Amazon Web Services (AWS) has introduced a REST API proxy service to streamline external access to Amazon SageMaker MLflow. The solution addresses the challenge of integrating MLflow with existing enterprise systems that require HTTPS-based integrations rather than direct SDK usage. According to AWS, many organizations need to maintain security and infrastructure patterns while integrating SageMaker MLflow with their established systems. This solution is designed for companies undergoing cloud transformation who want to preserve their existing ML workflows while adopting cloud-native services. The proxy service acts as a bridge, transforming standard HTTPS requests into authenticated AWS API calls that can interact with SageMaker MLflow. The architecture includes three key components: an Application Load Balancer (ALB), a Flask-based proxy service, and the SageMaker MLflow service itself. The ALB serves as the upstream router, handling traffic distribution and SSL termination. The Flask proxy service processes incoming HTTPS requests, manages AWS authentication, and transforms URLs for secure access. The SageMaker MLflow service provides ML tracking and model management capabilities. The solution enables secure communication while maintaining compatibility with existing enterprise systems. *Source: [awsml](https://aws.com/blogs/machine-learning/streamline-external-access-to-amazon-sagemaker-mlflow-using-a-rest-api-proxy/)*