A Practical Guide to Oracle AI Engineering
Description
In A Practical Guide to Oracle AI Engineering, you'll learn how to tackle the challenges of building scalable, high-performance AI workflows in modern enterprises. Many organizations struggle to turn raw data into actionable insights while maintaining security, compliance, and operational efficiency. This book provides practical, end-to-end guidance for data engineers and architects to design, secure, implement, and optimize ML and GenAI solutions across Oracle Cloud, Oracle Database, and MySQL HeatWave. Written by multiple Oracle experts with deep experience in Oracle technologies and enterprise data platforms, this book walks you through real-world examples and hands-on workflows, from data preparation and in-database ML to deploying GenAI-powered applications and intelligent agents. You'll gain skills in building pipelines, managing models, leveraging vector search for advanced AI use cases, and integrating AI into business applications with APEX and Oracle Digital Assistant. Advanced topics include scalable model deployment, serverless inference, monitoring, and MLOps best practices. By the end, you'll be equipped to solve complex data challenges, accelerate AI adoption, and deliver measurable business impact through intelligent, production-ready solutions.
All prices
More details
Content
- Cover
- Title Page
- Contributors
- Table of Contents
- Preface
- Free benefits with your book
- Chapter 1: Overview of Oracle's AI and ML Ecosystem
- Your purchase includes a free PDF copy + exclusive extras
- An overview of Oracle's AI stack
- AI Services: Pre-built intelligence
- OCI Generative AI: Foundation models for the enterprise
- AI Agents: Orchestrating intelligent workflows
- ML services: OCI Data Science
- AI infrastructure: The compute foundation
- OCI Data Science: Building and deploying machine learning models
- OCI Data Science model deployment
- OCI Data Science pipelines
- Integration of Oracle's AI and machine learning ecosystem for data engineering
- How the pieces connect
- Overview of Oracle's cloud and database solutions for machine learning
- Oracle Autonomous Database
- Oracle AI Database 26ai
- AI Vector Search
- ONNX model import
- Select AI
- RAG with DBMS_VECTOR_CHAIN
- OCI Supercluster vs. legacy SuperCluster
- Real-world use case examples
- Summary
- Get this book's PDF version and more
- Chapter 2: Oracle AI Solution Lifecycle, Design Patterns, and Platform Choices
- Oracle AI as an enterprise architecture
- Enterprise AI and Oracle AI
- Oracle's approach to enterprise AI
- Addressing the AI lifecycle with the Oracle AI stack
- Navigating enterprise realities and constraints
- AI lifecycle
- Key design drivers across the lifecycle
- Core Oracle AI architecture patterns
- Modern AI landscape
- Mapping AI stages to Oracle AI capabilities
- Oracle design patterns
- In-database AI patterns
- Service-centric and GenAI patterns
- Generative-centric and agentic AI pattern
- Hybrid AI patterns
- Summary
- Get this book's PDF version and more
- Chapter 3: Data Preparation and In-Database Model Training
- Introduction to Oracle Machine Learning
- OML lifecycle overview
- Data preparation within Oracle Database
- Data cleaning and transformation fundamentals
- In-database tools and techniques for data cleaning
- Feature engineering for predictive models
- Building features with Oracle SQL and PL/SQL
- Automating feature engineering with Oracle tools
- Leveraging in-database machine learning
- OML components by deployment environment
- Key features of OML
- Common in-database machine learning use cases
- Automating model selection and tuning with AutoML
- Oracle AutoML workflow
- Benefits of using Oracle AutoML
- Implementing AI Vector Search in Oracle
- Understanding and creating vector embeddings
- Performing semantic similarity search
- Enhancing LLMs with RAG
- Querying data naturally with Select AI
- Benefits of using Select AI
- Select AI use cases in practice
- Summary
- Further reading
- Get this book's PDF version and more
- Chapter 4: Model Deployment and In-Database Management
- In-database machine learning in Oracle Database
- Overview of OML Services for deploying models in database
- Model scoring
- Model inspection and explainability
- Enterprise deployment planning
- RESTful endpoint support
- Benefits of in-database model deployment
- Seamless integration with enterprise workflows
- Enterprise-grade security and governance
- Scalability and high availability
- Consistency across the machine learning lifecycle
- Real-time analytics with in-database machine learning
- Techniques for real-time prediction
- SQL and PL/SQL: inline predictions
- REST APIs with OML Services
- System-level optimizations: Exadata and Autonomous Database
- Automatic data preparation
- Partitioned models and parallel scoring
- Governance, security, and observability
- Real-time machine learning use cases
- Managing and monitoring OML models
- Managing model versions and lifecycle
- Monitoring model performance
- OML Services REST API
- Summary
- Further reading
- Get this book's PDF version and more
- Chapter 5: Advanced Techniques for Optimizing Machine Learning and AI Workloads on Oracle Database
- Technical requirements
- Scaling and optimizing in-database AI models
- Data layer: partitioning, sharding, and Oracle True Cache
- Partitioning
- Sharding
- Oracle True Cache
- In-database feature engineering, model execution and deployment
- Feature engineering
- Model execution
- Model deployment
- In-database similarity search and RAG
- Embeddings and vectors
- Embeddings generation
- Advanced vectorization
- Connecting LLMs with data using RAG
- RAG workflow overview
- End-to-end RAG scenario
- Advanced RAG
- Summary
- Get this book's PDF version and more
- Chapter 6: Preparation and Installation of MySQL HeatWave
- Technical requirements
- Understanding MySQL and HeatWave
- A quick MySQL history lesson
- What is HeatWave?
