Add SpaCy Semantic match resolver for KG Builder #310
Closed
Conversation
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
stellasia
reviewed
Mar 20, 2025
examples/customize/build_graph/components/resolvers/spacy_entity_resolver_pre_filter.py
Show resolved
Hide resolved
| try: | ||
| return spacy.load(model_name) | ||
| except OSError as e: | ||
| # The exact error message can differ slightly depending on spaCy version, |
There was a problem hiding this comment.
I don't get the message here, does that mean that the fallback does not work in some cases?
There was a problem hiding this comment.
If the user would like to use the spaCy resolver two things are required:
1- installing the spaCy library
2- downloading the language model.
The first one is handled in poetry. This function is to handle downloading the model. Maybe we can also trigger it from poetry? it's just that I found it easier this way. any preference?
15 tasks
|
Closing this PR as it was handled by PR#319 |
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Outdated suggestions cannot be applied.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.
Description
This PR introduces a new
SpaCySemanticMatchResolvercomponent that leverages spaCy embeddings to merge nodes based on textual similarity. It expands upon the existing resolver framework (which was previously limited to exact matching) to support semantic comparisons of a given set of textual properties (the "name" property is still the default choice) via cosine similarity of embeddings. The main motivation behind this is to provide a more robust entity resolution approach that avoid missing merges (e.g., TwoPersonnodes whosenameproperties are respectively "John Smith" and "Jonathan Smith" andSSNproperties are the same, etc.), and false merges (e.g., TwoPersonnodes with exactnameproperties and differentSSNproperties, etc.).Type of Change
Complexity
Complexity:
How Has This Been Tested?
Checklist
The following requirements should have been met (depending on the changes in the branch):