原文-Spring AI知识库，欢迎大家评论互动
师父领进门，修行靠自己。

Spring AI is an application framework for AI engineering. Its goal is to apply to the AI domain Spring ecosystem design principles such as portability and modular design and promote using POJOs as the building blocks of an application to the AI domain.
Spring AI 是一个面向人工智能工程的应用框架。其目标是将 Spring 生态系统的设计原则应用于人工智能领域，如可移植性和模块化设计，并推广使用 POJOs 作为人工智能领域应用程序的构建块。

At its core, Spring AI addresses the fundamental challenge of AI integration: Connecting your enterprise Data and APIs with the AI Models.
从本质上讲，Spring AI 解决了 AI 集成的基本挑战：将企业数据和 API 与 AI 模型连接起来。(生产要素：数据、APIs和AI模型s)

Features-功能

Spring AI provides the following features:

• Support for all major AI Model providers such as Anthropic, OpenAI, Microsoft, Amazon, Google, and Ollama. Supported model types include:
• 支持所有主要的 AI 模型提供商，支持的模型类型包括：
  • Chat Completion，对话聊天模型
  • Embedding，嵌入模型
  • Text to Image
  • Audio Transcription
  • Text to Speech
  • Moderation，审核模型
• Portable API support across AI providers for both synchronous and streaming API options are supported. Access to model-specific features is also available.
• 跨 AI 提供商的可移植 API，包括同步 API 和流式 API 选项。还提供特定于模型的功能访问。
• Structured Outputs - Mapping of AI Model output to POJOs.
• 结构化输出 - AI 模型输出到 POJOs 的映射。
• Support for all major Vector Database providers such as Apache Cassandra, Azure Vector Search, Chroma, Milvus, MongoDB Atlas, Neo4j, Oracle, PostgreSQL/PGVector, PineCone, Qdrant, Redis, and Weaviate.
• 支持所有主要的向量数据库提供商。
• Portable API across Vector Store providers, including a novel SQL-like metadata filter API.
• 跨向量存储提供商的可移植 API，包括新颖的类似 SQL 的元数据过滤器 API。
• Tools/Function Calling - permits the model to request the execution of client-side tools and functions, thereby accessing necessary real-time information as required.
• 工具/函数调用 - 允许模型请求执行客户端工具和函数，从而根据需要访问必要的实时信息。
• Observability - Provides insights into AI-related operations.
• 可观测性 - 提供 AI 相关操作的洞察。
• Document injection ETL framework for Data Engineering.
• 用于数据工程的文档注入 ETL 框架。
• AI Model Evaluation - Utilities to help evaluate generated content and protect against hallucinated response.
• AI 模型评估 - 帮助评估生成的内容并防止幻觉反应/虚假响应的工具。
• ChatClient API - Fluent API for communicating with AI Chat Models, idiomatically similar to the WebClient and RestClient APIs.
• ChatClient API - 与 AI 聊天模型通信的流畅 API
• Advisors API - Encapsulates recurring Generative AI patterns, transforms data sent to and from Language Models (LLMs), and provides portability across various models and use cases.
• 顾问 API - 封装重复的生成式 AI 模式，转换发送到和来自语言模型 (LLMs) 的数据，并提供跨各种模型和用例的可移植性。(数据流管道)
• Support for Chat Conversation Memory and Retrieval Augmented Generation (RAG).
• 支持聊天对话记忆和检索增强生成 (RAG)。
• Spring Boot Auto Configuration and Starters for all AI Models and Vector Stores - use the start.spring.io to select the Model or Vector-store of choice.
• 所有 AI 模型和向量存储的 Spring Boot 自动配置和启动器 - 使用 start.spring.io 选择所需的模型或向量存储。

This feature set lets you implement common use cases such as “Q&A over your documentation” or “Chat with your documentation”.
此功能集可让您实现常见用例，例如 “对您的文档进行问答” 或 “与您的文档聊天”。(文档是知识库的一种组织形式)

参考引用

• Spring AI
• spring-ai
• Spring AI / Overview