Travel_Agent is an intelligent, autonomous agent designed to assist users in planning travel itineraries. Built using Google's Agent Development Kit (ADK), this project demonstrates how to orchestrate GenAI workflows to solve multi-step reasoning tasks.
The agent takes natural language queries (e.g., "Plan a 3-day trip to Paris on a budget") and generates structured travel plans, demonstrating the power of agentic workflows in real-world scenarios.
- Agentic Workflow: Utilizes the ADK framework to structure reasoning loops and decision-making processes.
- Natural Language Processing: Understands complex travel constraints like budget, dietary restrictions, and time preferences.
- Modular Design: Clean separation of agent logic (
agent.py) making it easy to extend with new tools. - Python-Native: Fully implemented in Python for easy integration and deployment.
- Language: Python
- Framework: Google Agent Development Kit (ADK)
- Model: Gemini Pro (via Google GenAI SDK)
Before running the agent, ensure you have the following:
- Python 3.10 or higher installed.
- A Google Cloud Project (if using Vertex AI) or a valid API Key for Gemini.
-
Clone the repository:
git clone [https://github.com/Dhineshkumar272005/Travel_Agent.git](https://github.com/Dhineshkumar272005/Travel_Agent.git) cd Travel_Agent -
Create a virtual environment (Recommended):
python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate`
-
Install dependencies: (Note: Ensure you have the ADK and GenAI libraries installed)
pip install google-generativeai # Add other requirements here if you have a requirements.txt -
Set up Environment Variables: Create a
.envfile in the root directory and add your API keys:GOOGLE_API_KEY=your_api_key_here
To start the agent, simply run the main script:
python agent.py