- Data lake
- Data warehouse
- HeatWave Lakehouse
- How to build a HeatWave database
- OCI tenancy access
- Creating a compartment and VCN
- Allowing network access
- Creating a user group and policy
- Building a HeatWave database
- Working with data in MySQL HeatWave
- Importing data
- Automatic loading
- Manual loading
- Training on the data
- HeatWave and GenAI and vectors
- Summary
- Get this book's PDF version and more
- Chapter 7: Model Deployment and Optimization on HeatWave
- Technical requirements
- How to build a Linux VM and load your data
- Building a Linux VM
- MySQL CLI data loading
- Using the model
- HeatWave Autopilot
- Use cases for machine learning inside the database
- Fraud detection and anomaly detection
- Predictive maintenance in manufacturing
- Customer churn prediction
- Recommendation systems
- Demand forecasting and inventory optimization
- Natural language processing for customer feedback
- Real-time personalization in marketing
- Healthcare predictive analytics
- Cybersecurity and access control
- Financial forecasting and risk modeling
- Summary
- Get this book's PDF version and more
- Chapter 8: Introduction to Generative AI Services
- Technical requirements
- What is GenAI?
- How GenAI works
- Common applications of GenAI
- Understanding models and core concepts
- What are tokens?
- Why different models exist
- Pretrained models available in OCI
- Cohere models
- Meta Llama family
- Grok models
- Google Gemini
- Key GenAI terms
- Content moderation
- Embedding
- Frequency penalty
- GenAI model
- Inference
- Likelihood
- Model endpoint
- Playground
- Preamble
- Presence penalty
- Prompts and prompt engineering
- Retrieval-augmented generation (RAG)
- Retirement and depreciation
- Streaming
- Temperature
- Top K
- Top P
- Getting started with OCI Generative AI
- Exploring models in the playground
- Why use a dedicated AI cluster?
