Tracing Amazon Bedrock AgentCore

Integration via OpenTelemetry

Amazon Bedrock AgentCore can be integrated with MLflow via OpenTelemetry. Configure Amazon Bedrock AgentCore's OpenTelemetry exporter to send traces to MLflow's OTLP endpoint.

info

OpenTelemetry trace ingestion is supported in MLflow 3.6.0 and above.

OpenTelemetry endpoint (OTLP)

MLflow Server exposes an OTLP endpoint at /v1/traces (OTLP). This endpoint accepts traces from any native OpenTelemetry instrumentation, allowing you to trace applications written in other languages such as Java, Go, Rust, etc.

To use this endpoint, start MLflow Server with a SQL-based backend store. The following command starts MLflow Server with an SQLite backend store:

bash

mlflow server

To use other types of SQL databases such as PostgreSQL, MySQL, and MSSQL, change the store URI as described in the backend store documentation.

In your application, configure the server endpoint and set the MLflow experiment ID in the OTLP header x-mlflow-experiment-id.

bash

export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://localhost:5000/v1/traces
export OTEL_EXPORTER_OTLP_TRACES_HEADERS=x-mlflow-experiment-id=123

note

Currently, MLflow Server supports only the OTLP/HTTP endpoint, and the OTLP/gRPC endpoint is not yet supported.

Enable OpenTelemetry in Amazon Bedrock AgentCore

Refer to the Amazon Bedrock AgentCore Observability documentation for setting up tracing in Amazon Bedrock AgentCore and specify OTLP HTTP exporter with above environment variables.

Combine with the MLflow Tracing SDK

You can combine the auto-generated OpenTelemetry traces with the MLflow Tracing SDK to add custom spans, set tags, and log assessments within the same trace.

python

import os

os.environ["MLFLOW_USE_DEFAULT_TRACER_PROVIDER"] = "false"

import mlflow
from mlflow.entities.trace_location import MlflowExperimentLocation

mlflow.set_tracking_uri("http://localhost:5000")
exp_id = mlflow.set_experiment("Bedrock AgentCore").experiment_id
mlflow.tracing.set_destination(MlflowExperimentLocation(exp_id))

# Add custom MLflow spans alongside the auto-generated traces
with mlflow.start_span("custom_step") as span:
    span.set_inputs({"query": "test"})
    # your application logic here
    span.set_outputs({"result": "success"})

See Combining the OpenTelemetry SDK and the MLflow Tracing SDK for details.

Reference

For complete step-by-step instructions on sending traces to MLflow from OpenTelemetry compatible frameworks, see the Collect OpenTelemetry Traces into MLflow.