​
1. Installation

Install the traceAI package to access the observability framework.

pip install traceAI-bedrock

​
2. Environment Configuration

Set up your environment variables to authenticate with both AWS and FutureAGI services. These credentials enable:

  • Secure access to AWS services
  • Authentication with FutureAGI’s observability platform
  • Encrypted telemetry data transmission

Click here here to learn how to configure eval tags for observability.

import os
os.environ["AWS_ACCESS_KEY_ID"] = "your-aws-access-key-id"
os.environ["AWS_SECRET_ACCESS_KEY"] = "your-aws-secret-access-key"
os.environ["FI_API_KEY"] = "your-futureagi-api-key"
os.environ["FI_SECRET_KEY"] = "your-futureagi-secret-key"

​
3. Configure Evaluation Tags

Define evaluation criteria for monitoring LLM responses. Evaluation tags allow you to:

  • Define custom evaluation criteria
  • Set up automated response quality checks
  • Track model performance metrics
from fi_instrumentation.fi_types import EvalName, EvalSpanKind, EvalTag, EvalTagType

eval_tags = [
    EvalTag(
        eval_name=EvalName.DETERMINISTIC_EVALS,
        value=EvalSpanKind.TOOL,
        type=EvalTagType.OBSERVATION_SPAN,
        config={
            "multi_choice": False,
            "choices": ["Yes", "No"],
            "rule_prompt": "Evaluate if the response is correct",
        },
        custom_eval_name="det_eval_bedrock_1"
    )
]

​
4. Initialize Trace Provider

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

  • Creates a new project in FutureAGI
  • Establishes telemetry data pipelines
  • Configures version tracking
  • Sets up evaluation frameworks
from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_type=ProjectType.EXPERIMENT,
    project_name="bedrock_app",
    project_version_name="v1",
    eval_tags=eval_tags
)

​
5. Configure Bedrock Instrumentation

Initialize the Bedrock instrumentor to enable automatic tracing.

from traceai_bedrock import BedrockInstrumentor

BedrockInstrumentor().instrument(tracer_provider=trace_provider)

​
6. Install Required Dependencies

Install the necessary AWS SDK components required for your project.

pip install boto3

​
7. Create Bedrock Components

Set up your Bedrock client with built-in observability.

import boto3

client = boto3.client(
    service_name="bedrock",
    region_name="your-region",
    aws_access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
    aws_secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"],
)

​
8. Execute

Run your Bedrock application.

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()