LLM Tracekit - Gemini

OpenTelemetry instrumentation for Google Gemini, designed to simplify LLM application development and production tracing and debugging.

Supported Operations

• Text Generation: client.models.generate_content() and generate_content_stream() (sync and async)
• Embeddings: client.models.embed_content() (sync and async)

Installation

pip install "llm-tracekit-gemini"

Usage

This section describes how to set up instrumentation for Google Gemini.

Setting up tracing

You can use the setup_export_to_coralogix function to setup tracing and export traces to Coralogix

from llm_tracekit.gemini import setup_export_to_coralogix

setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

Alternatively, you can set up tracing manually:

from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import SERVICE_NAME, Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

tracer_provider = TracerProvider(
    resource=Resource.create({SERVICE_NAME: "ai-service"}),
)
exporter = OTLPSpanExporter()
span_processor = SimpleSpanProcessor(exporter)
tracer_provider.add_span_processor(span_processor)
trace.set_tracer_provider(tracer_provider)

Activation

To instrument all clients, call the instrument method

from llm_tracekit.gemini import GeminiInstrumentor

GeminiInstrumentor().instrument()

Enabling message content

Message content such as the contents of the prompt, completion, function arguments and return values are not captured by default. To capture message content as span attributes, do one of the following:

• Pass capture_content=True when calling setup_export_to_coralogix
• Set the environment variable OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT to true

Most Coralogix AI evaluations will not work without message contents, so it is highly recommended to enable capturing.

Uninstrument

To uninstrument clients, call the uninstrument method:

GeminiInstrumentor().uninstrument()

Full Example - Text Generation

from google import genai
from llm_tracekit.gemini import GeminiInstrumentor, setup_export_to_coralogix

# Optional: Configure sending spans to Coralogix
# Reads Coralogix connection details from the following environment variables:
# - CX_TOKEN
# - CX_ENDPOINT
setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

# Activate instrumentation
GeminiInstrumentor().instrument()

# Example Gemini Usage
client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=[{"role": "user", "parts": [{"text": "Write a short poem on open telemetry."}]}],
)

Full Example - Embeddings

from google import genai
from google.genai import types
from llm_tracekit.gemini import GeminiInstrumentor, setup_export_to_coralogix

setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

GeminiInstrumentor().instrument()

client = genai.Client()

# Single content embedding
response = client.models.embed_content(
    model="gemini-embedding-001",
    contents="What is machine learning?",
)
print(f"Embedding dimensions: {len(response.embeddings[0].values)}")

# Batch embedding
response = client.models.embed_content(
    model="gemini-embedding-001",
    contents=["First text", "Second text", "Third text"],
)
print(f"Number of embeddings: {len(response.embeddings)}")

# With dimensionality reduction
response = client.models.embed_content(
    model="gemini-embedding-001",
    contents="What is quantum computing?",
    config=types.EmbedContentConfig(output_dimensionality=256),
)
print(f"Reduced dimensions: {len(response.embeddings[0].values)}")

Semantic Conventions

Text Generation Attributes

Embeddings Attributes