spring-projects/spring-ai

An Application Framework for AI Engineering

What it solves

Spring AI simplifies the integration of artificial intelligence into enterprise Java applications. It addresses the challenge of connecting enterprise data and APIs with various AI models while maintaining portability and modular design, preventing developers from being locked into a single AI provider.

How it works

It provides a Spring-friendly API and a set of abstractions that allow developers to to use strongly-typed data structures to interact with AI models. It offers a portable API across different AI providers (such as OpenAI, Anthropic, and Google) and vector stores (such as Pinecone, Milvus, and Redis), allowing for easy switching between providers without rewriting core application logic.

Who it’s for

Java and Spring Boot developers who want to build generative AI applications, including those requiring RAG (Retrieval Augmented Generation), tool calling, and structured outputs.

Highlights

  • Multi-provider support: Support for major AI model providers including Anthropic, OpenAI, Amazon Bedrock, Google, and Ollama.
  • KNOWLEDGE base integration: Support for a wide array of vector store providers for efficient data retrieval.
  • Tool Calling: Allows AI models to request the execution of client-side tools and functions for real-time information.
  • Structured Outputs: Maps AI model outputs directly to POJOs (Plain Old Java Objects).
  • MCP Support: First-class support for the Model Context Protocol (MCP) for building AI applications that consume MCP servers.
  • ETL Framework: Includes a document injection ETL framework for data engineering tasks.
  • Observability: Built-in tools to provide insights into AI-related operations.

Related

  • Project
    ThomasVitale/llm-apps-java-spring-ai

    A collection of sample Java applications and patterns demonstrating how to build Generative AI and LLM-powered apps using the Spring AI framework.

  • Project
    agents-flex/agents-flex

    A lightweight, modular AI application framework for Java that provides unified abstractions for LLMs, RAG, and agents, with production-ready tooling for Spring Boot integration.

  • Project
    modelcontextprotocol/java-sdk

    A Java SDK for the Model Context Protocol that enables Java applications to interact with AI models and tools through a standardized, interoperable interface.

  • Project
    metorial/metorial

    An open-source identity and access layer for AI agents that provides standardized authentication, permissions, and observability across thousands of external system integrations.

  • Project
    langchain4j/langchain4j

    An idiomatic Java library that simplifies integrating LLMs into JVM applications through unified APIs for providers and embedding stores, and a toolbox for building RAG and agentic apps.