Skip to main content

OpenTelemetry instrumentation for Bedrock

Project description

Bedrock OpenTelemetry Integration

Overview

This integration provides support for using OpenTelemetry with the Bedrock framework. It enables tracing and monitoring of applications built with Bedrock.

Installation

  1. Install traceAI Bedrock
pip install traceAI-bedrock
  1. Install boto3
pip install boto3

Set Environment Variables

Set up your environment variables to authenticate with FutureAGI.

import os

os.environ["AWS_ACCESS_KEY_ID"] = AWS_ACCESS_KEY_ID
os.environ["AWS_SECRET_ACCESS_KEY"] = AWS_SECRET_ACCESS_KEY
os.environ["FI_API_KEY"] = FI_API_KEY
os.environ["FI_SECRET_KEY"] = FI_SECRET_KEY

Quickstart

Register Tracer Provider

Set up the trace provider to establish the observability pipeline. The trace provider:

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="bedrock_app"
)

Configure Bedrock Instrumentation

Instrument the Bedrock client to enable telemetry collection. This step ensures that all interactions with the Bedrock SDK are tracked and monitored.

from traceai_bedrock import BedrockInstrumentor

BedrockInstrumentor().instrument(tracer_provider=trace_provider)

Create Bedrock Components

Set up your Bedrock client with built-in observability.

def converse_with_claude():
    system_prompt = [{"text": "You are an expert at creating music playlists"}]
    messages = [
        {
            "role": "user",
            "content": [{"text": "Hello, how are you?"}, {"text": "What's your name?"}],
        }
    ]
    inference_config = {"maxTokens": 1024, "temperature": 0.0}

    try:
        response = client.converse(
            modelId="model_id",
            system=system_prompt,
            messages=messages,
            inferenceConfig=inference_config,
        )
        out = response["output"]["message"]
        messages.append(out)
        print(out)
    except Exception as e:
        print(f"Error: {str(e)}")

if __name__ == "__main__":
    converse_with_claude()

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

traceai_bedrock-0.1.8.tar.gz (35.7 kB view details)

Uploaded Source

Built Distribution

traceai_bedrock-0.1.8-py3-none-any.whl (43.3 kB view details)

Uploaded Python 3

File details

Details for the file traceai_bedrock-0.1.8.tar.gz.

File metadata

  • Download URL: traceai_bedrock-0.1.8.tar.gz
  • Upload date:
  • Size: 35.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.0.0 CPython/3.13.0 Darwin/24.1.0

File hashes

Hashes for traceai_bedrock-0.1.8.tar.gz
Algorithm Hash digest
SHA256 9c1cc489839f614a12fefeb0a8e497d4198fa8690818c08eba8bd581b34bfcd0
MD5 6fe3a9012dd71b1f1506565798b5f388
BLAKE2b-256 8db0b81b7993418a56122c36382887bd20b3c19bda01fb9ef89f56a4c18fa9a5

See more details on using hashes here.

File details

Details for the file traceai_bedrock-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: traceai_bedrock-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 43.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.0.0 CPython/3.13.0 Darwin/24.1.0

File hashes

Hashes for traceai_bedrock-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 53ba1992b64954b53982af92fcbe1568d29565670bd2d52065178d1ce8dbdfe7
MD5 2e58764fa44271f0a3e756570de28a21
BLAKE2b-256 54f7048919e4e6a2b3180fc42f0bc7407204d7cb721aa89fac5c262c1b91b766

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page