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 every Bedrock invocation, streamed response, and tool call — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

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

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

Use Respan Gateway

See Amazon Bedrock gateway setup to route this integration through the Respan gateway.

Example projects

Example projects root

Setup

Install packages

$ pip install respan-ai respan-instrumentation-aws-bedrock 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 for Bedrock requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import json
2 import boto3
3 from respan import Respan
4 from respan_instrumentation_aws_bedrock import AWSBedrockInstrumentor
5 
6 respan = Respan(instrumentations=[AWSBedrockInstrumentor()])
7 
8 client = boto3.client("bedrock-runtime", region_name="us-east-1")
9 
10 response = client.invoke_model(
11     modelId="anthropic.claude-3-sonnet-20240229-v1:0",
12     body=json.dumps({
13         "anthropic_version": "bedrock-2023-05-31",
14         "max_tokens": 1024,
15         "messages": [{"role": "user", "content": "Say hello in three languages."}],
16     }),
17     contentType="application/json",
18 )
19 result = json.loads(response["body"].read())
20 print(result["content"][0]["text"])
21 respan.flush()

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 (e.g. `AWSBedrockInstrumentor()`).
`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()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from respan_instrumentation_aws_bedrock import AWSBedrockInstrumentor
3 
4 respan = Respan(
5     instrumentations=[AWSBedrockInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "chat-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 import json
2 from respan import Respan, propagate_attributes
3 from respan_instrumentation_aws_bedrock import AWSBedrockInstrumentor
4 
5 respan = Respan(instrumentations=[AWSBedrockInstrumentor()])
6 
7 def handle_request(user_id: str, question: 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_model(
14             modelId="anthropic.claude-3-sonnet-20240229-v1:0",
15             body=json.dumps({
16                 "anthropic_version": "bedrock-2023-05-31",
17                 "max_tokens": 1024,
18                 "messages": [{"role": "user", "content": question}],
19             }),
20             contentType="application/json",
21         )
22         result = json.loads(response["body"].read())
23         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.