AgentOps provides seamless integration with Google’s Generative AI API, allowing you to monitor and analyze all your Gemini model interactions automatically.

​
Installation

pip install agentops google-genai

​
Usage

Initialize AgentOps at the beginning of your application to automatically track all Gemini API calls:

import agentops
from google import genai

# Initialize AgentOps
agentops.init(<INSERT YOUR API KEY HERE>)

# Create a client for Gemini Developer API
client = genai.Client(api_key="YOUR_GEMINI_API_KEY")

# Generate content with a model
response = client.models.generate_content(
    model='gemini-2.0-flash-001',
    contents='What is AI observability?'
)

print(response.text)

# All Gemini API calls are automatically tracked by AgentOps

​
Alternative Client Setup

You can also set up the client using Vertex AI or with environment variables:

import agentops
from google import genai

# Initialize AgentOps
agentops.init(<INSERT YOUR API KEY HERE>)

# Using Vertex AI
client = genai.Client(
    vertexai=True,
    project='your-project-id',
    location='us-central1'
)

# Generate content
response = client.models.generate_content(
    model='gemini-2.0-flash-001',
    contents='What is AI observability?'
)

print(response.text)

​
System Instructions and Settings

You can customize the model behavior with system instructions and other settings:

import agentops
from google import genai
from google.genai import types

# Initialize AgentOps
agentops.init(<INSERT YOUR API KEY HERE>)

# Create a client
client = genai.Client(api_key="YOUR_GEMINI_API_KEY")

# Generate content with system instructions
response = client.models.generate_content(
    model='gemini-2.0-flash-001',
    contents='Write a short poem',
    config=types.GenerateContentConfig(
        system_instruction='You are a professional poet who specializes in sonnets',
        max_output_tokens=200,
        temperature=0.7,
    ),
)

print(response.text)

​
Streaming Example

AgentOps also supports tracking streaming requests with Gemini:

import agentops
from google import genai

# Initialize AgentOps
agentops.init(<INSERT YOUR API KEY HERE>)

# Create a client
client = genai.Client(api_key="YOUR_GEMINI_API_KEY")

# Generate streaming content
for chunk in client.models.generate_content_stream(
    model='gemini-2.0-flash-001',
    contents='Explain quantum computing in simple terms.',
):
    print(chunk.text, end="", flush=True)

# All streaming requests are automatically tracked by AgentOps

​
Chat Example

import agentops
from google import genai

# Initialize AgentOps
agentops.init(<INSERT YOUR API KEY HERE>)

# Create a client
client = genai.Client(api_key="YOUR_GEMINI_API_KEY")

# Start a chat session
chat = client.chats.create(model='gemini-2.0-flash-001')

# Send messages and get responses
response = chat.send_message('Hello, how can you help me with AI development?')
print(response.text)

# Continue the conversation
response = chat.send_message('What are the best practices for prompt engineering?')
print(response.text)

# All chat interactions are automatically tracked by AgentOps

​
Environment Variables

Set your API key as an .env variable for easy access.

AGENTOPS_API_KEY=<YOUR API KEY>
GOOGLE_API_KEY=<YOUR GEMINI API KEY>

# For Vertex AI
# GOOGLE_GENAI_USE_VERTEXAI=true
# GOOGLE_CLOUD_PROJECT=your-project-id
# GOOGLE_CLOUD_LOCATION=us-central1

Read more about environment variables in Advanced Configuration

​
Additional Resources

For more information on using the Google Gen AI SDK, refer to the official documentation.