feat: Add cube description to members for vector search indexing and agent output#10593
Closed
paveltiunov wants to merge 5 commits intomasterfrom
Closed
feat: Add cube description to members for vector search indexing and agent output#10593paveltiunov wants to merge 5 commits intomasterfrom
paveltiunov wants to merge 5 commits intomasterfrom
Conversation
github-actions
bot
added
client:core
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## master #10593 +/- ##
===========================================
+ Coverage 57.88% 78.58% +20.70%
===========================================
Files 225 475 +250
Lines 17581 92866 +75285
Branches 3614 3616 +2
===========================================
+ Hits 10176 72980 +62804
- Misses 6861 19341 +12480
- Partials 544 545 +1
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
…agent output Add cubeDescription field to measures, dimensions, and segments in the meta response. This propagates the parent cube's description down to each member, making it available for vector search indexing (e.g., via LangChain document loader) and AI agent consumption. Changes: - CubeToMetaTransformer: Add cubeDescription to member configs - OpenAPI spec: Add cubeDescription field to member schemas - Rust cubeclient models: Add cube_description field - Client types: Add cubeDescription to BaseCubeMember - Annotations: Include cubeDescription in annotation output - Tests: Add assertions for cubeDescription in meta endpoints Co-authored-by: Pavel Tiunov <pavel.tiunov@gmail.com>
Co-authored-by: Pavel Tiunov <pavel.tiunov@gmail.com>
Add CUBEJS_MAX_EMBEDDING_DESCRIPTION_LENGTH environment variable to limit the number of characters in description fields exposed through the meta API. When set to a positive integer, all description and cubeDescription fields are truncated to that length during meta transformation. This prevents excessively long descriptions from consuming too many tokens when indexed by embedding models (e.g., via LangChain's CubeSemanticLoader). Default value of 0 means no truncation (backward compatible). Co-authored-by: Pavel Tiunov <pavel.tiunov@gmail.com>
Add cube_description: None to all CubeMetaMeasure and CubeMetaSegment struct literals in compile/test/mod.rs and benches/large_model.rs to match the new field added to the cubeclient models. Co-authored-by: Pavel Tiunov <pavel.tiunov@gmail.com>
…gment initializers The previous fix only covered the first two cube definitions in mod.rs. This adds cube_description: None to all 29 CubeMetaMeasure and CubeMetaSegment struct literals across NumberCube, WideCube, MultiTypeCube, StringCube, and SixteenChar test cubes. Co-authored-by: Pavel Tiunov <pavel.tiunov@gmail.com>
cursor
bot
force-pushed
the
cursor/cube-description-vector-search-0b7c
branch
from
eca938d to
d3d5071
Compare
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.
.