Umami Analytics

🚀 Umami Usage Guide

Umami is a powerful tool that can be customized to meet specific analytical needs. This guide will walk you through the installation, configuration, customization, and best practices of Umami.

🚀 Quick Start

📦 Installation

1.1 Install Dependencies

Run the following command to install the necessary Python packages:

pip install umami python-dotenv fastapi uvicorn

1.2 Configure Environment Variables

Create a .env file and add the following content:

DB_HOST=your-database-host
DB_PORT=5432
DB_NAME=umami
DB_USER=umami_user
DB_PASSWORD=your-database-password

1.3 Start the Service

Run the following command to start the Umami service:

uvicorn --reload src.analytics_service.app:app

💻 Usage Examples

2.1 Add New Prompts

Modify the list_prompts() function in src/analytics_service/server.py to add custom prompts.

Here is an example:

@app.list_prompts()
async def list_prompts():
    return [
        # Existing prompts...
        {
            "name": "Your Prompt Name",
            "description": "Your prompt description.",
            "arguments": [
                {
                    "name": "Parameter Name 1",
                    "description": "Parameter description.",
                    "required": True
                },
                {
                    "name": "Parameter Name 2",
                    "description": "Parameter description.",
                    "required": False
                }
            ]
        }
    ]

2.2 Implement Prompt Logic

Modify the get_prompt() function in src/analytics_service/server.py to handle new prompts.

Here is an example:

@app.get_prompt()
async def get_prompt(name: str, arguments: Any):
    if name == "Your Prompt Name":
        return {
            "messages": [
                {
                    "role": "user",
                    "content": {
                        "type": "text",
                        "text": f"Your prompt template, including {arguments['Parameter Name']}."
                    }
                }
            ]
        }

2.3 Explanation of Message Structure

• Role Field:

  • role: "user": Simulates user input or questions.
  • role: "assistant": Represents Claude's response or instructions.
  • role: "system": Sets the context or provides high - level instructions.

• Content Type:

  • "type": "text": Used for plain text content.
  • "type": "resource": Contains external resources, such as files, logs, etc. The uri, text, and mimeType attributes need to be specified.

📚 Documentation

3. Best Practices

• Clarity: Make prompts focused and specific.
• Parameter Naming: Use descriptive names and provide example values.
• Error Handling: Consider exceptional cases and boundary conditions.
• Testing and Validation: Test prompts with different inputs to ensure their effectiveness and reliability.

By following the above steps, you can customize the Umami service to meet specific analytical needs.