Skip to main content
In this cookbook, you’ll learn how to easily integrate Maxim’s powerful tracing into your GenAI app powered by Google Gemini. We’ll walk through a simple example that shows how to set up the integration, trace requests, and log tool calls.

​
Prerequisites

​
1. Load Environment Variables

First, load your API keys from a .env file or your environment. 
import dotenv
dotenv.load_dotenv()

​
2. Initialize Maxim and Gemini Clients

Set up the Maxim logger and wrap the Gemini client for tracing. 
from maxim import Maxim
from maxim.logger.gemini import MaximGeminiClient

logger = Maxim().logger()

​
3. Create the Gemini Client with Maxim Tracing

import os
from google import genai

client = MaximGeminiClient(
    client=genai.Client(api_key=os.getenv("GEMINI_API_KEY")),
    logger=logger
)

​
4. (Optional) Define a Tool Function

You can trace tool calls (function calls) as part of your workflow. For example, a weather function: 
def get_current_weather(location: str) -> str:
    """Get the current weather in a given location."""
    print(f"Called with: {location=}")
    return "23C"

​
5. Generate Content with Tracing

Now, make a request to Gemini and trace it with Maxim. You can also pass tool functions for tool-calling scenarios. 
response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents="What's the temp in SF?",
    config={
        "tools": [get_current_weather],
        "system_instruction": "You are a helpful assistant",
        "temperature": 0.8,
    },
)

​
6. View Traces in Maxim

All requests, responses, and tool calls are now automatically traced and can be viewed in your Maxim dashboard.

​
Full Example

import dotenv
import os
from maxim import Maxim
from maxim.logger.gemini import MaximGeminiClient
from google import genai

dotenv.load_dotenv()

logger = Maxim().logger()
client = MaximGeminiClient(
    client=genai.Client(api_key=os.getenv("GEMINI_API_KEY")),
    logger=logger
)

def get_current_weather(location: str) -> str:
    print(f"Called with: {location=}")
    return "23C"

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents="What's the temp in SF?",
    config={
        "tools": [get_current_weather],
        "system_instruction": "You are a helpful assistant",
        "temperature": 0.8,
    },
)
print(response)
Gif
For more details, see the Maxim Python SDK documentation.

​
Resources

Cookbook Code

Python Notebook for Gemini & Maxim
⌘I