Skip to main content
boto3 provides Python bindings to AWS services, including Bedrock, which provides access to a number of foundation models. Calls to these models can be instrumented using OpenInference, enabling OpenTelemetry-compliant observability of applications built using these models. Traces collected using OpenInference can be viewed in Phoenix. OpenInference Traces collect telemetry data about the execution of your LLM application. Consider using this instrumentation to understand how a Bedrock-managed models are being called inside a complex system and to troubleshoot issues such as extraction and response synthesis.

​
Launch Phoenix

  • Phoenix Cloud
  • Command Line
  • Docker
  • Notebook
Sign up for Phoenix:
  1. Sign up for an Arize Phoenix account at https://app.phoenix.arize.com/login
  2. Click Create Space, then follow the prompts to create and launch your space.
Install packages:
pip install arize-phoenix-otel
Set your Phoenix endpoint and API Key:From your new Phoenix Space
  1. Create your API key from the Settings page
  2. Copy your Hostname from the Settings page
  3. In your code, set your endpoint and API key: 
import os

os.environ["PHOENIX_API_KEY"] = "ADD YOUR PHOENIX API KEY"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "ADD YOUR PHOENIX HOSTNAME"

# If you created your Phoenix Cloud instance before June 24th, 2025,
# you also need to set the API key as a header:
# os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={os.getenv('PHOENIX_API_KEY')}"
Having trouble finding your endpoint? Check out Finding your Phoenix Endpoint

​
Install

pip install openinference-instrumentation-bedrock opentelemetry-exporter-otlp

​
Setup

Connect to your Phoenix instance using the register function. 
from phoenix.otel import register

# configure the Phoenix tracer
tracer_provider = register(
  project_name="my-llm-app", # Default is 'default'
  auto_instrument=True # Auto-instrument your app based on installed OI dependencies
)
After connecting to your Phoenix server, instrument boto3 prior to initializing a bedrock-runtime client. All clients created after instrumentation will send traces on all calls to invoke_model. 
import boto3

session = boto3.session.Session()
client = session.client("bedrock-runtime")

​
Run Bedrock

From here you can run Bedrock as normal 
prompt = (
    b'{"prompt": "Human: Hello there, how are you? Assistant:", "max_tokens_to_sample": 1024}'
)
response = client.invoke_model(modelId="anthropic.claude-v2", body=prompt)
response_body = json.loads(response.get("body").read())
print(response_body["completion"])
Warning: Use converse instead of invoke_model for Meta models on Amazon Bedrock.Outputs from Meta models (such as Llama 3) are not currently traced when using the invoke_model API.This issue is known, and a fix is actively in progress.

​
Observe

Now that you have tracing setup, all calls to invoke_model will be streamed to your running Phoenix for observability and evaluation.
Bedrock Tracing Evaluation

​
Resources