Introduction

Oracle Machine Learning (OML) in Oracle Autonomous Database provides access to in-database machine learning features. OML Services extends OML functionality to support data monitoring, model monitoring, model deployment, model lifecycle management for both in-database OML models and third-party Open Neural Networks Exchange (ONNX) format machine learning models through REST APIs.

The REST API for Oracle Machine Learning Services provides REST API endpoints hosted on Oracle Autonomous Database. These endpoints enable you to store machine learning models along with its metadata, and create scoring endpoints for the model.

• OML Services supports model deployment and model lifecycle management for both native in-database OML models and third-party Open Neural Networks Exchange (ONNX) machine learning models via REST APIs. The REST API for Oracle Machine Learning Services provides REST API endpoints hosted on Oracle Autonomous Database. These endpoints enable you to store machine learning models along with their metadata, and create scoring endpoints for the model. OML Services support for scoring data includes real-time singleton and small batch scoring for native and ONNX-format models, and asynchronous batch scoring for native models. For more information, refer to:
  • Work with Oracle Machine Learning Models
  • Work with Batch Scoring
  • Batch Scoring Examples using Regression, Classification, Clustering, and Feature Extraction Models
• OML Services Monitoring for native models enables users to monitor data for changes from a baseline dataset. Data monitoring can help maintain organizational data quality standards to help ensure the integrity of enterprise applications and dashboards. OML Services expands support for the machine learning lifecycle and MLOps with the combination of data monitoring and model monitoring. For more information, refer to:
  • Data Monitoring Example
  • Model Monitoring Example
• OML Services supports third-party ONNX-format classification, regression, and clustering models, which can be produced externally using packages like Scikit-learn and TensorFlow, among others. OML Services also supports image classification using third-party ONNX format models with scoring via images or tensors. For more information, refer to:
  • Work with ONNX Format Models
  • Work with ONNX Image Models
• OML Services cognitive text capability for English, Spanish, French, and Italian support topic discovery, keywords, summary, sentiment (English only), and feature extraction. For more information, refer to:
  • Work with Cognitive Text Functionality