Kuma AI Travel Agent

An AI-powered travel agent that generates personalized travel itineraries using Google's Gemini model.

Features

  • Generates two distinct travel options based on your preferences

  • Customizable model parameters (temperature, top_p, etc.)

  • Rich terminal output with Markdown formatting

  • Easy-to-use command-line interface

Prerequisites

  • Python 3.8+

  • Google Gemini API key

Installation

  1. Clone this repository:

    git clone https://github.com/yourusername/kuma-ai-travel-agent.git
cd kuma-ai-travel-agent

  2. Install the required packages:

    pip install -r requirements.txt

  3. Set up your Gemini API key:

    • Get an API key from Google AI Studio

    • Copy .env.example to .env

    • Add your API key to the .env file

Usage

Run the travel agent:

Follow the prompts to:

  1. Enter your departure location

  2. Enter your destination

  3. Specify the number of days for your trip

  4. (Optional) Adjust the creativity level (0.0-1.0)

The agent will generate two distinct travel itineraries in Markdown format.

Configuration

You can customize the model's behavior by modifying the default_config in the TravelAgent class in travel_agent.py. Available parameters include:

  • model: The Gemini model to use (default: "gemini-pro")

  • temperature: Controls randomness (0.0-1.0, default: 0.8)

  • top_p: Nucleus sampling parameter (default: 0.9)

  • top_k: Top-k sampling parameter (default: 40)

  • max_output_tokens: Maximum length of the response (default: 2000)

Example Output

Example

License

MIT License

Previouskuma-ai-agentsNextKuma AI Travel Agent

Last updated

Was this helpful?