Skip to content

Conversation

lzq986
Copy link
Contributor

@lzq986 lzq986 commented Oct 9, 2025

Describe what this PR does / why we need it

  1. 本次这次调整是不再依赖 AgentVectorStoreManager.java,解决之前硬编码向量不能扩展其他向量库的问题,用户只需要后台配置一个向量库即可,做了代码抽象,为后续的向量扩展提供基础。
  2. 补充回来spotless插件
  3. 删除部分无调用的代码

Does this pull request fix one issue?

Describe how you did it

Describe how to verify it

Special notes for reviews

@lzq986
Copy link
Contributor Author

lzq986 commented Oct 9, 2025

@VLSMB @zxuexingzhijie 辛苦审核下本次调整。涉及的比较多文件

@zxuexingzhijie zxuexingzhijie requested a review from Copilot October 9, 2025 10:18
@lzq986
Copy link
Contributor Author

lzq986 commented Oct 9, 2025

Related to [Task] 代码大重构 #37

Copy link

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR refactors the vector management system to remove hardcoded dependencies and improve extensibility, while also adding the Spotless code formatting plugin.

  • Abstracts vector store management to support multiple vector database implementations
  • Removes hardcoded AgentVectorStoreManager.java and introduces new service interfaces
  • Adds Spotless plugin for automatic code formatting

Reviewed Changes

Copilot reviewed 27 out of 27 changed files in this pull request and generated 6 comments.

Show a summary per file
File Description
AbstractVectorStoreService.java Major refactor - Introduces agent-based vector store operations with metadata filtering
AgentVectorStoreService.java New interface defining agent-specific vector store operations
SimpleVectorStoreService.java Simplified to extend abstract base class and focus on SimpleVectorStore implementation
AnalyticVectorStoreService.java Refactored to support AnalyticDbVectorStore implementation
VectorStoreServiceFactory.java Updated to create AgentVectorStoreService implementations
AgentVectorService.java Refactored to use new AgentVectorStoreService interface
AgentSearchRequest.java New request model with agent-specific search parameters
DocumentConverterUtil.java Added agent-aware document conversion methods
SchemaProcessorUtil.java Added database configuration creation utility
Various other files Cleanup of unused code and interface adjustments
pom.xml Added Spotless plugin configuration

Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.

@VLSMB VLSMB changed the title 向量管理的代码最终调整以及加入spotless插件 feat: 向量管理的代码最终调整以及加入spotless插件 Oct 9, 2025
@lzq986 lzq986 changed the title feat: 向量管理的代码最终调整以及加入spotless插件 refactor: Final adjustments for vector management and add spotless plugin Oct 9, 2025
@lzq986 lzq986 force-pushed the refactor/agent-vector-manage branch from 9bc3fa5 to ff46e4a Compare October 9, 2025 15:35
@lzq986 lzq986 changed the title refactor: Final adjustments for vector management and add spotless plugin feat: Final adjustments for vector management and add spotless plugin Oct 9, 2025
@lzq986 lzq986 changed the title feat: Final adjustments for vector management and add spotless plugin feat(chat): Final adjustments for vector management and add spotless plugin Oct 9, 2025
@lzq986 lzq986 changed the title feat(chat): Final adjustments for vector management and add spotless plugin refactor: final adjustments for vector management and add spotless plugin Oct 10, 2025
- rename classes and remove unused code
- adjust AgentVectorStoreServiceFactory and SchemaServiceFactory
Copy link
Collaborator

@zxuexingzhijie zxuexingzhijie left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@VLSMB VLSMB merged commit d4bb01d into spring-ai-alibaba:main Oct 10, 2025
6 checks passed
@lzq986 lzq986 deleted the refactor/agent-vector-manage branch October 10, 2025 08:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants