Spring AI API

Introduction

Spring AI API 涵盖广泛的功能。每个主要功能在其自己的专用部分中详细说明。为了提供一个概述,提供了以下关键功能:

The Spring AI API covers a wide range of functionalities. Each major feature is detailed in its own dedicated section. To provide an overview, the following key functionalities are available:

AI Model API

Model API 在 AI 提供商之间(适用于 ChatText to ImageAudio TranscriptionText to SpeechEmbedding 模型)可移植。支持 synchronousstream API 选项。还支持访问模型特定功能。

Portable Model API across AI providers for Chat, Text to Image, Audio Transcription, Text to Speech, and Embedding models. Both synchronous and stream API options are supported. Dropping down to access model specific features is also supported.

model hierarchy

支持来自 OpenAI、Microsoft、Amazon、Google、Amazon Bedrock、Hugging Face 等的 AI 模型。

With support for AI Models from OpenAI, Microsoft, Amazon, Google, Amazon Bedrock, Hugging Face and more.

spring ai chat completions clients

Vector Store API

Vector Store API 可跨多个提供商移植,包括一个新颖的 SQL-like metadata filter API ,它也是可移植的。支持 14 种矢量数据库。

Portable Vector Store API across multiple providers, including a novel SQL-like metadata filter API that is also portable. Support for 14 vector databases are available.

Tool Calling API

Spring AI 使得 AI 模型可以轻松地调用您的服务,作为 @Tool 注解的方法或 POJO java.util.Function 对象。

Spring AI makes it easy to have the AI model invoke your services as @Tool-annotated methods or POJO java.util.Function objects.

tool calling 01

查看 Spring AI Tool Calling 文档。

Check the Spring AI Tool Calling documentation.

Auto Configuration

用于 AI 模型和向量存储的 Spring Boot 自动配置和启动器。

Spring Boot Auto Configuration and Starters for AI Models and Vector Stores.

ETL Data Engineering

数据工程的 ETL 框架。这提供了将数据加载到向量数据库的基础,帮助实施数据增强型生成模式,使你能够将你的数据带到 AI 模型中,并将其纳入其响应中。

ETL framework for Data Engineering. This provides the basis of loading data into a vector database, helping implement the Retrieval Augmented Generation pattern that enables you to bring your data to the AI model to incorporate into its response.

etl pipeline

Feedback and Contributions

该项目的 GitHub discussions 是发送反馈的一个好地方。

The project’s GitHub discussions is a great place to send feedback.