Microsoft Foundry

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 the Azure AI Projects Python SDK (Microsoft Foundry), 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 the Azure AI Projects Python SDK (Microsoft Foundry), optimized to support large language model (LLM) application development with streamlined integration, detailed production tracing, and effective debugging capabilities.

Requirements

• Python 3.10–3.13.
• Coralogix API keys.

Installation

Run the following command.

pip install "llm-tracekit-microsoft-foundry"

Authentication

Authentication data is passed during OTel Span Exporter definition:

1. Choose the ingress.:443 endpoint that corresponds to your Coralogix domain using the domain selector at the top of the page.
2. Use your customized API key in the authorization request header.
3. Provide the application and subsystem names.

from llm_tracekit.microsoft_foundry import setup_export_to_coralogix

setup_export_to_coralogix(
    coralogix_token=<your_coralogix_token>,
    coralogix_endpoint="ingress.:443",
    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 the Microsoft Foundry SDK.

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.microsoft_foundry import MicrosoftFoundryInstrumentor

MicrosoftFoundryInstrumentor().instrument()

Uninstrument

To uninstrument clients, call the uninstrument method.

MicrosoftFoundryInstrumentor().uninstrument()

Full example

import os
from azure.ai.projects import AIProjectClient
from azure.identity import DefaultAzureCredential
from llm_tracekit.microsoft_foundry import MicrosoftFoundryInstrumentor, 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
MicrosoftFoundryInstrumentor().instrument()

# Microsoft Foundry usage example
with AIProjectClient(
    endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
    credential=DefaultAzureCredential(),
) as project_client:
    with project_client.get_openai_client() as openai_client:
        # Using Responses API
        response = openai_client.responses.create(
            model="gpt-4o-mini",
            input="Write a short poem on open telemetry.",
        )
        print(response.output_text)

        # Using Chat Completions API
        response = openai_client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[
                {"role": "user", "content": "Hello, world!"},
            ],
        )
        print(response.choices[0].message.content)

Enable message content capture

By default, message content — prompt contents, completions, function arguments, and return values — is 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.

Semantic conventions

Microsoft Foundry-specific attributes

In addition to standard GenAI semantic conventions, this instrumentation captures Foundry-specific context.

Attribute	Type	Description	Example
gen_ai.microsoft_foundry.agent.name	string	Agent name from extra_body.agent_reference	MyAgent
gen_ai.microsoft_foundry.agent.version	string	Agent version if specified	v1
gen_ai.microsoft_foundry.conversation_id	string	Conversation ID if using conversations	conv_123

Standard GenAI attributes

Next steps

Once your integration is set up, explore the AI Center Overview to monitor performance, costs, quality issues, and security across all your AI applications — and to set up Guardrails for real-time policy enforcement.