Hi, Spring fans! Welcome to another installment of This Week in Spring, which I'm writing from magnificent Minneapolis, Minnesota, where I'm recording an amazing Frontend Masters course introducing Spring Boot.

• I love this article introducing Spring AI in JavaPro magazine
• Want to run an LLM entirely in Java, supercharged with GraalVM native images? Check out this tweet from GraalVM developer advocate Alina Yurenko — it's dope.
• I loved it so much I made a quick YouTube Short on the same topic.
• By the way, want to learn Java? This is a great resource.
• The amazing Spring AI co-lead Christian Tsolov has a great talk introducing MCP.
• Spring team alumnus Arjen Poutsma has helped shape the APIs in Spring for a long time with his famous Poutsma Principles — in this blog, he discusses them.
• Spring Data 2025.0.0-RC1…

Hi, Spring fans! In this episode I'm joined by well-known member of the Java community Jeff Genender, whose contributions to Apache over the decades have driven several key projects with which you're no doubt familiar.

• Spring AI M7 is here! This new release includes a bunch of awesome new features! And some refactorings. Notably that the Spring AI auto-configuration has changed from a single monolithic artifact to individual auto-configuration artifacts per model, vector store, and other components. This change was made to minimize the impact of different versions of dependent libraries conflicting, such as Google Protocol Buffers, Google RPC, and others. By separating auto-configuration into component-specific artifacts, you can avoid pulling in unnecessary dependencies and reduce the risk of version…

This blog post demonstrates practical implementations of Prompt Engineering techniques using Spring AI.

The examples and patterns in this article are based on the comprehensive Prompt Engineering Guide that covers the theory, principles, and patterns of effective prompt engineering.

The blog shows how to translate those concepts into working Java code using Spring AI's fluent ChatClient API.

For convenience, the examples are structured to follow the same patterns and techniques outlined in the original guide.

The demo source code used in this article is available at: https://github.com/spring…

Hi, Spring fans! In this installment we talk to Wiremock's leaders Lee Turner and Tom Akehurst

Hi, Spring fans! How are ya? I'm doing fine. Excited, even. You see, Spring AI M7 is coming soon! In theory, it drops on Thursday. Don't hold us to that — these things can change :-) But soon, and it's turning out to be a whopper of a release!

You should try upgrading your application to the new M7 by using the -SNAPSHOT builds. The coordinates for the various starters have been reworked, so things will break there. Don't panic — you just need to update the coordinates. There's good information in the documentation.

Here's the gist:

• Model starters: spring-ai-{model}-spring-boot-starter → spring-ai-starter-model-{model}
• Vector Store starters: spring-ai-{store}-store-spring-boot-starter → spring-ai-starter-vector-store-{store}
• MCP starters: spring-ai-mcp-{type}-spring-boot-starter → spring-ai-starter-mcp-{type}
…

Hi, Spring fans! In this installment I talk to AWS Developer Advocate and industry legend James Ward about AWS Bedrock, Amazon Cohere, Spring AI, MCP, and so much more!

Using Spring AI 1.0.0-SNAPSHOT: Part 2 - Important Changes and Updates

This blog post is a continuation of our previous article Using Spring AI 1.0.0-SNAPSHOT: Important Changes and Updates, where we introduced the significant changes to artifact IDs, dependency management, and autoconfiguration in Spring AI 1.0.0-SNAPSHOT.

Since publishing that article, the Spring team has released an updates to the snapshots, In this follow-up article, we'll explore the latest changes and provide additional guidance for developers working with the snapshot versions. For comprehensive details, refer to the Spring AI Upgrade Notes…

Spring AI offers support for Model Context Protocol, or MCP for short, which allows AI models to interact with and access external tools and resources in a structured way. With Spring AI, developers can create their own MCP Servers and expose capabilities to AI models in just a few lines of code.

Authorization and security in MCP

MCP Servers can run locally, using the STDIO transport. To expose an MCP server to the outside world, it must expose a few standard HTTP endpoints. While MCP Servers used privately might not require strict authentication, enterprise deployments need robust security and permission management for exposed endpoints. This challenge is addressed in the newest version of the MCP specification (2025-03-26), which was released last week. It lays the foundation for securing communications between Clients and Servers, leveraging the widespread OAuth2 framework…