- Creating a dedicated AI cluster in OCI
- Calling GenAI from a REST API
- Understanding GenAI agents
- How an OCI Generative AI Agent uses SQL for retrieval
- Building a GenAI agent with RAG and a database
- Summary
- Get this book's PDF version and more
- Chapter 9: Leveraging Oracle AI Services for Machine Learning
- Technical requirements
- Introduction to Oracle AI Services
- An overview of Oracle AI Services
- Benefits of using Oracle AI Services for AI and machine learning development
- Core Oracle AI Services and use cases
- Preparing to use the APIs
- Speech AI
- Language AI
- Vision AI
- Document Understanding
- Implementation and best practices
- Calling AI services using Oracle Functions
- Tips for optimizing performance, scalability, and cost
- Security considerations when using AI services
- Summary
- Get this book's PDF version and more
- Chapter 10: Leveraging Oracle Data Science Service for Machine Learning
- Introduction to Oracle Data Science Service
- OCI Data Science lifecycle
- Key features and benefits for machine learning development
- End-to-end machine learning workflow
- Creating and managing notebooks
- Notebook configuration and execution
- Running models via REST API
- Best practices for performance and security in OCI Data Science
- Optimizing model performance and scalability
- Data quality
- Optimizing compute performance
- Collaboration optimization
- Security and governance considerations
- Access control to protect the data
- Auditing and security monitoring
- Managing regulatory compliance
- Summary
- Get this book's PDF version and more
- Chapter 11: Building Intelligent Applications with Oracle Digital Assistant
- Oracle Digital Assistant foundations
- Oracle Digital Assistant overview
- Oracle Digital Assistant high-level architecture
- Digital assistants (chatbots)
- Skills
- Channels
- Oracle Digital Assistant conversational applications
- Oracle Digital Assistant project
- Oracle Digital Assistant project team
- Conversation design best practices, challenges, and limitations
- Design best practices
- Design challenges
- Limitations
- Extending Oracle Digital Assistant with GenAI
- LLM-based conversation
- Configuring the LLM integration
- Executing generative inference at runtime
- Agents-based conversation
- Design patterns
- Oracle Digital Assistant with GenAI agents
- Summary
- Get this book's PDF version and more
- Chapter 12: Machine Learning and AI Security, Governance, and Best Practices
- Ethical and transparency challenges in AI systems
- Safety, security, and data risks in AI deployment
- Safeguarding sensitive data during model development
- Safeguarding challenges and solutions
- Organization changes are required
- Best practices for data governance and regulatory compliance
- Data governance
- Regulatory compliance
- Data quality
- Data transparency
- Data privacy
- Implementing governance
- The need for AI guardrails
- Summary
- Get this book's PDF version and more
- Why subscribe?
- Other Books You May Enjoy
- Index
Preface
Oracle has spent decades building one of the world's most trusted enterprise technology platforms. From the early days of relational databases to today's AI-driven cloud architecture, Oracle has continuously evolved to meet changing business demands. Now, with AI integrated directly into the database, embedded across cloud platform services, and enhanced through modern generative AI capabilities, Oracle is redefining enterprise AI.
This book explores that transformation.
For years, organizations treated AI as a separate ecosystem requiring specialized infrastructure, disconnected machine learning platforms, complex data pipelines, and costly integrations. Data had to be extracted from operational systems, copied into external platforms, transformed multiple times, and secured across various environments before meaningful intelligence could be generated. This often resulted in slow innovation, higher costs, fragmented governance, and unnecessary risks. Instead of forcing enterprises to move data to AI, Oracle brings AI directly to the data.
This architectural distinction is one of Oracle's greatest competitive advantages and a central theme of this book. Oracle AI is not simply a collection of standalone machine learning services; it is a deeply integrated platform strategy spanning the Oracle Database, Oracle Cloud Infrastructure, platform as a service (PaaS) offerings, and enterprise-grade generative AI services.
Oracle Database 26ai and MySQL represent a major shift in enterprise data platforms. These databases are evolving from systems of record into systems of intelligence, with AI capabilities embedded directly where mission-critical business data resides. This reduces latency, lowers operational complexity, strengthens security, and accelerates enterprise AI adoption.
Beyond the database, Oracle Cloud Infrastructure extends this AI-first philosophy into the cloud. OCI was engineered for modern enterprise workloads, including large-scale AI and high-performance computing. Oracle's networking architecture, bare metal performance, GPU infrastructure, RDMA cluster networking, and distributed cloud model provide the foundation for demanding AI training and inference workloads. Oracle also emphasizes predictable performance, cost efficiency, and enterprise interoperability.
Oracle's generative AI services combine enterprise security, scalable infrastructure, and access to leading large language models through a unified cloud platform. Businesses can use these services for conversational AI, content generation, code assistance, document summarization, semantic search, intelligent agents, and industry-specific AI applications while maintaining enterprise-grade governance and data privacy.
Unlike many AI platforms focused on isolated use cases or demonstrations, Oracle integrates AI into real business operations across finance, healthcare, manufacturing, telecommunications, retail, government, and enterprise applications.
Throughout these chapters, we will explore:
- AI capabilities embedded directly inside Oracle Database
- Oracle Cloud Infrastructure for AI workloads
- Oracle AI and machine learning services
- Generative AI integration patterns
- Enterprise security and governance strategies
- Real-world business use cases and modernization scenarios
- AI-enabled application development
- Hybrid and distributed cloud AI architectures
The future belongs to integrated intelligence, where databases, applications, cloud infrastructure, and AI services operate as a unified platform.
Oracle is uniquely positioned to lead that future.
Who this book is for
This book is intended for architects, developers, database administrators, cloud engineers, IT leaders, and business decision makers who want to understand how Oracle AI technologies work together across the modern enterprise stack. Whether you are building AI-powered applications, modernizing legacy systems, implementing cloud-native architectures, or evaluating enterprise AI strategies, this book will provide both technical insight and business perspective.
What this book covers
Chapter 1, Overview of the Oracle AI and Machine Learning Ecosystem, introduces the Oracle AI ecosystem and provides an overview of Oracle Database, Oracle Cloud Infrastructure, Oracle AI Services, and Generative AI platforms. It also explains Oracle's approach to in-database AI and enterprise AI architectures.
Chapter 2, Oracle AI Solutions Lifecycle, Design Patterns, and Platform Choices, examines the AI and machine learning lifecycle using Oracle technologies, including enterprise AI design patterns, deployment strategies, and platform selection across Oracle Database, HeatWave, OCI AI Services, and Generative AI solutions.
Chapter 3, Data Preparation and In-Database Model Training, explores data cleansing, transformation, feature engineering, and machine learning model training directly inside Oracle Database using Oracle Machine Learning capabilities.
Chapter 4, Model Deployment and In-Database Management, focuses on deploying and managing machine learning models within Oracle environments, including model lifecycle management, scoring pipelines, REST interfaces, automation, version control, and monitoring techniques.
Chapter 5, Optimizing Machine Learning and AI Workloads on Oracle Database, covers techniques for tuning AI and machine learning workloads using vector search optimization, parallel processing, indexing strategies, memory management, and autonomous database features.
Chapter 6, Getting Started with MySQL HeatWave, introduces MySQL HeatWave and explains its role in AI and analytics architectures, including HeatWave architecture, setup, data loading, and foundational AI concepts.
Chapter 7, Model Deployment and Optimization on HeatWave, explores deploying and optimizing machine learning models within MySQL HeatWave using HeatWave AutoML, in-database analytics, and query acceleration capabilities.
Chapter 8, Introduction to Oracle Generative AI Services and Agents, introduces Oracle Generative AI Services, large language models, retrieval-augmented generation, AI agents, and conversational AI architectures across OCI.
Chapter 9, Leveraging Oracle AI Services for Machine Learning, focuses on Oracle AI Services available through OCI, including prebuilt AI services for vision, language, speech, anomaly detection, forecasting, and document understanding.
Chapter 10, Building Machine Learning Solutions with Oracle Data Science, explores the tools and workflows for building machine learning solutions using Oracle Data Science, including notebook environments, training pipelines, MLOps, and OCI integration.
Chapter 11, Building Intelligent Applications with Oracle Digital Assistant, explains how Oracle Digital Assistant enables organizations to build AI-powered chatbots, automate workflows, integrate backend systems, and deliver conversational experiences.
Chapter 12, Machine Learning and AI Security, Governance, and Best Practices, explores AI security, governance, compliance, responsible AI frameworks, and best practices for building scalable and trustworthy enterprise AI solutions using Oracle technologies.
To get the most out of this book
You will need a general understanding of the technologies outside of the AI use cases. You should understand the basics of Oracle Enterprise Edition, Oracle MySQL, and Oracle Cloud Infrastructure.
An understanding of Linux and python will be helpful for most of the examples. Most of the examples will need an OCI account. You can get a free OCI account from https://www.oracle.com/cloud/free/
Download the example code files
This book includes a complete downloadable code bundle containing all the example projects and files used throughout the chapters. We recommend downloading the bundle so you can follow along smoothly and experiment with the examples.
Use the bundle as a practical starting point. Modify it, extend it, and apply what you learn by creating your own variations as you progress through the chapters.
Get the code bundle
If you bought the book directly from Packt:
- Go to packtpub.com
- Click your profile picture and select Your Orders
- Find this book and click Download Code
If you bought this book from Amazon or any other channel partner:
- Go to packtpub.com/unlock or scan the following QR code:
- Search for this book
- Sign up or log in to your free Packt account
- Upload your proof of purchase and download the code bundle locally
Usage note: You're free to use and modify this code for personal learning and non-commercial projects.
Download the color images
Your purchase includes a color, DRM-free PDF copy of this book, ideal for viewing color images, screenshots, and diagrams. Refer to Free Benefits with Your...
