Skip to main content
The OpenInference Bedrock instrumentor traces Amazon Bedrock calls made with boto3 — both the converse and invoke_model APIs on the bedrock-runtime client — as OTLP spans. Point the exporter at AgentMark and the traces arrive normalized.

​
Setup

1

Install the instrumentor and the OTLP exporter

pip install openinference-instrumentation-bedrock boto3 \
  opentelemetry-sdk opentelemetry-exporter-otlp-proto-http
2

Point the exporter at AgentMark and instrument Bedrock

Use your AgentMark API key and app id from project settings.
from openinference.instrumentation.bedrock import BedrockInstrumentor
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

provider = TracerProvider()
provider.add_span_processor(
    BatchSpanProcessor(
        OTLPSpanExporter(
            endpoint="https://api.agentmark.co/v1/traces",
            headers={
                "Authorization": "<YOUR_API_KEY>",  # raw key, no "Bearer" prefix
                "X-Agentmark-App-Id": "<YOUR_APP_ID>",
            },
        )
    )
)

BedrockInstrumentor().instrument(tracer_provider=provider)
3

Run your calls

Use a bedrock-runtime client as usual — client.converse(...) or client.invoke_model(...). Each call arrives in AgentMark as a span, grouped into a trace. See Traces and logs.
import boto3

client = boto3.client("bedrock-runtime", region_name="us-east-1")
client.converse(
    modelId="anthropic.claude-3-5-sonnet-20240620-v1:0",
    messages=[{"role": "user", "content": [{"text": "What is the capital of France?"}]}],
)

​
What AgentMark captures

Bedrock spans use the OpenInference attribute conventions — model, token usage, input and output messages, tool calls, settings, and span kind are all mapped onto AgentMark’s normalized trace fields, and token counts feed cost tracking. See OpenInference for the full attribute mapping.

​
Next steps

OpenInference

How AgentMark reads OpenInference attributes

Traces and logs

Explore traces once they arrive

​
Have questions?

Reach out any time: