Trace · Google GenAI

Trace Google GenAI

LLM Providers

Auto-instrument Google GenAI with traceAI in under 3 minutes. Every LLM call, tool use, retrieval, and chain step becomes an OpenTelemetry span you can search, replay, and debug.

python typescript java · trace evaluate optimize simulate

Start free Open in docs View example on GitHub

Recipes for Google GenAI

Trace Google GenAI live Evaluate Google GenAI Optimize Google GenAI Simulate Google GenAI

Prerequisites

Before you start

· A working Google GenAI app — local or already in production.
· A free Future AGI account with FI_API_KEY and FI_SECRET_KEY.
· Python 3.9+ / Node 18+ / Java 17+ depending on which SDK you're installing.

Install

pip install traceAI-google-genai

npm install @traceai/google-genai

<dependency>
  <groupId>ai.futureagi</groupId>
  <artifactId>traceai-java-google-genai</artifactId>
  <version>LATEST</version>
</dependency>

Trace recipe

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType
from traceai_google_genai import GoogleGenAIInstrumentor

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

GoogleGenAIInstrumentor().instrument(tracer_provider=trace_provider)

# Your existing Google GenAI code runs unchanged from here.
# Every call is now an OpenTelemetry span in Future AGI.

import { register } from '@traceai/fi-core';
import { GoogleGenAIInstrumentation } from '@traceai/google-genai';

const tracerProvider = register({
  projectName: 'google_genai_app',
  projectType: 'observe',
});

new GoogleGenAIInstrumentation().instrument({ tracerProvider });

// Your existing Google GenAI code runs unchanged.
// Every call is now an OpenTelemetry span in Future AGI.

import ai.futureagi.fi.instrumentation.TraceProvider;
import ai.futureagi.traceai.google_genai.GoogleGenAIInstrumentor;

TraceProvider provider = TraceProvider.builder()
    .projectName("google_genai_app")
    .projectType("observe")
    .build();

new GoogleGenAIInstrumentor().instrument(provider);

// Your existing Google GenAI code runs unchanged.
// Every call is now an OpenTelemetry span in Future AGI.

What Future AGI captures

Trace fields you'll see in the dashboard

Spans for every Google GenAI call: input, output, latency, tokens, cost, model name, errors
Trace tree across LLM, tool, retrieval, embedding, and chain spans
Custom attributes via `using_attributes` (session_id, user_id, prompt_template, tags, custom dicts)
Streaming-safe — partial chunks aggregated into a single span

Common gotchas

Read these before you ship

01
Set `FI_API_KEY` and `FI_SECRET_KEY` in env before calling `register()` — silent fallback otherwise.
02
Async frameworks: instantiate the instrumentor *before* you create the client, not after.
03
Streaming responses are aggregated into a single span only when you use the official SDK iterator.

Next: chain it with the other recipes

Trace is the first step. Most teams add an evaluator the same week, and start optimising or simulating once they have a baseline. Each recipe takes minutes to wire up.

Start free Read the Trace docs

Adjacent integrations