Google Gen AI Tracing

Install#

pip install openinference-instrumentation-google-genai google-genai

Setup#

Set the GEMINI_API_KEY environment variable. To use the Gen AI SDK with Vertex AI instead of the Developer API, refer to Google’s guide on setting the required environment variables.

export GEMINI_API_KEY=[your_key_here]

Connect your application to Phoenix with the register function:

from phoenix.otel import register# configure the Phoenix tracertracer_provider = register(project_name="my-llm-app", # Default is 'default'auto_instrument=True # Auto-instrument your app based on installed OI dependencies)

Observe#

Now that you have tracing setup, all Gen AI SDK requests will be streamed to Phoenix for observability and evaluation.

import osfrom google import genaidef send_message_multi_turn() -> tuple[str, str]:    client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])    chat = client.chats.create(model="gemini-2.0-flash-001")    response1 = chat.send_message("What is the capital of France?")    response2 = chat.send_message("Why is the sky blue?")    return response1.text or "", response2.text or ""

Info

This instrumentation will support tool calling soon. Refer to this page for the status.