Registry /
aws / opentelemetry-instrumentation-sagemaker
Install & Compatibility
Where this runs
tested against v0.62.3 · pip install
no network on importno background threads
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
muslpy 3.10–3.95 runs
installs and imports cleanly · install 0.0s · import 0.000s · 52.1MB
glibcpy 3.10–3.95 runs
installs and imports cleanly · install 5.4s · import 0.000s · 51MB
50MB installed
● package 50MB
Code
Verified usage
Verified import paths — ran on the pinned version, not inferred.
SageMakerInstrumentor
✓ from opentelemetry.instrumentation.sagemaker import SageMakerInstrumentor
TracerProvider
✓ from opentelemetry.sdk.trace import TracerProvider
✗ from opentelemetry.trace import TracerProvider
The SDK TracerProvider is used for configuration, while `opentelemetry.trace` provides the API interfaces.
This quickstart demonstrates how to enable OpenTelemetry SageMaker instrumentation and manually configure the SDK to export traces to the console. It uses a mocked boto3 client to simulate an `invoke_endpoint` call without requiring actual AWS credentials, allowing you to see the generated spans. The `TRACELOOP_TRACE_CONTENT` environment variable is set to 'false' to prevent logging of sensitive request/response data.
import os
from unittest.mock import MagicMock
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor
from opentelemetry.instrumentation.sagemaker import SageMakerInstrumentor
# Set up OpenTelemetry SDK for console output
provider = TracerProvider()
processor = SimpleSpanProcessor(ConsoleSpanExporter())
provider.add_span_processor(processor)
trace.set_tracer_provider(provider)
# Instrument SageMaker (Boto3 calls)
SageMakerInstrumentor().instrument()
# Disable logging of request/response bodies for privacy (optional but recommended)
os.environ['TRACELOOP_TRACE_CONTENT'] = 'false'
# Mock boto3 client to avoid actual AWS calls
mock_client = MagicMock()
mock_client.invoke_endpoint.return_value = {
'Body': MagicMock(read=lambda: b'{"predictions": [0.9]}'),
'ContentType': 'application/json',
'InvokedProductionVariant': 'variant-1'
}
# Use the instrumented client (even if mocked, instrumentation hooks will be called)
print('Invoking SageMaker endpoint (mocked)...')
response = mock_client.invoke_endpoint(
EndpointName='my-ml-endpoint',
ContentType='application/json',
Body=b'{"instances": [[1,2,3]]}'
)
print(f"Mocked response: {response['Body'].read().decode()}")
print("Check console for OpenTelemetry trace output.")
# To uninstrument (optional)
# SageMakerInstrumentor().uninstrument()
Debug
Known issues
gotchaBy default, the instrumentation logs SageMaker endpoint request bodies and responses as span attributes. This may expose sensitive data. It can also increase trace size significantly.fixSet the environment variable `TRACELOOP_TRACE_CONTENT=false` to disable logging of request and response content. This is highly recommended for production environments dealing with sensitive information.
affects: All versions
breakingThe `opentelemetry-instrumentation-sagemaker` library, along with other OpenTelemetry GenAI instrumentations, is actively adopting the evolving OpenTelemetry Generative AI Semantic Conventions. This may lead to changes in span names, attribute keys, and overall trace structure between minor versions, especially when new experimental conventions are introduced.fixReview the release notes for your specific version and related OpenTelemetry GenAI projects. If you rely on specific attribute names or trace structures, you may need to update your data processing logic. The `OTEL_SEMCONV_STABILITY_OPT_IN` environment variable (e.g., `OTEL_SEMCONV_STABILITY_OPT_IN=gen_ai_latest_experimental`) can be used to explicitly opt into the latest experimental conventions or maintain older ones, but careful testing is advised during upgrades.
affects: 0.53.0 and newer (especially impacting versions adopting 'GenAI semantic conventions' changes)
gotchaThis instrumentation specifically targets SageMaker calls made through the Boto3 client. If you require broader instrumentation for other AWS services or general Boto3 operations, you might also need to install and instrument `opentelemetry-instrumentation-boto3` or `opentelemetry-instrumentation-botocore` separately.fixIdentify all AWS services you interact with. Install `opentelemetry-instrumentation-boto3` or `opentelemetry-instrumentation-botocore` if you need general AWS SDK tracing beyond SageMaker. Enable each instrumentor explicitly via `MyInstrumentor().instrument()`.
affects: All versions
gotchaFor traces to be collected and exported, you must have a configured OpenTelemetry `TracerProvider` and a `SpanProcessor` with an appropriate `SpanExporter` (e.g., OTLP, Console). Merely installing the instrumentation package and calling `instrument()` will not result in visible traces without the core SDK setup.fixAlways ensure your application includes the setup for `opentelemetry.sdk.trace.TracerProvider`, adds a `SpanProcessor`, and configures an `SpanExporter` that sends data to your observability backend (e.g., OTLP exporter to a collector, or console exporter for local debugging).
affects: All versions
Upgrade
Version history
0.62.3latest on PyPI · released Aug 10, 2026
Audit
Dependencies
opentelemetry-apirequiredCore OpenTelemetry API, essential for any instrumentation.
opentelemetry-sdkrequiredCore OpenTelemetry SDK, required for trace and metric providers.
boto3optionalThe underlying AWS SDK for Python that this instrumentation targets for SageMaker interactions.