fix: Split compound terms via VectorTermsService #2081
Merged
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
dustinbyrne
changed the title
dividedmind
force-pushed
the
feat/support-vertex-ai
branch
from
f798f3e
to
f1e6372
Compare
dustinbyrne
force-pushed
the
fix/llm-split-compound-terms
branch
from
e75d724
to
7140c05
Compare
dividedmind
approved these changes
Oct 22, 2024
dustinbyrne
force-pushed
the
fix/llm-split-compound-terms
branch
from
7140c05
to
e5305f8
Compare
|
🎉 This PR is included in version @appland/navie-v1.34.1 🎉 The release is available on:
Your semantic-release bot 📦🚀 |
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Outdated suggestions cannot be applied.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.
The LLM is now instructed to split compound words into individual search terms. This will improve search performance among lower case search terms that cannot be split by word boundary without a word list.
E.g., given the input
The following vector terms are generated
This is preferred over the current behavior, which outputs the following:
Without proper casing, these outputs will not be split on word boundary, resulting in lower quality search results. This previously created a disparity between two inputs like
HTTPServer,httpserver.Resolves #2067