Blaxel Google ADK Agent

A template implementation of a conversational agent using Google Agent Development Kit (ADK) and GPT-4. This agent demonstrates the power of Google ADK for building interactive AI agents with tool integration capabilities and advanced conversation management.

📑 Table of Contents

• Features
• Quick Start
• Prerequisites
• Installation
• Usage
  • Running Locally
  • Testing
  • Deployment
• Project Structure
• Troubleshooting
• Contributing
• Support
• License

✨ Features

• Interactive conversational interface with Google ADK integration
• Tool integration support (including weather and search capabilities)
• Streaming responses for real-time interaction
• Built on Google ADK for efficient agent orchestration
• Advanced conversation state management
• Easy deployment and integration with Blaxel platform
• Google Cloud services integration capabilities

🚀 Quick Start

For those who want to get up and running quickly:

# Clone the repository
git clone https://github.com/blaxel-ai/template-google-adk-py.git

# Navigate to the project directory
cd template-google-adk-py

# Install dependencies
uv sync

# Start the server
bl serve --hotreload

# In another terminal, test the agent
bl chat --local blaxel-agent

📋 Prerequisites

• Python: 3.10 or later
• UV: An extremely fast Python package and project manager, written in Rust
• Google Cloud Account: For Google ADK service access and integration
• Blaxel Platform Setup: Complete Blaxel setup by following the quickstart guide
  • Blaxel CLI: Ensure you have the Blaxel CLI installed. If not, install it globally:

    curl -fsSL https://raw.githubusercontent.com/blaxel-ai/toolkit/main/install.sh | BINDIR=/usr/local/bin sudo -E sh

  • Blaxel login: Login to Blaxel platform

    bl login YOUR-WORKSPACE

💻 Installation

Clone the repository and install dependencies:

git clone https://github.com/blaxel-ai/template-google-adk-py.git
cd template-google-adk-py
uv sync

🔧 Usage

Running the Server Locally

Start the development server with hot reloading:

bl serve --hotreload

Note: This command starts the server and enables hot reload so that changes to the source code are automatically reflected.

Testing your agent

You can test your agent using the chat interface:

bl chat --local blaxel-agent

Or run it directly with specific input:

bl run agent blaxel-agent --local --data '{"inputs": "What is the weather in Paris?"}'

Deploying to Blaxel

When you are ready to deploy your application:

bl deploy

This command uses your code and the configuration files under the .blaxel directory to deploy your application.

📁 Project Structure

• src/main.py - Application entry point
• src/agent.py - Core agent implementation with Google ADK integration
• src/server/ - Server implementation and routing
  • router.py - API route definitions
  • middleware.py - Request/response middleware
• pyproject.toml - UV package manager configuration
• blaxel.toml - Blaxel deployment configuration

❓ Troubleshooting

Common Issues

1. Blaxel Platform Issues:

   • Ensure you're logged in to your workspace: bl login MY-WORKSPACE
   • Verify models are available: bl get models
   • Check that functions exist: bl get functions

2. Google ADK Configuration Issues:

   • Verify Google ADK SDK installation and configuration
   • Check agent definition and conversation flow setup
   • Review Google Cloud project permissions

3. Agent Conversation Flow Problems:

   • Check conversation state management and transitions
   • Verify intent handling and response generation
   • Monitor conversation context and memory

4. Tool Integration Failures:

   • Ensure tool definitions are compatible with Google ADK
   • Check tool execution permissions through Blaxel platform
   • Verify tool response formats match ADK expectations

5. Deployment and Configuration:

   • Check Google Cloud service account configurations
   • Verify ADK agent deployment settings
   • Review endpoint configurations and routing

For more help, please submit an issue on GitHub.

👥 Contributing

Contributions are welcome! Here's how you can contribute:

1. Fork the repository
2. Create a feature branch:

   git checkout -b feature/amazing-feature

3. Commit your changes:

   git commit -m 'Add amazing feature'

4. Push to the branch:

   git push origin feature/amazing-feature

5. Submit a Pull Request

Please make sure to update tests as appropriate and follow the code style of the project.

🆘 Support

If you need help with this template:

• Submit an issue for bug reports or feature requests
• Visit the Blaxel Documentation for platform guidance
• Check the Google ADK Documentation for framework-specific help
• Join our Discord Community for real-time assistance

📄 License

This project is licensed under the MIT License. See the LICENSE file for more details.