Support new VAMANA vector type #3702
Merged
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
…upport-for-vamana-vector-type-in-ft-create
ofekshenawa force-pushed the add-support-for-vamana-vector-type-in-ft-create branch from 5542b84 to 7f78eb0 Compare 
Collaborator
| Several RESP 3 tests are failing. Can you take a look? Also, can you please add a few tests for async client - I don't think we need all the tests to be duplicated there - but just 3-4 that will contain the new configurations... |
ofekshenawa force-pushed the add-support-for-vamana-vector-type-in-ft-create branch from 040992e to 5044695 Compare ofekshenawa force-pushed the add-support-for-vamana-vector-type-in-ft-create branch from 2fb3633 to 1171e0e Compare 
petyaslavova approved these changes Jul 11, 2025
petyaslavova approved these changes Jul 11, 2025
petyaslavova pushed a commit that referenced this pull request Jul 25, 2025
* Support new vector type * Skip VAMANA tests is redis versin is not 8.2 * Add async tests * Fix resp 3 errors
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 Outdated suggestions cannot be applied.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.
This PR adds comprehensive support for SVS-VAMANA vector search algorithm in redis-py, providing a high-performance approximate nearest neighbor search capability with advanced compression options.
Core Implementation
SVS-VAMANAalgorithm support toVectorFieldclassCompression Support
Build Parameters
CONSTRUCTION_WINDOW_SIZE: Controls graph construction qualityGRAPH_MAX_DEGREE: Maximum connections per nodeSEARCH_WINDOW_SIZE: Search beam widthEPSILON: Search accuracy vs speed tradeoffTRAINING_THRESHOLD: Minimum vectors needed for compression training