book

Spring AI in Action

Name: Spring AI in Action
Author: Craig Walls
ISBN: 9781633436114

by Craig Walls

November 2025

Intermediate to advanced

320 pages

9h 3m

English

Manning Publications

Read now

Unlock full access

Spring AI in Action
copyright
contents
foreword
preface
acknowledgments
about this book
about the author
about the cover illustration
1 Getting started with Spring AI
1.1 Hello, Spring AI!1.1.1 Initializing the project1.1.2 Submitting prompts1.1.3 Writing a test1.1.4 Trying it out1.2 Choosing a model1.2.1 Configuring OpenAI models1.2.2 Serving models locally with Ollama1.3 Previewing Spring AI’s capabilities

2 Evaluating generated responses
2.1 Ensuring relevant answers2.2 Testing for factual accuracy2.3 Applying self-evaluation at runtime
3 Submitting prompts for generation
3.1 Working with prompt templates3.1.1 Defining a prompt template3.1.2 Importing the template as a resource3.2 Stuffing the prompt with context3.3 Assigning prompt roles3.4 Influencing response generation3.4.1 Specifying chat options3.4.2 Formatting response output3.4.3 Streaming the response3.5 Working with response metadata
4 Talking with your documents
4.1 Understanding RAG4.2 Setting up a vector store4.3 Loading documents4.3.1 Initializing the loader project4.3.2 Defining the loader pipeline4.3.3 Creating the pipeline components4.3.4 Running the pipeline4.4 Implementing RAG4.4.1 Searching for similar documents4.4.2 Updating the service4.5 Implementing RAG with an advisor4.6 Applying modular RAG4.6.1 Rewriting the user’s query4.6.2 Translating user queries4.6.3 Expanding user queries
5 Enabling conversational memory
5.1 Making memories in AI5.2 Adding conversational memory5.2.1 Enabling an in-memory chat advisor5.2.2 Inspecting the prompt for chat memory5.2.3 Configuring chat memory size5.3 Specifying the conversation ID5.4 Enabling persistent chat memory5.4.1 Persisting chat memory to a database5.4.2 Storing chat memory in a vector store
6 Activating tool-driven generation
6.1 Getting started with AI tools6.1.1 Developing a tools-enabled application6.1.2 Digging deeper6.2 Implementing tools6.2.1 Writing the tool’s foundations6.2.2 Defining the tool6.2.3 Putting the tool to work6.3 Enables functions as tools
7 Applying Model Context Protocol
7.1 Introducing Model Context Protocol7.2 Working with MCP Clients7.3 Creating your own MCP Server7.3.1 Building the server7.3.2 Setting up the database7.3.3 Creating the MCP Server tools7.3.4 Inspecting the MCP Server7.3.5 Using the server in a client application7.4 Working with the HTTP+SSE transport7.4.1 Configuring an HTTP+SSE in the MCP Server7.4.2 Inspecting the MCP Server7.4.3 Configuring the client to use an HTTP+SSE server7.5 Exposing prompts and resources7.5.1 Declaring prompt and resource-exposing beans7.5.2 Applying annotation-driven prompts and resources
8 Generating with voice and pictures
8.1 Working with voice8.1.1 Transcribing speech8.1.2 Generating speech from text8.1.3 Applying audio input and output directly8.2 Asking questions about images8.3 Generating images8.3.1 Specifying image options
9 Observing AI operations
9.1 Enabling Actuator metrics9.1.1 Inspecting vector store operations9.1.2 Examining AI model interaction9.1.3 Counting token usage9.1.4 Observing ChatClient operations9.2 Viewing metrics in Prometheus9.3 Creating AI dashboards9.4 Tracing AI operations
10 Safeguarding generative AI
10.1 Controlling document access with RAG10.1.1 Designating premium content10.1.2 Adding security to Board Game Buddy10.1.3 Filtering for premium content10.1.4 Applying per-user conversational memory10.1.5 Trying it out10.2 Securing tools10.3 Safeguarding against adversarial prompting10.3.1 Preventing prompts with sensitive terms10.3.2 Preventing prompt leaks10.4 Moderating user input
11 Applying generative AI patterns
11.1 Summarizing content11.2 Translating messages11.2.1 Building a simple translator11.2.2 Translating game rule answers11.3 Analyzing sentiment
12 Employing agents
12.1 Understanding agents12.2 Implementing agentic workflows and patterns12.2.1 Chaining prompts12.2.2 Routing tasks12.2.3 Applying parallelization12.3 Creating self-planning agentic solutions12.3.1 Initializing an Embabel project12.3.2 Defining the agent class12.3.3 Defining an action to get game rules12.3.4 Defining an action to get the rules filename12.3.5 Defining an action to get the game title12.3.6 Running the agent via Embabel’s shell12.3.7 Accessing the agent via MCP

Content preview from Spring AI in Action

7 Applying Model Context Protocol

This chapter covers

Using tools from a predefined MCP Server
Creating a custom MCP Server
Enabling MCP’s STDIO and HTTP+SSE transports
Exposing tools, prompts, and resources

In the movie Wreck-It Ralph, the character Fix-It Felix Jr. carries an incredibly powerful hammer. With this one tool, Fix-It Felix Jr. is able to repair anything that’s broken by just hitting it once. Got a cracked wall? Hit it with a hammer. Bent streetlights? Hit it with a hammer. Broken window? Defying all logic and everything you know about glass and hammers, hit it with a hammer, and it will be fixed. Fix-It Felix Jr.’s hammer is rivaled only by Thor’s Mjolnir as the most amazing hammer that has ever been wielded.

But ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Spring Microservices in Action, Second Edition

Publisher Resources

ISBN: 9781633436114Publisher Support Other Publisher Website Purchase Link

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Spring AI in Action

by Craig Walls