feat: unify BM25 scoring with persistent namespace MAP - #359
Merged
Merged
Conversation
…map snapshot handling
- Updated the backfill_map_unit_indexes script to include patching of the namespace map snapshot after persisting the revision serving state. - Removed outdated contract tests related to BM25 FTS prefilter and unit tests for BM25 channel token preparation. - Refactored retrieval logic to improve handling of document map units, including new fields for asset presence.
- Added new test cases for document publishing and scoring with additional image chunks. - Refactored the lazy snapshot retrieval logic to improve score preservation without unnecessary payload reads. - Updated the handling of incomplete index scenarios to ensure empty scores are returned when no data is available. - Removed obsolete methods related to document unit loading to streamline the codebase.
- Introduced new fields `average_idf_path` and `average_idf_content` in the DocumentMapUnitIndex for improved scoring accuracy. - Updated the retrieval logic to calculate average IDF values during document map unit processing. - Refactored map unit discovery to utilize average IDF in scoring calculations, enhancing retrieval performance. - Removed obsolete code related to previous scoring methods to streamline the implementation.
Co-authored-by: Cursor <cursoragent@cursor.com>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| import sqlalchemy as sa | ||
|
|
||
|
|
||
| revision: str = "6c7d8e9f0a1b" |
|
|
||
|
|
||
| revision: str = "6c7d8e9f0a1b" | ||
| down_revision: str | None = "5b6c7d8e9f0a" |
|
|
||
| revision: str = "6c7d8e9f0a1b" | ||
| down_revision: str | None = "5b6c7d8e9f0a" | ||
| branch_labels: Sequence[str] | None = None |
| revision: str = "6c7d8e9f0a1b" | ||
| down_revision: str | None = "5b6c7d8e9f0a" | ||
| branch_labels: Sequence[str] | None = None | ||
| depends_on: Sequence[str] | None = None |
Co-authored-by: Cursor <cursoragent@cursor.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
2 participants
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
Test plan
make check(lint + pyright)Made with Cursor