🚀 Spring AI 2.0.0 GA is now available!
🏗️ Improved foundations: Spring Boot 4 baseline, null-safety, Jackson 3, re-designed options
🤖 Agentic improvements: unified tool calling, tool search, self-correcting output
🔌 MCP 2025-11-25 spec integration
spring.io/blog/2026/06...
Talking to an AI application feels surprisingly natural, until it answers with a wall of text. In this recipe, you’ll enable your Spring AI application to speak its responses aloud.
medium.com/@thetalkinga...
#SpringAI #Java #SpringBoot #OpenAI #VoiceAI #TextToSpeech
Heads up: Big changes to tool use in Spring AI 2.0.0.
Spring AI 2.0.0 is almost here.
To prepare, I've updated all Spring AI Recipes and code samples to Spring AI 2.0.0-RC2 so they're aligned with the APIs and features headed toward the 2.0 release.
Recipes: www.habuma.com/springaireci...
Code: github.com/habuma/sprin...
#SpringAI #Java #GenAI
🚀 Spring AI 2.0.0-RC2 is out and one more step to GA!
✅Configurable HTTP clients for OpenAI & Anthropic
✅ Restored Spring Framework < 7.0.4 compatibility
✅ Multi-turn thinking fixed for Ollama & OpenAI, bug fixes and more on spring.io/blog/2026/06...
Why type your prompts when you can just say them out loud? In this recipe, we'll add voice input to our chat loop by recording audio from the microphone and transcribing it into text with Spring AI.
medium.com/@thetalkinga...
#SpringAI #Java #SpeechToText #VoiceAI #GenAI
LLMs know a lot, but they don't know everything. With RAG, you can teach an AI about documents it has never seen before without retraining a model. #SpringAI #RAG
medium.com/@thetalkinga...
From my Spring AI "Test Kitchen": Traditional RAG retrieves context for every question, whether it’s needed or not. In this recipe, we'll let the LLM decide whether or not to query the vector store.
#SpringAI #RAG
medium.com/@thetalkinga...
Bringing all of the Spring AI Recipes forward to 2.0.0-RC2 was done late at night. I think I've found all of the breaking changes, but there's always a chance something slipped through.
If you spot an issue, please let me know Your feedback helps keep the recipes useful for everyone.
Semantic caching can use any vector store. If you’re already using a vector store such as Qdrant, you can use it to speed up semantically similar requests and reduce token usage without adding another database to your stack.
#SpringAI #Java #SemanticCaching #VectorStore
medium.com/@thetalkinga...