LLM Tracekit - LiteLLM

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

Installation

pip install "llm-tracekit-litellm"

Usage

This section describes how to set up instrumentation for LiteLLM.

Setting up tracing

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

from llm_tracekit.litellm 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.litellm import LiteLLMInstrumentor

LiteLLMInstrumentor().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:

LiteLLMInstrumentor().uninstrument()

Full Example

import litellm
from llm_tracekit.litellm import LiteLLMInstrumentor, 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
LiteLLMInstrumentor().instrument()

# Example LiteLLM Usage
response = litellm.completion(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Write a short poem on open telemetry."}],
    user="user@company.com",
)

Semantic Conventions