Repository navigation
refactor: enhance schema recall - #108
Merged
Merged
Conversation
- adjust workflow before plannerNode - call hybrid search in AgentVectorStoreService - add aop for log - clean unsed code
lzq986
marked this pull request as draft
November 11, 2025 10:17
VLSMB
self-requested a review
November 11, 2025 14:36
There was a problem hiding this comment.
Pull Request Overview
This PR refactors the schema recall workflow by restructuring the query processing pipeline. The changes replace the previous two-step process (QueryRewrite + KeywordExtract) with a three-step process (IntentRecognition → EvidenceRecall → QueryEnhance) and introduce a FeasibilityAssessment node before planning.
Key changes:
- Replaced query rewrite and keyword extraction with intent recognition, evidence recall, and query enhancement nodes
- Added feasibility assessment node to validate data analysis requests before planning
- Implemented hybrid search functionality with configurable vector store properties
- Refactored schema service to use direct document lists instead of nested lists
- Added AOP-based logging for node entry points
- Removed unused code including sample data enrichment in NL2SQL service
Reviewed Changes
Copilot reviewed 61 out of 61 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| schema.sql / data.sql | Added table_name and schema_name columns to semantic_model table for better metadata tracking |
| AgentSearchRequest.java | Simplified to use Lombok builder pattern, removed complex factory methods |
| AgentVectorStoreService*.java | Refactored to support hybrid search and removed estimateDocuments method |
| SchemaService*.java | Changed column document handling from nested lists to flat lists with fusion strategy |
| Node classes | Replaced QueryRewriteNode/KeywordExtractNode with IntentRecognition/EvidenceRecall/QueryEnhance/FeasibilityAssessment nodes |
| Hybrid search classes | Updated fusion strategy to support variable arguments and parameter order |
| Configuration | Added DataAgentProperties for vector store settings and AOP logging aspect |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
There was a problem hiding this comment.
Pull Request Overview
Copilot reviewed 80 out of 80 changed files in this pull request and generated 6 comments.
Comments suppressed due to low confidence (2)
spring-ai-alibaba-data-agent-chat/src/main/java/com/alibaba/cloud/ai/service/schema/SchemaServiceImpl.java:1
- The code adds
docstoallResultswhendocuments(the filtered result) is not empty. This appears to be a bug - it should adddocumentsinstead ofdocsto maintain consistency with the filtering logic.
spring-ai-alibaba-data-agent-chat/src/main/java/com/alibaba/cloud/ai/node/PythonExecuteNode.java:1 - Changed from
createResponsetocreatePureResponseon line 100, but line 99 usescreatePureResponsefor the start sign. This inconsistency has been corrected. Good fix.
/*
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
Author
|
related to #104 |
VLSMB
approved these changes
Nov 14, 2025
VLSMB
marked this pull request as ready for review
November 14, 2025 16:51
pangpang20
pushed a commit
to pangpang20/DataAgent
that referenced
this pull request
Jan 28, 2026
* refactor: enhance schema recall - adjust workflow before plannerNode - call hybrid search in AgentVectorStoreService - add aop for log - clean unsed code * clean unsed node * feat: adapt flux output * add semantic support * fix: python bug * fix unit test * fix TableRelationDispatcher unit test * fix method buildBusinessKnowledgePrompt * delete unused code * add metadata constant * add semantic support * update semantic crud cotroller * fix MappersTest.java * feat: add semantic frontend * fix bugs * feat: add search text-edit * fix: bugs in schema.sql * adjust semantic and business knowledge * adjust by copilot feedback * fix MapperTest type error. * refactor: workflow * chore update README.md --------- Co-authored-by: VLSMB <2047857654@qq.com> Co-authored-by: VLSMB <36068250+VLSMB@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Describe what this PR does / why we need it
Does this pull request fix one issue?
close #58 close #97 close #99, fix #30 fix #104
Describe how you did it
Describe how to verify it
Special notes for reviews