Amazon SageMaker | Respan Docs

Amazon SageMaker is AWS’s fully managed machine learning platform. It provides tools for building, training, and deploying ML models at scale, including real-time inference endpoints for LLMs and other models. Respan gives you full observability over every endpoint invocation, payload, and response — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai opentelemetry-instrumentation-sagemaker boto3

Set environment variables

$ export AWS_ACCESS_KEY_ID="YOUR_AWS_ACCESS_KEY_ID"
$ export AWS_SECRET_ACCESS_KEY="YOUR_AWS_SECRET_ACCESS_KEY"
$ export AWS_REGION="us-east-1"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

AWS credentials are used to invoke SageMaker endpoints. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import os
2 import json
3 import boto3
4 from respan import Respan
5 from opentelemetry.instrumentation.sagemaker import SageMakerInstrumentor
6 
7 respan = Respan(instrumentations=[SageMakerInstrumentor()])
8 
9 client = boto3.client("sagemaker-runtime", region_name=os.environ["AWS_REGION"])
10 
11 payload = json.dumps({"inputs": "Say hello in three languages."})
12 
13 response = client.invoke_endpoint(
14     EndpointName="my-llm-endpoint",
15     ContentType="application/json",
16     Body=payload,
17 )
18 result = json.loads(response["Body"].read().decode())
19 print(result)
20 respan.flush()

View your trace

Open the Traces page to see your auto-instrumented endpoint invocation spans with payloads, latency, and tokens.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `SageMakerInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

1 from respan import Respan
2 from opentelemetry.instrumentation.sagemaker import SageMakerInstrumentor
3 
4 respan = Respan(
5     instrumentations=[SageMakerInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "sagemaker-api", "version": "1.0.0"},
8 )

With propagate_attributes

1 import json
2 from respan import Respan, propagate_attributes
3 from opentelemetry.instrumentation.sagemaker import SageMakerInstrumentor
4 
5 respan = Respan(instrumentations=[SageMakerInstrumentor()])
6 
7 def handle_request(user_id: str, prompt: str):
8     with propagate_attributes(
9         customer_identifier=user_id,
10         thread_identifier="conv_abc_123",
11         metadata={"plan": "pro"},
12     ):
13         response = client.invoke_endpoint(
14             EndpointName="my-llm-endpoint",
15             ContentType="application/json",
16             Body=json.dumps({"inputs": prompt}),
17         )
18         print(json.loads(response["Body"].read().decode()))

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.