Google GenAI Integration with Future AGI for Gemini Tracing

Set up Google GenAI with Future AGI tracing. Install traceAI-google-genai to capture and monitor Gemini model interactions automatically.

Trace Google GenAI model calls in Future AGI using the Google GenAI instrumentor.

1. Installation

Install the traceAI and Google GenAI packages.

pip install traceAI-google-genai google-genai

2. Set Environment Variables

Set up your environment variables to authenticate with FutureAGI.

import os

os.environ["FI_API_KEY"] = "your-futureagi-api-key"
os.environ["FI_SECRET_KEY"] = "your-futureagi-secret-key"

The instrumentor captures request and response content by default, including prompts and generated text. To hide input, output and request parameters in traces, set these before initializing instrumentation:

export FI_HIDE_INPUTS=true
export FI_HIDE_OUTPUTS=true
export FI_HIDE_LLM_INVOCATION_PARAMETERS=true

See trace masking settings for additional controls. Do not treat input/output masking as a general-purpose scrubber for error text, user IDs, metadata or custom spans.

3. Initialize Trace Provider

Register the google_genai Observe project.

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="google_genai",
)

4. Instrument your Project

Instrument your project to enable automatic tracing.

from traceai_google_genai import GoogleGenAIInstrumentor

GoogleGenAIInstrumentor().instrument(tracer_provider=trace_provider)

5. Make a Google GenAI request

After initializing the instrumentor, use a Google GenAI client to make a request through Vertex AI. Set project to your Google Cloud project and configure Application Default Credentials.

from google import genai
from google.genai import types

client = genai.Client(vertexai=True, project="your_project_name", location="global")

content = types.Content(
    role="user",
    parts=[
        types.Part.from_text(text="Hello how are you?"),
    ],
)
response = client.models.generate_content(
    model="gemini-3.5-flash-lite", contents=content
)

print(response)
trace_provider.force_flush()  # Export buffered spans before this script exits.

6. View the trace

In Future AGI, open Observe, select the google_genai project, and open the trace.

Was this page helpful?

Questions & Discussion