Easily get started with Spring-AI to develop various AI applications, including TextToSQL and private data AI application development. In addition to these capabilities, Spring-AI also supports integration with several other advanced AI technologies and platforms such as DeepSeek, Azure, Ollama, Vector Databases, Function Calling, MCP and RAG.
# spring-ai-apps **[中文版本](./README-zh.md)** This is a collection of Spring AI small applications, aimed at helping everyone easily learn how to apply Spring AI for AI application development, reducing cognitive burden. Each small application has minimal code, but the framework is fully set up, resolving various version conflict issues. # Spring AI Small Application List: | Category | Application Name | Description | |---------------------|-------------------------------|-----------------------------------------------------------------------------------------------| | **Chat Model** | [chat-deepseek](chat-deepseek) | A chat application based on DeepSeek. | | **Chat Model** | [chat-azure](chat-azure) | A chat application based on Azure's OpenAI large model. | | **Chat Model** | [newston](newston) | An intelligent editing agent that retrieves the latest stories, summarizes AI and software development content, and sends them to recipients via email. | | **Chat Model** | [memory-llama](memory-llama) | Demonstrates how Spring AI implements memory functions and streaming output, supporting multi-turn conversations for better answers. | | **Chat Model** | [prototype-design](prototype-design) | Quickly generates prototype designs based on natural language and templates, suitable for product managers or business analysts. | | **Embedding Model** | [embeddings-ollama](embeddings-ollama) | A Q&A application that vectorizes private data using Ollama+Qwen2.5. | | **Vector Database** | [chroma-ollama](chroma-ollama) | Combines Ollama+Qwen2.5 with Chroma for vector storage and Q&A applications with private PDF data **Vector Database** | [neo4j-ollama](neo4j-ollama) | A GraphRAG example using Neo4j
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型