_url
SUPABASE_API_KEY=your_supabase_api_key
```

## Running the Application

1. Start the Streamlit app:
```bash
streamlit run app.py
```

2. Open your browser and navigate to the URL shown in the terminal (usually http://localhost:8501)

## Usage

### 1. Upload & Generate
- Select exam type (SAT, IELTS, or TOEFL)
- Upload PDF files containing exam content
- Click "Generate and Upload Questions" to process files
- Download generated questions as JSON if needed

### 2. View Questions
- Browse questions with filtering options:
  - Exam Type
  - Domain
  - Subdomain
  - Topic
  - Difficulty Level
- Rewrite or delete individual questions
- View detailed explanations and answers

### 3. Analytics
- View comprehensive analytics dashboard
- Monitor question distribution
- Track content quality metrics
- Analyze domain coverage
- View generation timeline

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

## License

This project is licensed under the MIT License - see the LICENSE file for details.