bugfix: Duplicated citation nodes #17440
Open
+1
−1
Conversation
This file contains 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
Duplicated citation nodes in CitationQueryEngine when chunk_size is less than the content length
dosubot
bot
added
the
size:XS
| @@ -217,7 +217,7 @@ def _create_citation_nodes(self, nodes: List[NodeWithScore]) -> List[NodeWithSco | |||
| text = f"Source {len(new_nodes) + 1}:\n{text_chunk}\n" | |||
|
|
|||
| new_node = NodeWithScore( | |||
| node=TextNode.model_validate(node.node), score=node.score | |||
| node=TextNode(metadata=node.node.metadata), score=node.score | |||
There was a problem hiding this comment.
I don't think this is correct? I think what this code is originally trying to do is for each text chunk, create a copy of the original node but with new text
So, I would expect this to work:
node=TextNode.model_validate(node.node.model_dump()), score=node.score
There was a problem hiding this comment.
Yes, you are right.
I tried your solution, it worked.
However, using your solution, the sub nodes will share the same IDs. But I think it's ok since we only use the text field.
There was a problem hiding this comment.
Yea I think thats fine tbh -- feel free to update the PR!
bugfix: Duplicated citation nodes in CitationQueryEngine when chunk_size is less than the content length.
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Outdated suggestions cannot be applied.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.
bugfix:
Duplicated citation nodes in CitationQueryEngine when chunk_size is less than the content length.
Description
TextNode.model_validate dosen't create a new instance but return node.node itself, which cause a duplicated context.
Fixes #17439
New Package?
Did I fill in the
tool.llamahubsection in thepyproject.tomland provide a detailed README.md for my new integration or package?Version Bump?
Did I bump the version in the
pyproject.tomlfile of the package I am updating? (Except for thellama-index-corepackage)Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.
Suggested Checklist:
make format; make lintto appease the lint gods