OpenAI

Coralogix's AI Observability integrations enable organizations to gain deep insight into their AI applications, helping them monitor, analyze, and optimize performance across the stack. Through integrations with OpenAI, Coralogix delivers end-to-end visibility into AI workloads, supporting proactive issue detection and efficient performance tuning.

Overview

This library offers customized OpenTelemetry instrumentation for OpenAI SDK, optimized to support large language model (LLM) application development with streamlined integration, detailed production tracing, and effective debugging capabilities.

Requirements

• Python version 3.8 and above.
• Coralogix API keys.

Installation

Run the following command.

pip install llm-tracekit[openai]

Authentication

Authentication data is passed during OTel Span Exporter definition:

1. Select the endpoint associated with your Coralogix domain .
2. Use your customized API key in the authorization request header.
3. Provide the application and subsystem names.

from llm_tracekit import setup_export_to_coralogix

setup_export_to_coralogix(
    coralogix_token=<your_coralogix_token>,
    coralogix_endpoint=<your_coralogix_endpoint>,
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

Usage

This section describes how to set up instrumentation for OpenAI.

Set up tracing

Automatic

Use the setup_export_to_coralogix function to set up tracing and export traces to Coralogix. See the code snippet in the Authentication section.

Manual

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)

Instrument

To instrument all clients, call the instrument method.

from llm_tracekit import OpenAIInstrumentor

OpenAIInstrumentor().instrument()

Uninstrument

To uninstrument clients, call the uninstrument method.

OpenAIInstrumentor().uninstrument() 

Full example

from llm_tracekit import OpenAIInstrumentor, setup_export_to_coralogix
from openai import OpenAI

# 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
OpenAIInstrumentor().instrument()

# OpenAI Usage Example
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Write a short poem on open telemetry."},
    ],
)

Enable message content capture

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

• 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 require message contents to function properly, so enabling message capture is strongly recommended.

Key differences from OpenTelemetry

• The user parameter in the OpenAI Chat Completions API is captured in the span as the gen_ai.openai.request.user attribute.
• The tools parameter in the OpenAI Chat Completions API is now captured in the span as the gen_ai.openai.request.tools attribute.
• User prompts and model responses are captured as span attributes instead of log events, as detailed below.

Semantic conventions

OpenAI-specific attributes

Previous Introduction

Next Amazon Bedrock

Theme

Light

light

dark

Home

User Guides

DataPrime

Integrations

OpenTelemetry

Developer Portal