Most Java developers think building AI features means learning Python first. It doesn't. **Spring AI** gives you `ChatClient`, `VectorStore`, function calling, and structured output — inside the same Spring Boot app you already know how to build, test, and deploy. You don't need to bolt on a separate Python service just to add a chatbot, a RAG pipeline, or an agent to your product. To make that concrete, I put together **100 project ideas** you can build with Spring Boot and Spring AI. Not vague titles — each one comes with the actual stack you'd reach for. Here are five, to give you a feel for the format: Project | Stack ---|--- Support Bot with RAG | Spring AI + pgvector + `QuestionAnswerAdvisor` Meeting Notes Summarizer | `BeanOutputConverter` → `ActionItem` records Natural Language to SQL | JDBC `DatabaseMetaData` for schema context Repo-Aware Coding Agent | Tree-sitter + `VectorStore` + function calling Voice Support Agent | WebSocket audio + RAG + function calling ## The three tiers The full list is organized by difficulty, so you can pick something that matches where you are right now instead of jumping straight into agent orchestration: * **1–40 · Beginner** — Spring Boot + Spring AI fundamentals: your first `ChatClient` calls, prompt templates, basic conversational endpoints. * **41–80 · Intermediate** — RAG pipelines and integrations: vector stores, document ingestion, structured output, calling external APIs from a model. * **81–100 · Advanced** — Agents and orchestration: multi-step reasoning, tool-calling agents, and systems that coordinate several models or services. ## Why I'm doing this project by project I'm building these one at a time — real code, real architecture decisions, and the parts that break along the way (because something always does). Each finished project gets a full write-up: what I built, the tradeoffs I hit, and the code itself. **Want the full list of all 100 projects (with stacks) as a PDF?** Download it here — save it for later. If you want to follow along as the series grows, I'm publishing every project on my Substack the day it's done — subscribe here to get each one as it lands. I also run a small community for Java developers building with Spring Boot and Spring AI, if you want to talk through ideas or share what you're building: Global Java Developers Community. ## **Which one should I build first?** Drop a number (or a project idea of your own) in the comments — I'm picking the next build from replies.

About Notate is an advanced research enhancement tool that integrates AI-driven data organization and vectorstore collections to amplify your research and optimize workflows. - CNTRLAI/Notate

search results for "home cooked meals"

VectorStore infrastructure

MySQL HeatWave integrates GenAI capabilities into MySQL on OCI. We have demonstrated how HeatWave GenAI can leverage RAG's capability to utilize ingested documents (unstructured data) in LakeHouse and...

Contribute to michaelisvy/demo-spring-ai development by creating an account on GitHub.

LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]

LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]

LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]

LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]

LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]

LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutorial, we will show […]