fix: deduplicate relation edges using MERGE instead of CREATE#33
Open
back2zion wants to merge 1 commit intonikmcfly:mainfrom
Open
fix: deduplicate relation edges using MERGE instead of CREATE#33back2zion wants to merge 1 commit intonikmcfly:mainfrom
back2zion wants to merge 1 commit intonikmcfly:mainfrom
Conversation
When the same (source, relation_type, target) pair appears in multiple text chunks, the graph builder creates duplicate edges because it uses CREATE unconditionally. Entity nodes already use MERGE for dedup, but relations did not. Changed CREATE to MERGE keyed on (graph_id, name) between the same source and target nodes. On duplicate, the fact and embedding are updated and the episode_id is appended to the list.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
MERGEto prevent duplicates, but relation edges useCREATE— causing duplicate edges when the same (source, relation_type, target) appears across multiple text chunksFix
Changed
CREATEtoMERGEkeyed on(graph_id, name)between the same source/target nodes:ON CREATE: initializes all properties as beforeON MATCH: updates fact/embedding and appends episode_id to the listBefore
Multiple chunks mentioning the same relationship → duplicate edges in graph
After
Same (source, relation, target) → single edge, enriched with all episode references
Test plan