序
本文主要研究一下Spring AI 1.0.0-SNAPSHOT的变更
Artifact ID变更
- Model starters: spring-ai-{model}-spring-boot-starter → spring-ai-starter-model-{model}
- Vector Store starters: spring-ai-{store}-store-spring-boot-starter → spring-ai-starter-vector-store-{store}
- MCP starters: spring-ai-mcp-{type}-spring-boot-starter → spring-ai-starter-mcp-{type}
示例
<!-- BEFORE -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-openai-spring-boot-starter</artifactId>
</dependency>
<!-- AFTER -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-starter-model-openai</artifactId>
</dependency>Spring AI Autoconfiguration从单体模块变更为每个model、vector-store等独立的autoconfiguration，拆开的目的就是避免引入没必要的依赖，减少冲突风险：
<!-- NO LONGER AVAILABLE -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-spring-boot-autoconfigure</artifactId>
<version>${project.version}</version>
</dependency>取而代之的是：
-
Model autoconfiguration: spring-ai-autoconfigure-model-{model}
org.springframework.ai spring-ai-autoconfigure-model-openai org.springframework.ai spring-ai-autoconfigure-model-anthropic org.springframework.ai spring-ai-autoconfigure-model-vertex-ai -
Vector Store autoconfiguration: spring-ai-autoconfigure-vector-store-{store}
org.springframework.ai spring-ai-autoconfigure-vector-store-redis org.springframework.ai spring-ai-autoconfigure-vector-store-pgvector org.springframework.ai spring-ai-autoconfigure-vector-store-chroma -
MCP autoconfiguration: spring-ai-autoconfigure-mcp-{type}
org.springframework.ai spring-ai-autoconfigure-mcp-client org.springframework.ai spring-ai-autoconfigure-mcp-server
Package Name变更
- KeywordMetadataEnricher以及SummaryMetadataEnricher从
org.springframework.ai.transformer变更到org.springframework.ai.chat.transformer - Content, MediaContent以及Media从
org.springframework.ai.model变更到org.springframework.ai.content
Module变更
之前是所有的都在spring-ai-core，现在拆分到具体的领域模块来减少不必要的依赖，如下：
- spring-ai-commons包含了核心的model比如
Document、TextSplitter - spring-ai-model包含了AI能力的相关抽象，比如
ChatModel、EmbeddingModel、ImageModel、ToolDefinition、ToolCallback - spring-ai-vector-store统一了向量数据库的抽象
VectorStore，提供了SimpleVectorStore便于内存使用 - spring-ai-client-chat提供了high-level的AI会话API，比如
ChatClient、ChatMemory、OutputConverter - spring-ai-advisors-vector-store为RAG衔接了chat和向量数据库，比如
QuestionAnswerAdvisor、VectorStoreChatMemoryAdvisor - spring-ai-model-chat-memory-cassandra提供了
CassandraChatMemory - spring-ai-rag提供了RAG的pipelines，比如
RetrievalAugmentationAdvisor
Dependency Structure变更如下：
- spring-ai-commons (foundation)
- spring-ai-model (depends on commons)
- spring-ai-vector-store and spring-ai-client-chat (both depend on model)
- spring-ai-advisors-vector-store and spring-ai-rag (depend on both client-chat and vector-store)
- spring-ai-model-chat-memory-* modules (depend on client-chat)
小结
Spring AI 1.0.0-SNAPSHOT主要是涉及了Artifact ID, Package, Module的变更；Spring AI Autoconfiguration从单体模块变更为每个model、vector-store等独立的autoconfiguration，拆开的目的就是避免引入没必要的依赖，减少冲突风险；KeywordMetadataEnricher、SummaryMetadataEnricher、Content、MediaContent以及Media涉及了包名的变更；模块的变更将spring-ai-core拆分到具体的领域模块来减少不必要的依赖。