# Spring AI

Spring AI is an application framework for AI engineering that integrates enterprise data and APIs with AI models.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Spring AI 2.1.0 GA and 2.0.3 GA Available Now

DevFeed: [Spring AI 2.1.0 GA and 2.0.3 GA Available Now](<https://devfeed.tech/articles/spring-ai-2-1-0-ga-and-2-0-3-ga-available-now-146701.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/11/20/spring-ai-2-1-0-GA-available-now>)

Author: tzolov

Published: 2026-11-20T00:00:00Z

Content type: release

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [guardrail](<https://devfeed.tech/tags/guardrail.md>), [harness](<https://devfeed.tech/tags/harness.md>), [java](<https://devfeed.tech/tags/java.md>), [maven](<https://devfeed.tech/tags/maven.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [memory](<https://devfeed.tech/tags/memory.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [openai](<https://devfeed.tech/tags/openai.md>), [parts](<https://devfeed.tech/tags/parts.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [recall](<https://devfeed.tech/tags/recall.md>), [release](<https://devfeed.tech/tags/release.md>), [responses-api](<https://devfeed.tech/tags/responses-api.md>), [security](<https://devfeed.tech/tags/security.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [session](<https://devfeed.tech/tags/session.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1.0 GA, built on Spring Boot 4.2, adds a stateless MCP 2026-07-28 protocol, typed Decision Models, ordered message parts that preserve reasoning and provider-specific payloads, and an OpenAI Responses API chat model. Its agent building blocks include a Session API with compaction and event recall (ChatMemory is deprecated for removal in 3.0), per-tool approval pauses, configurable per-turn call limits, and marked guardrail refusals. Eleven vector stores can now write and search vectors computed elsewhere, with width checks and stable-ID replacement. The release also includes reference-documentation changes and security fixes; Spring AI 2.0.3 carries the fixes on the 2.0.x line. Upgrading to 2.1 generally involves updating Spring AI and Spring Boot together, but some security fixes change behavior, and applications upgrading from 2.0.2 or earlier are directed to review the 2.0.2 and 2.0.3 notes.

### Source excerpt

On behalf of the Spring AI team and everyone who has contributed, I'm happy to announce that Spring AI 2.1.0 has been released and is now available from Maven Central! Release notes | Upgrade notes | Reference documentation Spring AI 2.1 arrives five months after 2.0.0 GA. It is built on Spring Boot 4.2 and contains more than 430 commits from 86 contributors. This post covers everything that changed since 2.0.0: the features of the 2.1 milestones and release candidates, what was added after RC2, and the additions that already shipped in 2.0.1 and 2.0.2. The short version: MCP 2026-07-28. Servers and clients for the new, stateless revision of the Model Context Protocol, next to the existing ones. Decision Models. A new model API for typed yes/no, choice and score decisions, with three providers. A richer message model. Messages hold ordered parts, so reasoning, tool calls and provider-specific blocks survive a round trip. The OpenAI Responses API is supported next to Chat Completions. The building blocks of an agent harness. The Session API, with session memory, compaction and recall, replaces ChatMemory. Tool calls can wait for a person's approval and are limited per turn, and guardrail refusals are marked as such. Your own embeddings. Eleven vector stores can write and search with vectors you computed yourself. New reference documentation, organized around tasks, with a quickstart and tutorials. Security. Fixes for 13 CVEs, which Spring AI 2.0.3 has as well. Next: Spring AI Agent. A new project for composing and orchestrating agents, built on Spring AI 2.1, starts incubating in early December. See What's next. The following map shows the building blocks of Spring AI 2.1, with the community projects in blue. It comes from the new reference documentation, where the blocks link to their pages. MCP 2026-07-28 The 2026-07-28 revision is a redesign of the Model Context Protocol. It is stateless: there is no initialize handshake and no session, every request carries the p

## Building a reliable AI agent with OSCAR

DevFeed: [Building a reliable AI agent with OSCAR](<https://devfeed.tech/articles/building-a-reliable-ai-agent-with-oscar-141983.md>)

Original publisher: [Read original article](<https://temporal.io/blog/building-a-reliable-ai-agent-with-oscar>)

Author: Loïc Ortola

Published: 2026-11-18T00:00:00Z

Content type: article

Language: en

Sources: [Temporal](<https://devfeed.tech/sources/temporal-blog.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [observability](<https://devfeed.tech/topics/observability.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-loop](<https://devfeed.tech/tags/agentic-loop.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-decisions](<https://devfeed.tech/tags/ai-decisions.md>), [building](<https://devfeed.tech/tags/building.md>), [community](<https://devfeed.tech/tags/community.md>), [durable-execution](<https://devfeed.tech/tags/durable-execution.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [retries](<https://devfeed.tech/tags/retries.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [temporal](<https://devfeed.tech/tags/temporal.md>)

### AI overview

OSCAR turns an emailed refund request into an action across the marketplace backend and Stripe, using an LLM to interpret the complaint and tools to check orders, update status, issue refunds, and reply. The initial Spring AI prototype can complete the flow, but a Stripe outage or process restart can leave partial work stranded, with no recovery or visibility into the agent's decisions. The Spring AI/Temporal integration runs model calls and external tools as Activities, adding retries and durable resumption while preserving the agent's business logic; Temporal's UI records inputs, results, retries, and failures, though individual retry attempts need Worker logs or extra instrumentation. Workflows can also pause without polling for human approval, resume after a process restart, and branch on the decision or a timeout. Temporal does not solve context growth, prompt or tool quality, or security: backend tools must independently validate and authorize actions, since agent instructions are not a security boundary.

### Source excerpt

Learn how to take a Spring AI agent from prototype to production with Temporal, adding durable execution, retries, observability, and human approval.

## Java News Roundup: Lazy Constants, Spring for Apache Pulsar, GlassFish, Hibernate, TomEE, Seed4J

DevFeed: [Java News Roundup: Lazy Constants, Spring for Apache Pulsar, GlassFish, Hibernate, TomEE, Seed4J](<https://devfeed.tech/articles/java-news-roundup-lazy-constants-spring-for-apache-pulsar-glassfish-hibernate-tomee-seed4j-135562.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/java-news-roundup-nov09-2026/>)

Author: Michael Redlich

Published: 2026-11-16T15:25:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Java](<https://devfeed.tech/topics/java.md>), [releases](<https://devfeed.tech/topics/releases.md>), [Hibernate](<https://devfeed.tech/topics/hibernate.md>), [openjdk](<https://devfeed.tech/topics/openjdk.md>), [Apache Pulsar](<https://devfeed.tech/topics/pulsar.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Spring Boot](<https://devfeed.tech/topics/spring-boot.md>), [jpa](<https://devfeed.tech/topics/jpa.md>), [Quarkus](<https://devfeed.tech/topics/quarkus.md>), [Maven](<https://devfeed.tech/topics/maven.md>), [TornadoVM](<https://devfeed.tech/topics/tornadovm.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [ai](<https://devfeed.tech/tags/ai.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-tomee](<https://devfeed.tech/tags/apache-tomee.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [boot](<https://devfeed.tech/tags/boot.md>), [development](<https://devfeed.tech/tags/development.md>), [features](<https://devfeed.tech/tags/features.md>), [first](<https://devfeed.tech/tags/first.md>), [glassfish](<https://devfeed.tech/tags/glassfish.md>), [hibernate](<https://devfeed.tech/tags/hibernate.md>), [hibernate-orm](<https://devfeed.tech/tags/hibernate-orm.md>), [hibernate-reactive](<https://devfeed.tech/tags/hibernate-reactive.md>), [highlighting](<https://devfeed.tech/tags/highlighting.md>), [java](<https://devfeed.tech/tags/java.md>), [java-news-roundup-nov09-2026](<https://devfeed.tech/tags/java-news-roundup-nov09-2026.md>), [jdk-28](<https://devfeed.tech/tags/jdk-28.md>), [jobrunr](<https://devfeed.tech/tags/jobrunr.md>), [lazy](<https://devfeed.tech/tags/lazy.md>), [news](<https://devfeed.tech/tags/news.md>), [news-roundup](<https://devfeed.tech/tags/news-roundup.md>), [open-jdk](<https://devfeed.tech/tags/open-jdk.md>), [pulsar](<https://devfeed.tech/tags/pulsar.md>), [quarkus](<https://devfeed.tech/tags/quarkus.md>), [seed4j](<https://devfeed.tech/tags/seed4j.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-boot](<https://devfeed.tech/tags/spring-boot.md>), [tornadovm](<https://devfeed.tech/tags/tornadovm.md>)

### AI overview

The Java updates include a fourth preview of Lazy Constants proposed for JDK 28, keeping the computed-constants design unchanged: immutable values initialized at most once, with more flexible initialization timing than `final` fields. Spring AI 2.1.0 RC2 adds a DecisionModel API for outcome probabilities and embedding-based vector search; Spring Boot 4.2.0 RC2 fixes forwarded-prefix handling for WebFlux on Reactor Netty under the native strategy and Redis database selection for master/replica connections. Spring for Apache Pulsar is moving under the Apache Pulsar project; 2.0.8 was its final Spring ecosystem release. Other notable changes include jitLLM 3.0's reported faster startup and prefill and reduced model-weight copying on Apple Metal; GlassFish 9 milestone 4's Jakarta Persistence 4.0 milestone implementation; Hibernate ORM 8 RC1's Jakarta Persistence and Data implementations and graph-based flush coordination; and TomEE 11 milestone 2's 38 CVE resolutions and Jakarta Authorization 3.0 implementation. Seed4J 2.4/2.3 also share one global Maven cache and install Playwright only where relevant component tests run. This is a roundup excerpt, so it does not establish full detail

### Source excerpt

This week's Java roundup for November 9th, 2026, features news highlighting: Lazy Constants proposed to target for JDK 28; TornadoVM jitLLM 3.0; point releases of Seed4J; second release candidates of Spring AI and Spring Boot; first release candidates of Hibernate ORM and Hibernate Reactive; fourth milestone release of GlassFish; and the second milestone release of Apache TomEE. By Michael Redlich

## Porto TechHub 2026

DevFeed: [Porto TechHub 2026](<https://devfeed.tech/articles/porto-techhub-2026-134537.md>)

Original publisher: [Read original article](<https://blog.frankel.ch/porto-techhub-2026/>)

Author: Nicolas Fränkel

Published: 2026-11-15T00:00:00Z

Content type: article

Language: en

Sources: [Nicolas Fränkel](<https://devfeed.tech/sources/nicolas-frankel.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [QCon San Francisco 2025](<https://devfeed.tech/topics/qcon-san-francisco-2025.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-framework](<https://devfeed.tech/tags/agentic-ai-framework.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-frameworks](<https://devfeed.tech/tags/ai-frameworks.md>), [branch](<https://devfeed.tech/tags/branch.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [clone](<https://devfeed.tech/tags/clone.md>), [coding-assistants](<https://devfeed.tech/tags/coding-assistants.md>), [conference](<https://devfeed.tech/tags/conference.md>), [devrel](<https://devfeed.tech/tags/devrel.md>), [embabel](<https://devfeed.tech/tags/embabel.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [git](<https://devfeed.tech/tags/git.md>), [hash](<https://devfeed.tech/tags/hash.md>), [porto](<https://devfeed.tech/tags/porto.md>), [techhub](<https://devfeed.tech/tags/techhub.md>)

### AI overview

The Porto TechHub recap covers talks on agent workflows, Java AI frameworks, and upcoming Git defaults. Patrick Baumgartner's Embabel presentation described combining goal-oriented action planning with programmatic guardrails; in Embabel, Java types connect workflow steps when one method's return type matches another's input, with Spring and annotations supporting implementation. Rui Quintino's talk, as observed by the author, mostly showed coding-assistant demos, including building a Word clone to avoid Word's document lock. Sandra Ahlgrimm and Timo Salm compared Spring AI, LangChain4j, and Embabel using an AI nutrition planner, though the excerpt gives no comparison results. Rob Richardson covered four planned Git 3 defaults: SHA-256, reftable, `main`, and bare repositories marked safe. He said existing Git 2 repositories should still work and demonstrated migration; he identified hosting-provider support as the main release obstacle.

### Source excerpt

My conference participation has dropped sharply since I left DevRel for a regular office engineering job. In 2023, I was proud to have had 70 talks; I'll finish this year with 4, including one online and one quickie. It has one beneficial side effect, though. Because I go to so few, I take the time to attend. Last Tuesday, I was lucky to attend and talk at the Porto TechHub conference, for the 4th year. Here are the talks I attended and their respective summary.

## Rate Limit Information from Anthropic API Response Headers Using ChatResponseMetadata in Spring AI

DevFeed: [Rate Limit Information from Anthropic API Response Headers Using ChatResponseMetadata in Spring AI](<https://devfeed.tech/articles/rate-limit-information-from-anthropic-api-response-headers-using-chatresponsemetadata-in-spring-ai-134252.md>)

Original publisher: [Read original article](<https://www.baeldung.com/spring-ai-anthropic-rate-limit>)

Author: Olayemi Michael

Published: 2026-11-14T14:14:40Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Spring MVC](<https://devfeed.tech/topics/spring-mvc.md>)

Tags: [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-api](<https://devfeed.tech/tags/anthropic-api.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-anthropic-spring-ai-chatclient](<https://devfeed.tech/tags/artificial-intelligence-anthropic-spring-ai-chatclient.md>), [controller](<https://devfeed.tech/tags/controller.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [github](<https://devfeed.tech/tags/github.md>), [java](<https://devfeed.tech/tags/java.md>), [limits](<https://devfeed.tech/tags/limits.md>), [maven](<https://devfeed.tech/tags/maven.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-ai-chatclient](<https://devfeed.tech/tags/spring-ai-chatclient.md>)

### AI overview

The excerpt shows how a Spring AI application can return Anthropic rate-limit and token-usage data alongside generated text. Configure the Anthropic starter and API key, call the model through ChatClient, then read ChatResponseMetadata.getRateLimit() for request and token limits, remaining amounts, and reset duration; getUsage() supplies prompt and completion token counts. A controller can place these fields, the model name, and response text in a Java record returned from an endpoint. The sample response reports 10,000 requests allowed and 9,999 remaining, plus a token budget and usage counts. The values are those reported in the example; the excerpt does not compare providers.

### Source excerpt

Learn how to access rate limit metadata returned by Anthropic through Spring AI. The post Rate Limit Information from Anthropic API Response Headers Using ChatResponseMetadata in Spring AI first appeared on Baeldung.

## Using the Official OpenAI Java SDK With Spring AI

DevFeed: [Using the Official OpenAI Java SDK With Spring AI](<https://devfeed.tech/articles/using-the-official-openai-java-sdk-with-spring-ai-134250.md>)

Original publisher: [Read original article](<https://www.baeldung.com/java-spring-ai-openai-sdk>)

Author: Francesco Galgani

Published: 2026-11-14T14:11:09Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Spring Framework](<https://devfeed.tech/topics/spring-framework.md>), [SDK](<https://devfeed.tech/topics/sdk.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [Groovy](<https://devfeed.tech/topics/groovy.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [java](<https://devfeed.tech/tags/java.md>), [java-sdk](<https://devfeed.tech/tags/java-sdk.md>), [openai](<https://devfeed.tech/tags/openai.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-ai-chatclient](<https://devfeed.tech/tags/spring-ai-chatclient.md>), [spring-ai-openai-spring-ai-chatclient](<https://devfeed.tech/tags/spring-ai-openai-spring-ai-chatclient.md>)

### AI overview

Spring AI 2.0.2 routes ChatClient calls through OpenAiChatModel to the official OpenAI Java SDK, while Spring Boot configures the client. Add spring-ai-starter-model-openai; openai-java-core is included transitively. The example uses Chat Completions, not the Responses API. ChatClient-based summarization works with Gemini's OpenAI-compatible endpoint too, but requires provider-specific credentials and settings: Gemini 3 cannot disable thinking, so the example uses low reasoning effort, a larger token limit, and a longer timeout. Migrating from spring-ai-openai-sdk changes the starter, property prefix, and SDK-suffixed model/options classes; ChatClient service code can remain the same. Existing chat.options properties are retained as deprecated aliases.

### Source excerpt

Learn how to use Spring AI SDK bindings to integrate with OpenAI providers, using Spring abstractions while automatically configuring the underlying client. The post Using the Official OpenAI Java SDK With Spring AI first appeared on Baeldung.

## Build autonomous AI agents with Amazon Bedrock and Spring AI

DevFeed: [Build autonomous AI agents with Amazon Bedrock and Spring AI](<https://devfeed.tech/articles/build-autonomous-ai-agents-with-amazon-bedrock-and-spring-ai-129758.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/build-autonomous-ai-agents-with-amazon-bedrock-and-spring-ai/>)

Author: Viquar Khan

Published: 2026-11-12T01:18:23Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Spring Framework](<https://devfeed.tech/topics/spring-framework.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>)

Tags: [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [aws](<https://devfeed.tech/tags/aws.md>), [build](<https://devfeed.tech/tags/build.md>), [conversation-memory](<https://devfeed.tech/tags/conversation-memory.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [java](<https://devfeed.tech/tags/java.md>), [memory](<https://devfeed.tech/tags/memory.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-orchestration](<https://devfeed.tech/tags/multi-agent-orchestration.md>), [production](<https://devfeed.tech/tags/production.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [tool-calling](<https://devfeed.tech/tags/tool-calling.md>)

### AI overview

The walkthrough shows how Java teams can build agents with Spring AI and Amazon Bedrock, then deploy them on Amazon Bedrock AgentCore. It presents a travel assistant with tool calling, streaming, and short- and long-term memory, plus an intelligent document processing system with five specialist agents, configurable rules, alerts, and human review. It explains the AgentCore `/invocations` and `/ping` contract, Spring AI tool and memory integration, and production patterns for retries, identity, guardrails, and observability. The base multi-agent design routes each document to one specialist and evaluates results; parallel fan-out is an optional extension, while the batch endpoint processes documents sequentially. Structured output is best-effort for the verified Claude Sonnet 4.5 example; stricter schema compliance requires native provider enforcement or Spring AI validation and retry. The post's guardrail pre-check is a demo, and distributed tracing and automated evaluation are described as extensions rather than implemented deployment features.

### Source excerpt

Learn how Java developers can build production-ready autonomous AI agents using Amazon Bedrock and Spring AI. This post walks through tool calling, conversation memory, resilience patterns, and multi-agent orchestration, then deploys the agent to AWS with Amazon Bedrock AgentCore.

## Spring AI 2.1.0-RC2 Available Now

DevFeed: [Spring AI 2.1.0-RC2 Available Now](<https://devfeed.tech/articles/spring-ai-2-1-0-rc2-available-now-122954.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/11/09/spring-ai-2-1-0-RC2-available-now>)

Author: dimitarproynov

Published: 2026-11-09T00:00:00Z

Content type: release

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [chat](<https://devfeed.tech/tags/chat.md>), [choice](<https://devfeed.tech/tags/choice.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [decisionmodel](<https://devfeed.tech/tags/decisionmodel.md>), [delta](<https://devfeed.tech/tags/delta.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [java-sdk](<https://devfeed.tech/tags/java-sdk.md>), [maven](<https://devfeed.tech/tags/maven.md>), [maven-central](<https://devfeed.tech/tags/maven-central.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-protocol](<https://devfeed.tech/tags/mcp-protocol.md>), [probability](<https://devfeed.tech/tags/probability.md>), [score](<https://devfeed.tech/tags/score.md>), [server](<https://devfeed.tech/tags/server.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

Spring AI 2.1.0-RC2 adds `DecisionModel` for typed yes/no, choice, and score responses with probabilities, letting applications set confidence thresholds; answers remain nondeterministic. Implementations include OpenAI, Ollama, and `TypeSafeClient`. New reranking and filtering features use decision calls, run per document over an executor, and fail open by default; the filter can fail closed. Tool argument deltas are exposed as partial `ToolCallPart`s for Anthropic, OpenAI, Bedrock Converse, and DeepSeek, while only the completed call is actionable or aggregated. User-supplied embedding upsert and search expand to five additional vector stores, though the excerpt does not name them. The MCP server adds protocol revision 2026-07-28 (`MODERN`), with synchronous support only; async mode fails at startup, and some existing context functions have no modern equivalent yet. Upgrade changes include removing deprecated Anthropic sampling settings rejected by its newer SDK, plus adjustments to streaming, Typesense, and token-usage behavior.

### Source excerpt

On behalf of the Spring AI team and everyone who has contributed, I'm happy to announce that Spring AI 2.1.0-RC2 has been released and is now available from Maven Central! Release notes | Upgrade notes | Reference documentation 2.1.0-RC2 builds on 2.1.0-RC1 and delivers DecisionModel, a new API for typed yes/no, choice and score decisions, together with the first things that are built on it. It also adds tool call delta streaming, extends the pre-computed embeddings support to five more vector stores, brings server support for the new MCP protocol revision, and upgrades to the Anthropic Java SDK 3.x. New in this release Decision Models Many decisions in an application have a small, known set of possible results: yes or no, one of a few categories, or a level on a scale. You could ask a chat model, but it answers with free text, and you must turn that text into a reliable result yourself. The new DecisionModel API is made for these decisions. You describe the possible results, and the model picks one and tells you how likely each result is, instead of generating text. It follows the shape of the other model APIs: a DecisionPrompt goes in, a DecisionResponse comes out, and DecisionOptions tune the call. A prompt holds an input (a text, a set of named fields, or a conversation) and one or more named questions: YesNoQuestion, answered with the probability of yes. ChoiceQuestion, answered with the selected option and, when the provider reports them, the probability of each option. ScoreQuestion, answered with a level of an ordered scale, such as unhappy, neutral, happy. DecisionResponse response = decisionModel.call(DecisionPrompt.builder() .text("My new headphones arrived yesterday, but the left side doesn't work. Can I get my money back?") .question("defect", YesNoQuestion.builder() .text("Does the customer report a defect?") .whenYes("Part of the item does not work as it should") .whenNo("The item works, and the message is about something else") .build()) .question("t

## Spring News Roundup: First Release Candidates of Boot, Framework, Data, Security, Modulith, AI

DevFeed: [Spring News Roundup: First Release Candidates of Boot, Framework, Data, Security, Modulith, AI](<https://devfeed.tech/articles/spring-news-roundup-first-release-candidates-of-boot-framework-data-security-modulith-ai-109944.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/spring-news-roundup-oct19-2026/>)

Author: Michael Redlich

Published: 2026-10-31T13:30:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Spring Framework](<https://devfeed.tech/topics/spring-framework.md>), [Spring Boot](<https://devfeed.tech/topics/spring-boot.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [backend frameworks](<https://devfeed.tech/topics/backend-frameworks.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [Security](<https://devfeed.tech/topics/security.md>), [Redis](<https://devfeed.tech/topics/redis.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amqp](<https://devfeed.tech/tags/amqp.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-kafka](<https://devfeed.tech/tags/apache-kafka.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data](<https://devfeed.tech/tags/data.md>), [development](<https://devfeed.tech/tags/development.md>), [docs](<https://devfeed.tech/tags/docs.md>), [first](<https://devfeed.tech/tags/first.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graphql](<https://devfeed.tech/tags/graphql.md>), [integration](<https://devfeed.tech/tags/integration.md>), [java](<https://devfeed.tech/tags/java.md>), [kafka](<https://devfeed.tech/tags/kafka.md>), [news](<https://devfeed.tech/tags/news.md>), [news-roundup](<https://devfeed.tech/tags/news-roundup.md>), [release](<https://devfeed.tech/tags/release.md>), [security](<https://devfeed.tech/tags/security.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-batch](<https://devfeed.tech/tags/spring-batch.md>), [spring-boot](<https://devfeed.tech/tags/spring-boot.md>), [spring-cloud](<https://devfeed.tech/tags/spring-cloud.md>), [spring-data](<https://devfeed.tech/tags/spring-data.md>), [spring-framework](<https://devfeed.tech/tags/spring-framework.md>), [spring-integration](<https://devfeed.tech/tags/spring-integration.md>), [spring-modulith](<https://devfeed.tech/tags/spring-modulith.md>), [spring-news-roundup-oct19-2026](<https://devfeed.tech/tags/spring-news-roundup-oct19-2026.md>), [spring-security](<https://devfeed.tech/tags/spring-security.md>), [spring-web-services](<https://devfeed.tech/tags/spring-web-services.md>)

### AI overview

The week of October 19, 2026 brought first release candidates across 17 Spring projects. The excerpt highlights practical changes: Boot 4.2.0 improves Uber-Jar lookup and switches its builder to Ubuntu Resolute; Framework 7.1.0 exposes retry state to listeners; Cloud 2026.0 folds Spring Cloud Bus into Spring Cloud Stream; and Modulith 2.2 distinguishes abandoned from failed event publications and completes publications within the listener transaction by default. Other examples include Spring AI replacing the deprecated `ChatMemory` interface with `SessionService`, Batch adding `@JobParameter` and `PageableItemReader`, and Web Services supporting policy documents on generated WSDL bindings. The roundup also lists bug fixes, documentation and dependency updates, and project-specific changes across Security, GraphQL, Session, Integration, HATEOAS, REST Docs, AMQP, Kafka, and LDAP. These are release candidates; the excerpt does not establish final release status.

### Source excerpt

There was a flurry of activity during the week of October 19th, 2026, highlighting: first release candidates of: Spring Boot, Spring Framework, Spring Data, Spring Cloud, Spring Security, Spring for GraphQL, Spring Session, Spring Integration, Spring HATEOS, Spring Modulith, Spring REST Docs, Spring AI, Spring Batch, Spring AMQP, Spring for Apache Kafka, Spring LDAP and Spring Web Services. By Michael Redlich

## Query Transformation in Spring AI Modular RAG

DevFeed: [Query Transformation in Spring AI Modular RAG](<https://devfeed.tech/articles/query-transformation-in-spring-ai-modular-rag-109194.md>)

Original publisher: [Read original article](<https://www.baeldung.com/spring-ai-rag-query-transformation>)

Author: Manfred Ng

Published: 2026-10-30T11:51:20Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [llm](<https://devfeed.tech/tags/llm.md>), [modular](<https://devfeed.tech/tags/modular.md>), [query](<https://devfeed.tech/tags/query.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-ai-llm](<https://devfeed.tech/tags/spring-ai-llm.md>), [transformation](<https://devfeed.tech/tags/transformation.md>)

### AI overview

Spring AI's modular RAG pipeline can transform a query before vector-store retrieval, where wording affects which documents match. RewriteQueryTransformer uses an LLM to remove irrelevant detail from verbose queries. TranslationQueryTransformer converts queries to the datastore's language; it leaves queries unchanged when they are already in the target language or the LLM cannot recognize them. CompressionQueryTransformer uses query history to resolve references such as "it," and can leave unrelated prior context out; applications must provide history, for example through a chat memory advisor. Transformers run in sequence, each needs a ChatClient.Builder and makes an additional LLM call, increasing latency. The excerpt recommends a low temperature such as 0.0 for more deterministic rewrites and enabling only transformers that are needed.

### Source excerpt

Learn how to set up query transformation in Spring AI for retrieval augmented generation. The post Query Transformation in Spring AI Modular RAG first appeared on Baeldung.

## Spring AI 2.1 Message Parts: Reasoning That Survives the Round Trip

DevFeed: [Spring AI 2.1 Message Parts: Reasoning That Survives the Round Trip](<https://devfeed.tech/articles/spring-ai-2-1-message-parts-reasoning-that-survives-the-round-trip-104419.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/28/spring-ai-message-parts-reasoning-replay>)

Author: dimitarproynov

Published: 2026-10-28T00:00:00Z

Content type: article

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [function calling](<https://devfeed.tech/topics/function-calling.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [batch](<https://devfeed.tech/tags/batch.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [genai](<https://devfeed.tech/tags/genai.md>), [google](<https://devfeed.tech/tags/google.md>), [java](<https://devfeed.tech/tags/java.md>), [message](<https://devfeed.tech/tags/message.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [openai](<https://devfeed.tech/tags/openai.md>), [order](<https://devfeed.tech/tags/order.md>), [parts](<https://devfeed.tech/tags/parts.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reasoning-models](<https://devfeed.tech/tags/reasoning-models.md>), [responses](<https://devfeed.tech/tags/responses.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [text](<https://devfeed.tech/tags/text.md>), [thinking](<https://devfeed.tech/tags/thinking.md>), [thought](<https://devfeed.tech/tags/thought.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1 replaces messages' text-plus-side-lists model with ordered message parts, preserving reasoning, tool calls, media and provider payloads across requests and streaming. The key rules are to keep parts in order, replay each provider's payload unchanged, and persist parts rather than text. This matters because providers impose different requirements: Anthropic and Gemini can reject missing or altered thinking signatures; OpenAI Responses requires prior reasoning items and tool exchanges for replay; DeepSeek and Mistral require reasoning in certain tool loops. Cross-provider histories retain text and tool calls but do not forward another provider's signed reasoning. Spring AI Session stores complete parts and tool-loop rounds as JSON, while the older JDBC chat-memory repository stores only text and drops tool calls and results. Earlier histories lack reasoning parts, and custom storage must retain part attributes for Mistral and unsigned Bedrock reasoning replay.

### Source excerpt

Spring AI: Message Parts Doc | Upgrade Notes | OpenAI Responses Doc | Session Doc Reasoning models do more than think before they answer. They hand part of that thinking back to you and expect to get it back on the next request. Claude signs its thinking blocks. Gemini attaches thought signatures to its function calls. OpenAI's Responses API returns encrypted reasoning items. If you drop, reorder or edit them, the result ranges from an HTTP 400 to a model that quietly loses its earlier reasoning and starts over. Until now, a Spring AI message was a piece of text with side lists of tool calls and media. There was no place for that data, let alone its order. Spring AI 2.1 changes the data model itself: every message now holds its content as an ordered list of message parts. A part is one piece of a response, such as a run of text, a block of reasoning or a tool call. Providers call these pieces content blocks (Anthropic, Bedrock), parts (Gemini), items (OpenAI Responses) or chunks (Mistral), and Spring AI maps them all to message parts. With the 2.1.0-RC1 release candidate, the major chat models produce and consume parts: OpenAI Responses, Anthropic, Google GenAI, OpenAI Chat Completions, Ollama, Bedrock Converse, DeepSeek and Mistral AI. The release also adds Session memory, which persists them. This post covers the new abstraction, why the Responses API needed it, and what each chat model gains. It comes down to three rules: keep the order, replay what you were given verbatim, and persist the parts, not the text. Why a String Was Not Enough Here is what Claude, with thinking enabled, returns in a single tool-calling round: thinking "The user wants the weather in Paris. I should call get_weather..." signature: "EqQBCgIYAhIM..." text "Let me check that for you." tool_use get_weather {"location": "Paris"} When you send the tool result, Anthropic wants this turn back exactly as it was: same blocks, same order, signature included. Before 2.1, AssistantMessage could not d

## Using Your Own Embeddings in Spring AI 2.1

DevFeed: [Using Your Own Embeddings in Spring AI 2.1](<https://devfeed.tech/articles/using-your-own-embeddings-in-spring-ai-2-1-106228.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/28/spring-ai-upsert-own-embeddings>)

Author: sobychacko

Published: 2026-10-28T00:00:00Z

Content type: article

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [audio](<https://devfeed.tech/tags/audio.md>), [batch](<https://devfeed.tech/tags/batch.md>), [batch-api](<https://devfeed.tech/tags/batch-api.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [database](<https://devfeed.tech/tags/database.md>), [database-migration](<https://devfeed.tech/tags/database-migration.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embedding-model](<https://devfeed.tech/tags/embedding-model.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [ids](<https://devfeed.tech/tags/ids.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [java](<https://devfeed.tech/tags/java.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [search](<https://devfeed.tech/tags/search.md>), [searching](<https://devfeed.tech/tags/searching.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [text-embeddings](<https://devfeed.tech/tags/text-embeddings.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [video](<https://devfeed.tech/tags/video.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1 adds `upsert` for storing documents with application-supplied embeddings and a `similaritySearch` overload that accepts a query vector, bypassing the vector store's configured embedding model. This supports multimodal search, such as matching text queries to product photos, and reuse of existing text embeddings. Use a compatible model for indexed content and queries, configure dimensions to match the store, and keep stable document IDs so upserts replace records. Documents must still provide persistable text, metadata, and vectors; media itself remains external. The APIs are opt-in and throw `UnsupportedOperationException` in stores that do not implement them. As of Spring AI 2.1.0-RC1, PGvector, Redis, Elasticsearch, Qdrant, and OpenSearch support both operations. Writes in one upsert call are not guaranteed transactional; Redis also requires a readable or configured expected dimension to prevent invalid-sized vectors from being saved but omitted from search.

### Source excerpt

VectorStore.add() takes text documents, generates embeddings with the store's configured model, and saves both. Spring AI 2.1 adds upsert for applications that already have embeddings or generate them from images, video, or audio. It accepts documents paired with application-supplied vectors, without calling the store's embedding model. A new similaritySearch overload also accepts a query embedding, giving applications control over both indexing and searching. When to supply your own embeddings Let's look at a real-world example. Consider a furniture catalog with a product listed as "Armchair, model A42". Its photo shows green velvet upholstery and wooden legs, but a search for "green velvet armchair" could miss it if those details are absent from the description. A multimodal embedding model produces image and text embeddings that can be compared directly, letting the search match the customer's words to the photo. The application stores photo embeddings with upsert, then embeds search text with the same model to find the closest matches. Video or audio search works similarly if the model supports comparing that content with text queries. For example, store an embedding for a training video segment about replacing a filter (04:00 to 04:30), with the video URL and start and end times in metadata. A search for "how to replace the filter" can then return a result that the application opens at 04:00. Existing text embeddings benefit too, whether they come from a provider's batch API, another team, or a database migration. add() would generate them again. Writing directly to the database avoids that, but requires matching Spring AI's field names and formats for IDs, text, metadata, and vectors so it can read and search the records. upsert handles that storage format for you. Indexing product images For the furniture catalog, let's assume that we are using Spring AI's VertexAiMultimodalEmbeddingModel, which supports text, images, and video. The examples below use these t

## Spring Office Hours Podcast: S5E27 - Hugging Face for Java Developers with Pratik Patel

DevFeed: [Spring Office Hours Podcast: S5E27 - Hugging Face for Java Developers with Pratik Patel](<https://devfeed.tech/articles/spring-office-hours-podcast-s5e27-hugging-face-for-java-developers-with-pratik-patel-102189.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/26/spring-office-hours-podcast-S5E27>)

Author: danvega

Published: 2026-10-26T00:00:00Z

Content type: article

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [developers](<https://devfeed.tech/tags/developers.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [java](<https://devfeed.tech/tags/java.md>), [live-stream](<https://devfeed.tech/tags/live-stream.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [open](<https://devfeed.tech/tags/open.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

The episode introduces Hugging Face to Java developers and covers how to find an open model, ways to run open models from Java, and when an open model may be preferable to a paid API. Dan Vega and DaShaun Carter discuss these topics with Java Champion Pratik Patel. The supplied text gives the episode's topics but not the specific tools, comparisons, or recommendations discussed.

### Source excerpt

Join Dan Vega and DaShaun Carter for the latest updates from the Spring Ecosystem. In this episode, Dan and DaShaun are joined by Java Champion Pratik Patel to talk about Hugging Face for Java developers. Hugging Face hosts over a million open models, but most Java developers have never used one. They discuss what Hugging Face actually is, how to find a model worth using, the ways you can run open models from Java today, and when an open model beats a paid API. You can participate in our live stream to ask questions or catch the replay on your preferred podcast platform. Show Notes Pratik Patel on X and LinkedIn Devnexus 2027 Hugging Face Hugging Face Inference Endpoints Spring AI: OpenAI Chat (works with any OpenAI-compatible endpoint) Big Data and AI workshop (Spring Boot, Spring AI, Spark, Iceberg) RTX 5090 vs M5 Ultra: Which AI Powerhouse Wins? (video) Hands-on with Hugging Face Buckets and Xet llama.cpp oMLX: LLM inference for Apple Silicon The show: springofficehours.io - episodes, schedule, community Spring Developer on YouTube - join us live every Monday Dan Vega DaShaun Carter The Spring Blog - the news we cover each week

## Spring AI 2.1.0-RC1 and 2.0.2 Available Now

DevFeed: [Spring AI 2.1.0-RC1 and 2.0.2 Available Now](<https://devfeed.tech/articles/spring-ai-2-1-0-rc1-and-2-0-2-available-now-97730.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/23/spring-ai-2-1-0-RC1-available-now>)

Author: ebottard

Published: 2026-10-23T00:00:00Z

Content type: release

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [releases](<https://devfeed.tech/topics/releases.md>)

Tags: [accessors](<https://devfeed.tech/tags/accessors.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [also](<https://devfeed.tech/tags/also.md>), [announce](<https://devfeed.tech/tags/announce.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [batch](<https://devfeed.tech/tags/batch.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [boot](<https://devfeed.tech/tags/boot.md>), [builder](<https://devfeed.tech/tags/builder.md>), [builds](<https://devfeed.tech/tags/builds.md>), [call](<https://devfeed.tech/tags/call.md>), [central](<https://devfeed.tech/tags/central.md>), [chat](<https://devfeed.tech/tags/chat.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [code](<https://devfeed.tech/tags/code.md>), [content](<https://devfeed.tech/tags/content.md>), [contributed](<https://devfeed.tech/tags/contributed.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [java](<https://devfeed.tech/tags/java.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1.0-RC1 adds native message-part support across major chat providers, built-in session memory, tool-call confirmation, and vector search using a caller-supplied query embedding; 2.0.2 fixes are included. Session memory stores an append-only event log and builds a compacted view, cutting only at turn boundaries; JDBC repositories support PostgreSQL, MySQL, MariaDB, and H2, and callers must provide a session ID on every call. Existing chat-memory APIs are deprecated for removal in 3.0.0, with some replacement dialects still planned. Confirmation pauses tool execution until the application allows or denies each call, with policies based on metadata, named tools, or arguments. Query-vector search leaves the embedding model unused and is implemented by pgvector, Qdrant, Redis, Elasticsearch, and OpenSearch; unsupported stores fail fast, and OpenSearch upsert requires managed document IDs. The release also preserves provider-specific reasoning payloads, with replay configurable for OpenAI-compatible endpoints because some require it and others reject it.

### Source excerpt

On behalf of the Spring AI team and everyone who has contributed, I'm happy to announce that Spring AI 2.1.0-RC1 and 2.0.2 have been released and are now available from Maven Central! Release notes | Upgrade notes | Reference documentation 2.1.0-RC1 builds on 2.1.0-M1 and delivers most of what we promised in its "What's next" section: message parts are now produced and consumed natively by the major chat models, and session memory arrives in Spring AI itself. It also adds tool call confirmation, and extends the pre-computed embeddings support with search by query vector. New in this release Message Parts across providers In M1, only OpenAiResponsesChatModel worked natively with MessagePart content. In this release the following ChatModel implementations produce and consume parts as well: OpenAI (Chat Completions) Anthropic Google GenAI Amazon Bedrock Converse Ollama Mistral AI DeepSeek Reasoning, tool calls, and provider-specific blocks therefore keep their order and their opaque payloads, such as Anthropic thinking signatures and Gemini thought signatures, across a whole conversation. Code that uses the existing accessors (getText(), getToolCalls(), ...) keeps working. The message builders' setters now replace parts in place, so UserMessage.builder().text(...) followed by another call no longer leaves stale parts behind. Two related details for OpenAI-compatible endpoints. reasoning_content is echoed back on assistant messages because some endpoints, such as DeepSeek in thinking mode, require it, while others, such as Groq, reject it. Replaying is now configurable with spring.ai.openai.chat.replay-reasoning-content (or OpenAiChatOptions.replayReasoningContent); it keeps sending the property by default, and false turns it off. And on the Responses API, the order of the parts of a user message is preserved, and file URLs are sent as file_url. Session Memory ChatMemory stores a flat list of messages per conversation id. Long-running conversations and agents need more

## Consistent LLM Call Handling Across Java Frameworks: A Reference Implementation and Benchmark

DevFeed: [Consistent LLM Call Handling Across Java Frameworks: A Reference Implementation and Benchmark](<https://devfeed.tech/articles/consistent-llm-call-handling-across-java-frameworks-a-reference-implementation-and-benchmark-93489.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.25480>)

Author: Oleksandr Klymenko

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [langchain4j](<https://devfeed.tech/topics/langchain4j.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Java HttpClient](<https://devfeed.tech/topics/java-httpclient.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [java](<https://devfeed.tech/tags/java.md>), [llm](<https://devfeed.tech/tags/llm.md>)

### AI overview

The benchmark finds different reliability-contract results for Spring AI 2.0.1 and LangChain4j 1.21.0: across scripted synchronous and streaming failures, Spring AI met the contract in 72/77 applicable default cases (76/83 explicitly configured), while LangChain4j met it in 47/77 (51/83). Both treated streams missing their terminator as complete answers. A shared HTTP-boundary implementation--a 725-line JDK and Micrometer Observation API core with framework-specific adapters--made Spring AI, LangChain4j, and a no-framework client behave identically and satisfy 90/91 cases. The remaining case reflects a trade-off between retrying a hung provider and waiting for a slow first token. Against a local model server, it rejected none of 700 calls and added median latency of 32-217 microseconds.

### Source excerpt

arXiv:2610.25480v1 Announce Type: new Abstract: Java applications reach large language models (LLMs) through an integration framework, and rely on it to handle a failing provider: to retry what can be retried and nothing else, to wait as long as the provider asks, never to present a truncated answer as complete, and to record each failure in the application's metrics. We state these expectations as a six-clause reliability contract and measure Spring AI 2.0.1 and LangChain4j 1.21.0 against it with a scripted OpenAI-compatible provider: fifteen failure scenarios, synchronous and streaming, three repetitions. LangChain4j meets it in 47 of 77 applicable cases with its defaults and in 51 of 83 when configured explicitly, Spring AI in 72 of 77 and 76 of 83; both deliver a stream that ended without its terminator as a complete answer. We then place one implementation of the contract beneath both frameworks, at the HTTP boundary - an OkHttp interceptor for Spring AI, an HttpClient for LangChain4j, and a java.net.http transport for code without a framework - sharing a 725-line core that depends only on the JDK and the Micrometer Observation API. With it, all three clients behave identically and meet the contract in 90 of 91 cases; the remaining case is a policy trade-off between retrying a hung provider and waiting for a slow first token. Against a local model server the layer rejected none of 700 calls, and it adds a median of 32-217 microseconds to a call.

## Spring Office Hours Podcast: S5E26 - dev2Next, Native JSON and a Week of New Models

DevFeed: [Spring Office Hours Podcast: S5E26 - dev2Next, Native JSON and a Week of New Models](<https://devfeed.tech/articles/spring-office-hours-podcast-s5e26-dev2next-native-json-and-a-week-of-new-models-91331.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/19/spring-office-hours-podcast-S5E26>)

Author: danvega

Published: 2026-10-19T00:00:00Z

Content type: article

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [JSON](<https://devfeed.tech/topics/json.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intellij](<https://devfeed.tech/tags/intellij.md>), [java](<https://devfeed.tech/tags/java.md>), [jdk](<https://devfeed.tech/tags/jdk.md>), [jdk-28](<https://devfeed.tech/tags/jdk-28.md>), [json](<https://devfeed.tech/tags/json.md>), [local-inference](<https://devfeed.tech/tags/local-inference.md>), [meta](<https://devfeed.tech/tags/meta.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [muse](<https://devfeed.tech/tags/muse.md>), [muse-spark-open](<https://devfeed.tech/tags/muse-spark-open.md>), [native](<https://devfeed.tech/tags/native.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [office-hours](<https://devfeed.tech/tags/office-hours.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [questions](<https://devfeed.tech/tags/questions.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

The episode recaps Dev2Next, showcases Kiln, a warm IntelliJ theme, and demos of the JSON API planned for JDK 28. It also covers recent model releases: Meta's Muse Spark Open weights, NVIDIA fitting a 74B model into 24GB, and DeepSeek's faster V4.1 Flash. The hosts discuss the tradeoff between increasingly practical local inference and rising RAM and VRAM prices, including when running models on personal hardware may make sense and how to connect Spring AI to a local model. They also take live questions.

### Source excerpt

Join Dan Vega and DaShaun Carter for the latest from the Spring ecosystem. We're back from Dev2Next with a recap. Dan shows off two things he built last week. One is Kiln, a warm new theme for IntelliJ. The other is a set of demos for the JSON API coming to JDK 28. Then we dig into a busy week of model releases. Meta released the weights for Muse Spark Open, NVIDIA fit a 74B model into 24GB, and DeepSeek shipped a faster V4.1 Flash. Local inference is getting real, but RAM and VRAM prices keep climbing. We'll talk about when running models on your own hardware makes sense, and how to point Spring AI at a model on your own machine. We'll also answer your questions live. Show Notes dev2next Conference Spring AI: There and Back Again (demo code) ArchUnit JEP 540: Simple JSON API (Incubator) Native JSON demos for JDK 28 Kiln: a warm theme for JetBrains IDEs Spring AI Evaluation Testing Spring AI Recipes by Craig Walls The show: springofficehours.io - episodes, schedule, community Spring Developer on YouTube - join us live every Monday Dan Vega DaShaun Carter The Spring Blog - the news we cover each week

## Safeguarding LLM Output in Spring AI

DevFeed: [Safeguarding LLM Output in Spring AI](<https://devfeed.tech/articles/safeguarding-llm-output-in-spring-ai-89790.md>)

Original publisher: [Read original article](<https://www.baeldung.com/spring-ai-safeguarding-llm-output>)

Author: Yadier Betancourt

Published: 2026-10-18T17:55:03Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Spring Framework](<https://devfeed.tech/topics/spring-framework.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Spring MVC](<https://devfeed.tech/topics/spring-mvc.md>), [console](<https://devfeed.tech/topics/console.md>), [Maven](<https://devfeed.tech/topics/maven.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-spring-ai-chatclient](<https://devfeed.tech/tags/artificial-intelligence-spring-ai-chatclient.md>), [developer](<https://devfeed.tech/tags/developer.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-api](<https://devfeed.tech/tags/gemini-api.md>), [google](<https://devfeed.tech/tags/google.md>), [guardrail](<https://devfeed.tech/tags/guardrail.md>), [guards](<https://devfeed.tech/tags/guards.md>), [implementing](<https://devfeed.tech/tags/implementing.md>), [llm](<https://devfeed.tech/tags/llm.md>), [popular](<https://devfeed.tech/tags/popular.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-ai-chatclient](<https://devfeed.tech/tags/spring-ai-chatclient.md>)

### AI overview

This tutorial shows how to add an output guard to a Spring AI ChatClient. It builds a custom advisor that checks model responses for sensitive terms and replaces matching answers, complementing Spring AI's input guard. The article explains the substring matching limitations and notes that streamed responses bypass this call-only guard.

### Source excerpt

Learn to create a custom advisor that inspects the model's response before Spring AI ChatClient hands it back to the user. The post Safeguarding LLM Output in Spring AI first appeared on Baeldung.

## This Week in Spring - October 13th, 2026

DevFeed: [This Week in Spring - October 13th, 2026](<https://devfeed.tech/articles/this-week-in-spring-october-13th-2026-86662.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/13/this-week-in-spring-october-13th-2026>)

Author: joshlong

Published: 2026-10-13T00:00:00Z

Content type: article

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [modular-monolith](<https://devfeed.tech/topics/modular-monolith.md>), [Spring Boot](<https://devfeed.tech/topics/spring-boot.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [application](<https://devfeed.tech/tags/application.md>), [approach](<https://devfeed.tech/tags/approach.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [intellij](<https://devfeed.tech/tags/intellij.md>), [intellij-idea](<https://devfeed.tech/tags/intellij-idea.md>), [java](<https://devfeed.tech/tags/java.md>), [jenkins](<https://devfeed.tech/tags/jenkins.md>), [jobrunr](<https://devfeed.tech/tags/jobrunr.md>), [layers](<https://devfeed.tech/tags/layers.md>), [learning](<https://devfeed.tech/tags/learning.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-boot](<https://devfeed.tech/tags/spring-boot.md>), [tool-calling](<https://devfeed.tech/tags/tool-calling.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

This roundup highlights JobRunr 9 features for identifying failed steps and slow jobs, stopping runs without losing work, and starting jobs within milliseconds. It favors Spring Modulith's feature-based organization over traditional layered Spring Boot packages. Other items include a Spring learning roadmap, Progen CLI application scaffolding, IntelliJ IDEA features, Spring AI agentic patterns and tool calling, and a Bootiful Podcast conversation with Jenkins creator Kohsuke Kawaguchi.

### Source excerpt

Hi, Spring fans! Welcome to another rip-roarin' installment of This Week in Spring! This one I am writing from beautiful Carmel-by-the-Sea in sunny California's Bay Area, overlooking the Pacific Ocean. As I sit here, I'm enjoying a cup of coffee and bemusedly enjoying the amazing content in this week's roundup. We've got a ton of stuff to dive into, so let's do it! Have you seen the new features in Jobrunr 9? You can easily see which step failed, find the job behind a slowdown, stop a job run without losing work, and start jobs within milliseconds. It's awesome! (And it's on the Spring Initializr, too)! The GeeksforGeeks.org blog has a post about structuring a Spring Boot application and its packages. Unfortunately, it describes the traditional layered approach to architecture, and this is exactly how I would not layer my application. Instead, prefer Spring Modulith's approach, which allows you to rotate your layers 90 degrees and group things by feature, not by architectural layer. I don't know if I agree with everything in this roadmap on learning Spring, but I do like that somebody's tried to document it. An interesting watch by SivaLabs on scaffolding applications with Progen CLI Speaking of Siva, I was happy to sit with him and do a joint video looking at some of the new features in IntelliJ IDEA at the recent IntelliJ IDEA conf. A ton of fun, as always, and I hope you get something out of it At the same show, my friend and Spring AI lead Christian Tsolov looked at agentic patterns and tool calling with Spring AI - super interesting watch! I was thrilled to sit with legendary Java luminary Kohsuke Kawaguchi (creator of Jenkins!) and catch up in last week's installment of A Bootiful Podcast!

## Building Graph-Based Workflows With Spring AI Alibaba

DevFeed: [Building Graph-Based Workflows With Spring AI Alibaba](<https://devfeed.tech/articles/building-graph-based-workflows-with-spring-ai-alibaba-84350.md>)

Original publisher: [Read original article](<https://www.baeldung.com/spring-ai-alibaba-graph-based-workflows>)

Author: Hardik Singh Behl

Published: 2026-10-10T01:04:27Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-spring-ai-chatclient](<https://devfeed.tech/tags/artificial-intelligence-spring-ai-chatclient.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [popular](<https://devfeed.tech/tags/popular.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-ai-chatclient](<https://devfeed.tech/tags/spring-ai-chatclient.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

This tutorial demonstrates how to build a graph-based agentic workflow with Spring AI Alibaba. It defines shared state, LLM-powered nodes, and conditional edges, then connects them into a workflow that can repeat or stop based on the manager node's rating and a maximum attempt limit.

### Source excerpt

Learn how to use Spring AI Alibaba to implement and maintain your prompt orchestration logic. The post Building Graph-Based Workflows With Spring AI Alibaba first appeared on Baeldung.

## Spring AI Modular RAG and TypeSafe Jev: Retrieve More, Keep Only What Answers

DevFeed: [Spring AI Modular RAG and TypeSafe Jev: Retrieve More, Keep Only What Answers](<https://devfeed.tech/articles/spring-ai-modular-rag-and-typesafe-jev-retrieve-more-keep-only-what-answers-63834.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/10/02/spring-ai-modular-rag-typesafe-jev>)

Author: tzolov

Published: 2026-10-02T00:00:00Z

Content type: article

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [java](<https://devfeed.tech/tags/java.md>), [jev](<https://devfeed.tech/tags/jev.md>), [llm](<https://devfeed.tech/tags/llm.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [modular](<https://devfeed.tech/tags/modular.md>), [naive-rag](<https://devfeed.tech/tags/naive-rag.md>), [pdf](<https://devfeed.tech/tags/pdf.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [rag](<https://devfeed.tech/tags/rag.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [typesafe](<https://devfeed.tech/tags/typesafe.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

The example combines Spring AI's Modular RAG pipeline with Jev to turn a chatty question into focused searches and keep retrieved passages that can answer it. `RetrievalAugmentationAdvisor` rewrites and expands the query, retrieves and deduplicates similar chunks, then applies `JevDocumentFilter` before `JevDocumentReranker`; the original question remains the input to post-processing and answer generation. In the Hurricane Milton demo, six retrieved chunks included reference entries that were topically similar but unhelpful. Jev filtered those out and kept two answer-bearing chunks, producing a response that Milton made landfall near Siesta Key on October 9, 2024, as a Category 3 hurricane. The filter preserves contradictory evidence, and both Jev stages fail open if the API is unreachable. The pipeline adds two LLM calls before retrieval and one Jev call per retrieved chunk, so the article advises measuring latency. It also notes that supplying Spring's `TaskExecutor` prevents a command-line app from hanging after output.

### Source excerpt

Spring AI: RAG Doc | Jev Doc | Demo In the previous article we introduced Spring AI TypeSafe and its Jev model: typed questions in, calibrated numbers out, in a few hundred milliseconds. One row in that article's SPI table deserves its own post. JevDocumentFilter and JevDocumentReranker are DocumentPostProcessors, which means they plug straight into Spring AI's Modular RAG pipeline. This article puts the two together. Two LLM calls clean up and multiply the user's question before retrieval. Jev then judges every retrieved chunk before it reaches the prompt. The whole pipeline is one advisor builder. 💡 Demo: The complete example is the 05-1-modular-rag module. It sits next to 05-rag, the naive version, so you can diff the two. Every output quoted below is from a live run. Why Naive RAG Falls Short The classic Spring AI RAG demo is a QuestionAnswerAdvisor over a vector store. It embeds the user's text, fetches similar chunks and stuffs them into the prompt. That works on stage and gets shaky in real life, for three reasons: Users don't type search queries. They type "I'm a Florida resident and heard a lot about storms last fall. Did Milton actually make landfall in my state, and where?" Embedding that verbatim drags all the noise into the search. Similar is not the same as useful. A vector store returns chunks that are about the topic. A reference list that mentions "Hurricane Milton" five times scores high and answers nothing. Retrieved text is untrusted input. Whatever sits in your documents goes straight into the prompt, including text written to hijack the model. We will answer exactly that question over a Wikipedia PDF about Hurricane Milton, and fix each problem with one pluggable component. Modular RAG in Spring AI The RetrievalAugmentationAdvisor, from the spring-ai-rag module, implements the architecture described in Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks. From the outside it is just another advisor: it sits between you

## Spring News Roundup: Second Milestone Releases of Boot, Framework, Data, Security, Integration

DevFeed: [Spring News Roundup: Second Milestone Releases of Boot, Framework, Data, Security, Integration](<https://devfeed.tech/articles/spring-news-roundup-second-milestone-releases-of-boot-framework-data-security-integration-61646.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/09/spring-news-roundup-sep21-2026/>)

Author: Michael Redlich

Published: 2026-09-29T12:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Spring Boot](<https://devfeed.tech/topics/spring-boot.md>), [releases](<https://devfeed.tech/topics/releases.md>), [Spring Framework](<https://devfeed.tech/topics/spring-framework.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>)

Tags: [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [boot](<https://devfeed.tech/tags/boot.md>), [development](<https://devfeed.tech/tags/development.md>), [java](<https://devfeed.tech/tags/java.md>), [news](<https://devfeed.tech/tags/news.md>), [release](<https://devfeed.tech/tags/release.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-batch](<https://devfeed.tech/tags/spring-batch.md>), [spring-boot](<https://devfeed.tech/tags/spring-boot.md>), [spring-cloud](<https://devfeed.tech/tags/spring-cloud.md>), [spring-data](<https://devfeed.tech/tags/spring-data.md>), [spring-framework](<https://devfeed.tech/tags/spring-framework.md>), [spring-integration](<https://devfeed.tech/tags/spring-integration.md>), [spring-news-roundup-sep21-2026](<https://devfeed.tech/tags/spring-news-roundup-sep21-2026.md>), [spring-security](<https://devfeed.tech/tags/spring-security.md>), [spring-web-services](<https://devfeed.tech/tags/spring-web-services.md>)

### AI overview

The roundup covers milestone releases during the week of September 21, 2026, across Spring projects. It highlights second milestones for projects including Spring Boot, Spring Framework, Spring Data, Spring Security and Spring Integration, along with first milestones for Spring AI, Spring Cloud and other projects.

### Source excerpt

There was a flurry of activity during the week of September 21st, 2026, highlighting: second milestone releases of: Spring Boot, Spring Batch, Spring Security, Spring AMQP, Spring Integration, Spring Data, Spring Framework, Spring for GraphQL and Spring for Apache Kafka. There were also first milestone releases of Spring AI, Spring Cloud, Spring Web Services and Spring LDAP. By Michael Redlich

## This Week in Spring - September 29th, 2026

DevFeed: [This Week in Spring - September 29th, 2026](<https://devfeed.tech/articles/this-week-in-spring-september-29th-2026-62144.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/09/29/this-week-in-spring-september-29th-2026>)

Author: joshlong

Published: 2026-09-29T00:00:00Z

Content type: news

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring Framework](<https://devfeed.tech/topics/spring-framework.md>), [Spring Boot](<https://devfeed.tech/topics/spring-boot.md>), [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amqp](<https://devfeed.tech/tags/amqp.md>), [batch](<https://devfeed.tech/tags/batch.md>), [boot](<https://devfeed.tech/tags/boot.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data](<https://devfeed.tech/tags/data.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [integration](<https://devfeed.tech/tags/integration.md>), [java](<https://devfeed.tech/tags/java.md>), [ldap](<https://devfeed.tech/tags/ldap.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [security](<https://devfeed.tech/tags/security.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-batch](<https://devfeed.tech/tags/spring-batch.md>), [spring-boot](<https://devfeed.tech/tags/spring-boot.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

The September 24 releases include Spring Boot 4.2.0 M2, which adds SSL bundle support for LDAP (including LDAPS for the embedded LDAP server), OpenTelemetry semantic conventions, and shared OTLP endpoint, header, and compression configuration. The roundup also lists milestone releases for Spring AI, Spring Data, Spring Integration, Spring AMQP, Spring Web Services, Spring Security, Spring Cloud (2026.0.0-M1, "Paddington"), and Spring Batch. It mentions a post on using Spring AI with TypeSafe.AI's Jev model and a podcast discussion of data optimization for agentic workflows. The excerpt says Jev is very cheap but provides no further detail.

### Source excerpt

Hi, Spring fans! Welcome to another rip-roarin' and exciting installment of This Week in Spring! We've got a ton of cool stuff to look at this week, so let's dive right into it! an important update on Spring's release practice Speaking of which, we had a slew of releases on the 24th, including Spring Boot 4.2.0 M2. This release brings with it SSL bundle support for LDAP, including LDAPS support for the embedded LDAP server, support for OpenTelemetry's semantic conventions, along with common OTLP endpoint, header, and compression configuration, and so much more. Spring AI 2.1.0 M1 is available now Spring Data 2026.1.0-M2 is released Spring Integration 7.2.0 M2 released Spring AMQP 4.2.0 M2 Spring Web Services 5.1.0 M1 available now Spring Security 7.2.0-M2 available now Spring Cloud 2026.0.0-M1 (aka Paddington) has been released Spring Batch 6.1.0-M2 is out Spring Boot 4.2.0-M2 available now Spring AI lead Christian Tsolov has a wonderful post looking at how to wield Spring AI and the new TypeSafe.AI "Jev" model. Jev, if you didn't know, is a model that does very cheap In last week's installment, we had Michael Carducci on a Bootiful Podcast to talk about optimizing data for agentic workflows I loved this talk from Moritz Halbritter on upgrading Spring Boot 4 (and the internal work behind it) from this year's Spring IO

## A Guide to Structured Output in Spring AI

DevFeed: [A Guide to Structured Output in Spring AI](<https://devfeed.tech/articles/a-guide-to-structured-output-in-spring-ai-59802.md>)

Original publisher: [Read original article](<https://www.baeldung.com/spring-ai-structured-output>)

Author: Hardik Singh Behl

Published: 2026-09-25T05:15:12Z

Content type: tutorial

Language: en

Sources: [Baeldung](<https://devfeed.tech/sources/baeldung.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Java](<https://devfeed.tech/topics/java.md>), [JSON Schema](<https://devfeed.tech/topics/json-schema.md>), [OpenAI API](<https://devfeed.tech/topics/openai-api.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-llm-spring-ai-chatclient](<https://devfeed.tech/tags/artificial-intelligence-llm-spring-ai-chatclient.md>), [guide](<https://devfeed.tech/tags/guide.md>), [java](<https://devfeed.tech/tags/java.md>), [json](<https://devfeed.tech/tags/json.md>), [json-schema](<https://devfeed.tech/tags/json-schema.md>), [llm](<https://devfeed.tech/tags/llm.md>), [openai](<https://devfeed.tech/tags/openai.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [spring-ai-chatclient](<https://devfeed.tech/tags/spring-ai-chatclient.md>), [structured-output](<https://devfeed.tech/tags/structured-output.md>)

### AI overview

A tutorial on using Spring AI to receive structured output from large language models and map responses directly to Java classes, collections, and other domain types. It covers configuring a chat model, defining entities, and converting responses without handwritten parsing logic.

### Source excerpt

Learn how to receive structured output from LLMs with Spring AI. The post A Guide to Structured Output in Spring AI first appeared on Baeldung.

## Spring AI 2.1.0-M1 Available Now

DevFeed: [Spring AI 2.1.0-M1 Available Now](<https://devfeed.tech/articles/spring-ai-2-1-0-m1-available-now-59815.md>)

Original publisher: [Read original article](<https://spring.io/blog/2026/09/25/spring-ai-2-1-0-M1-available-now>)

Author: tzolov

Published: 2026-09-25T00:00:00Z

Content type: release

Language: en

Sources: [Spring](<https://devfeed.tech/sources/spring.md>)

Topics: [Spring AI](<https://devfeed.tech/topics/spring-ai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Spring Boot](<https://devfeed.tech/topics/spring-boot.md>)

Tags: [accessors](<https://devfeed.tech/tags/accessors.md>), [adapter](<https://devfeed.tech/tags/adapter.md>), [ai](<https://devfeed.tech/tags/ai.md>), [announce](<https://devfeed.tech/tags/announce.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [batch](<https://devfeed.tech/tags/batch.md>), [block](<https://devfeed.tech/tags/block.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [boot](<https://devfeed.tech/tags/boot.md>), [builder](<https://devfeed.tech/tags/builder.md>), [builds](<https://devfeed.tech/tags/builds.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [central](<https://devfeed.tech/tags/central.md>), [change](<https://devfeed.tech/tags/change.md>), [charts](<https://devfeed.tech/tags/charts.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [java](<https://devfeed.tech/tags/java.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [reactive](<https://devfeed.tech/tags/reactive.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [spring](<https://devfeed.tech/tags/spring.md>), [spring-ai](<https://devfeed.tech/tags/spring-ai.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

Spring AI 2.1.0-M1, the first milestone in the 2.1 line, builds on 2.0.1 and moves to Spring Boot 4.2 (built against 4.2.0-M2). It adds ordered message parts to preserve interleaved text, reasoning, tools and media, including opaque provider payloads and unknown blocks; in this milestone, only OpenAiResponsesChatModel handles parts natively. That model adds OpenAI's Responses endpoint alongside the existing Chat Completions model, with reasoning and tool support, but persistent chat memory repositories do not yet preserve message parts; InMemoryChatMemoryRepository does. VectorStore.upsert() stores supplied document vectors and replaces rows with matching IDs; pgvector, Redis, Elasticsearch and Qdrant support it, while other stores reject it. The milestone APIs may change before GA.

### Source excerpt

On behalf of the Spring AI team and everyone who has contributed, I'm happy to announce that Spring AI 2.1.0-M1 has been released and is now available from Maven Central! Release notes | Upgrade notes | Reference documentation 2.1.0-M1 is the first milestone of the 2.1 line. It builds on everything that shipped in 2.0.1, moves the baseline to Spring Boot 4.2 (this milestone is built against 4.2.0-M2), and introduces three new capabilities: initial support for a structured, ordered model for message content, support for the OpenAI Responses API, and a way to write pre-computed embeddings into a vector store. As with any milestone, the new APIs are ready to try but may still change before GA. Your feedback now is what shapes them. New in this release Message Parts Until now, a Spring AI message was a text plus side lists of tool calls and media. That shape cannot represent what current models actually return: reasoning interleaved with tool calls, text between images, or provider-specific blocks that must be sent back verbatim on the next turn. AssistantMessage, UserMessage, and ToolResponseMessage now hold their content as an ordered list of MessagePart entries: TextPart, ReasoningPart, ToolCallPart, ToolResultPart, MediaPart, and UnknownPart. Parts keep the order the provider produced them in, so a conversation round-trips faithfully. A ReasoningPart or ToolCallPart can carry an OpaquePayload, which holds data such as an Anthropic thinking signature or a Gemini thought signature that has to be replayed unchanged. UnknownPart keeps the raw JSON of any block an adapter does not model yet, so nothing is silently dropped. The familiar accessors (getText(), getMedia(), getToolCalls(), and the new getReasoning()) are now views over the parts, and existing constructors and builders keep producing them in the legacy order. To control the order yourself, add parts directly: UserMessage question = UserMessage.builder() .part(TextPart.of("What changed between these two charts?

[Next page](<https://devfeed.tech/topics/spring-ai.md?cursor=WyIyMDI2LTA5LTI1VDAwOjAwOjAwKzAwOjAwIiwgIjZiNzM4ZGNjLTQwZDYtNGVmYi1hZDhjLWY4N2I0OWM1ZWIzNCJd>)