Add quantal#629
Open
PaytonWebber wants to merge 1 commit into
Open
Conversation
quantal is an embedded vector index that combines HNSW-style graph routing over 1-bit SimHash codes with 3-bit TurboQuant scoring and an exact rerank pass. Supports angular and dot metrics. Installed from PyPI (quantaldb); dimensions the wheel does not bundle are compiled in the Dockerfile with Zig.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 adds quantal, an embedded vector index with a Zig core: an HNSW-style graph routes over 1-bit SimHash codes, 3-bit TurboQuant codes score the candidate pool, and an exact pass (sq8 by default) settles the final order. Angular and dot metrics are supported.
Following the checklist in the README:
module.pyDockerfile(installs the publishedquantaldbwheel; dimensions the wheel does not bundle are compiled in the image with Zig, so runs never pay a compile)config.yml(ef_constructionat build time, candidate-pool sizemswept at query time).github/workflows/benchmarks.ymlTested locally on
random-xs-20-angularwith--runs 2, both standard and--batchmode, plusplot.pyover the results.Disclosure: I am the author of quantal.