Overview

This project demonstrates a powerful multi-modal chatbot built using OpenAI's Agent Framework. The chatbot can handle various tasks including financial data retrieval, weather information, image generation, and creative content creation. It showcases the capabilities of modern AI agents in handling complex, multi-step tasks with external API integrations.

Demo action

Tech Stack 🛠️

  • OpenAI API & Agent SDK
  • Anthropic API
  • External API Integrations:
    1. Yahoo Finance API 💰
    2. OpenWeatherMap API 🌤️
    3. Gemini API for Image Generation 🎨

Architecture Diagram 📊

tech flow

Implementation Details 🔧

  1. Agent Core 🧠

    • OpenAI Agent Framework for task orchestration
    • Anthropic API for enhanced reasoning capabilities
    • Function calling for external API integration
  2. Available Tools 🛠️

    • Stock price lookup via Yahoo Finance
    • Weather data retrieval
    • Image generation using Gemini
    • ASCII art generation
    • Poem generation
  3. Workflow 🔄

    • User query processing
    • Intent recognition
    • Tool selection and execution
    • Response generation and formatting
    • Multi-modal output delivery

Key Features ✨

  • Multi-modal capabilities
  • Real-time data integration
  • Creative content generation
  • Seamless API integration
  • Natural language understanding

Future Enhancements 🚀

  • Additional API integrations
  • Enhanced error handling
  • Performance optimization
  • Extended creative capabilities