Scorecard Streamlit Demo

A simple Streamlit demo app showing how to integrate AI evaluation with Scorecard.

Features

• 🤖 Basic OpenAI chat interface
• ⚙️ Model selection (GPT-4, GPT-3.5-turbo)
• 💬 Chat history
• 🔐 Secure API key handling

Quick Start

1. Install dependencies:

   pip install -r requirements.txt

2. Set up environment:

   export OPENAI_API_KEY="your_openai_api_key"

3. Run the app:

   streamlit run app.py

4. Open in browser: Navigate to http://localhost:8501

Usage

1. Enter your OpenAI API key in the sidebar
2. Select your preferred model
3. Start chatting with the AI assistant
4. Use the "Clear Chat" button to reset conversation

Roadmap

• Scorecard tracing integration
• Test case creation
• GitHub Actions for automated evaluation
• Performance metrics

Contributing

This demo is part of the Scorecard ecosystem for AI evaluation and testing.