原文-Spring AI知識庫，歡迎大家評論互動
師父領進門，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 是一個面向人工智能工程的應用框架。其目標是將 Spring 生態系統的設計原則應用于人工智能領域，如可移植性和模塊化設計，并推廣使用 POJOs 作為人工智能領域應用程序的構建塊。

At its core, Spring AI addresses the fundamental challenge of AI integration: Connecting your enterprise Data and APIs with the AI Models.
從本質上講，Spring AI 解決了 AI 集成的基本挑戰：將企業數據和 API 與 AI 模型連接起來。(生產要素：數據、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，支持的模型類型包括：
  • Chat Completion，對話聊天模型
  • Embedding，嵌入模型
  • Text to Image
  • Audio Transcription
  • Text to Speech
  • Moderation，審核模型
• 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 選項。還提供特定于模型的功能訪問。
• Structured Outputs - Mapping of AI Model output to POJOs.
• 結構化輸出 - AI 模型輸出到 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數據庫提供商。
• Portable API across Vector Store providers, including a novel SQL-like metadata filter API.
• 跨向量存儲提供商的可移植 API，包括新穎的類似 SQL 的元數據過濾器 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/函數調用 - 允許模型請求執行客戶端工具和函數，從而根據需要訪問必要的實時信息。
• Observability - Provides insights into AI-related operations.
• 可觀測性 - 提供 AI 相關操作的洞察。
• Document injection ETL framework for Data Engineering.
• 用于數據工程的文檔注入 ETL 框架。
• AI Model Evaluation - Utilities to help evaluate generated content and protect against hallucinated response.
• AI 模型評估 - 幫助評估生成的內容并防止幻覺反應/虛假響應的工具。
• ChatClient API - Fluent API for communicating with AI Chat Models, idiomatically similar to the WebClient and RestClient APIs.
• ChatClient API - 與 AI 聊天模型通信的流暢 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.
• 顧問 API - 封裝重復的生成式 AI 模式，轉換發送到和來自語言模型 (LLMs) 的數據，并提供跨各種模型和用例的可移植性。(數據流管道)
• Support for Chat Conversation Memory and Retrieval Augmented Generation (RAG).
• 支持聊天對話記憶和檢索增強生成 (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 模型和向量存儲的 Spring Boot 自動配置和啟動器 - 使用 start.spring.io 選擇所需的模型或向量存儲。

This feature set lets you implement common use cases such as “Q&A over your documentation” or “Chat with your documentation”.
此功能集可讓您實現常見用例，例如 “對您的文檔進行問答” 或 “與您的文檔聊天”。(文檔是知識庫的一種組織形式)

參考引用

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