AWS Bedrock (tracing)

Amazon Bedrock is a fully managed service that offers foundation models from leading AI providers through a single API. Respan gives you full observability over Bedrock invocations, streamed responses, and tool calls, plus separate gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key .

Paste this into your coding agent:


Help me set up Respan tracing with the AWS Bedrock integration.
Follow https://www.respan.ai/docs/integrations/aws-bedrock.md

Setup

Install packages

Terminal


pip install respan-ai respan-instrumentation-aws-bedrock boto3

Set environment variables

Terminal


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 for direct Bedrock requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

Python


import json
import boto3
from respan import Respan
from respan_instrumentation_aws_bedrock import AWSBedrockInstrumentor

respan = Respan(instrumentations=[AWSBedrockInstrumentor()])

client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.invoke_model(
    modelId="anthropic.claude-3-sonnet-20240229-v1:0",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 1024,
        "messages": [{"role": "user", "content": "Say hello in three languages."}],
    }),
    contentType="application/json",
)
result = json.loads(response["body"].read())
print(result["content"][0]["text"])

View your trace

Open the Traces page to see your auto-instrumented LLM spans.

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, such as `AWSBedrockInstrumentor()` or `new AWSBedrockInstrumentor()`.
`sdkModule`	`object \| undefined`	`undefined`	TypeScript only. Optional AWS SDK module instance for runtimes that resolve multiple copies.
`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, such as `"production"`.

Supported calls

SDK call	Traced
`InvokeModel`	Model invocation spans
`InvokeModelWithResponseStream`	Streaming invocation spans after the stream is consumed
`Converse`	Chat spans with messages, output, usage, and tool definitions
`ConverseStream`	Streaming chat spans after the stream is consumed

Attributes

In Respan()

Set defaults at initialization. These apply to all spans.

Python


from respan import Respan
from respan_instrumentation_aws_bedrock import AWSBedrockInstrumentor

respan = Respan(
    instrumentations=[AWSBedrockInstrumentor()],
    customer_identifier="user_123",
    metadata={"service": "chat-api", "version": "1.0.0"},
)

With propagate_attributes

Override per-request using a context scope.

Python


import json
from respan import Respan, propagate_attributes
from respan_instrumentation_aws_bedrock import AWSBedrockInstrumentor

respan = Respan(instrumentations=[AWSBedrockInstrumentor()])

def handle_request(user_id: str, question: str):
    with propagate_attributes(
        customer_identifier=user_id,
        thread_identifier="conv_abc_123",
        metadata={"plan": "pro"},
    ):
        response = client.invoke_model(
            modelId="anthropic.claude-3-sonnet-20240229-v1:0",
            body=json.dumps({
                "anthropic_version": "bedrock-2023-05-31",
                "max_tokens": 1024,
                "messages": [{"role": "user", "content": question}],
            }),
            contentType="application/json",
        )
        result = json.loads(response["body"].read())
        print(result["content"][0]["text"])

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.