ContextQMD
Back to Opik

Using Opik with Gemini

apps/opik-documentation/documentation/docs/cookbook/gemini.ipynb

2.0.22-6605-merge-20652.8 KB
Original Source

Using Opik with Gemini

Opik integrates with Gemini to provide a simple way to log traces for all Gemini LLM calls. This works for all Gemini models.

Creating an account on Comet.com

Comet provides a hosted version of the Opik platform, simply create an account and grab your API Key.

You can also run the Opik platform locally, see the installation guide for more information.

python
%pip install --upgrade opik google-genai litellm
python
import opik

opik.configure(use_local=False)

Preparing our environment

First, we will set up our GOOGLE_API_KEY keys.

python
import os
import getpass

if "GOOGLE_API_KEY" not in os.environ:
    os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter your Gemini API key: ")

Logging traces

Now each completion will logs a separate trace to LiteLLM:

python
from google import genai
from opik import track
from opik.integrations.genai import track_genai

os.environ["OPIK_PROJECT_NAME"] = "gemini-integration-demo"

client = genai.Client()
gemini_client = track_genai(client)

prompt = """
Write a short two sentence story about Opik.
"""

response = gemini_client.models.generate_content(
    model="gemini-2.0-flash-001", contents=prompt
)
print(response.text)

The prompt and response messages are automatically logged to Opik and can be viewed in the UI.

Using it with the track decorator

If you have multiple steps in your LLM pipeline, you can use the track decorator to log the traces for each step. If Gemini is called within one of these steps, the LLM call with be associated with that corresponding step:

python
@track
def generate_story(prompt):
    response = gemini_client.models.generate_content(
        model="gemini-2.0-flash-001", contents=prompt
    )
    return response.text


@track
def generate_topic():
    prompt = "Generate a topic for a story about Opik."
    response = gemini_client.models.generate_content(
        model="gemini-2.0-flash-001", contents=prompt
    )
    return response.text


@track
def generate_opik_story():
    topic = generate_topic()
    story = generate_story(topic)
    return story


generate_opik_story()

The trace can now be viewed in the UI: