Which do you intend to use? (OpenAI, Ollama for local models, Azure, etc.)
Once you have a baseline Spring Boot AI application operational, you can extend your architectural capabilities into production-ready patterns: spring ai in action pdf github link
This public link is valid for 7 days and shares a thread, including any personal information you added. This link or copies made by others cannot be deleted. If you share with third parties, their policies apply. Can’t copy the link right now. Try again later. Which do you intend to use
To help me point you toward the most useful or documentation links for your project, please let me know: If you share with third parties, their policies apply
| Repository | Description | Key Technologies | | :--------- | :---------- | :--------------- | | | A tutorial putting AI to work using Spring Boot. Covers basic integration patterns and includes a companion Medium article. Great starting point for absolute beginners. | Spring Boot, OpenAI | | Ravikharatmal/spring-ai-tutorial | Comprehensive tutorial setup with detailed configuration instructions for multiple models including OpenAI and Anthropic. Includes MCP (Model Context Protocol) examples. | OpenAI, Anthropic, MCP, PostgreSQL | | liuyueyi/spring-ai-demo | A rich demo project covering the entire Spring AI learning path: prompts, structured output, tool calling, MCP, advisors, ChatClient, and multiple model integration. Includes extensive Chinese documentation. | Spring Boot 3.5+, Spring AI 1.x & 2.x, LangGraph4J | | asaikali/spring-ai-zero-to-hero | Workshop content designed for conference sessions. Requires Java 21+, Docker, and Ollama. Includes a check-deps.sh script to verify prerequisites. Best for hands-on workshop learning. | Ollama, Docker, Testcontainers | | ThomasVitale/llm-apps-java-spring-ai | Production-quality examples from a respected Spring contributor. Covers chatbots, question answering (RAG), semantic search, structured data extraction, text classification, and multimodal models (image, audio). | Ollama, PGVector, Mistral AI, OpenAI |
Function calling allows an LLM to request the execution of local Java code to fetch real-time data. For example, if a user asks about an account balance, the LLM recognizes it needs external data, triggers a registered Spring @Bean function, receives the balance, and formats a final natural language answer for the user.
Implementing safety measures in AI applications. Observability: Monitoring Gen AI apps from the start. Spring AI in Action PDF & eBook