NVIDIA / NVIDIA/cuvs

[FEA]. Expose IVFPQ unpack* functions to Python

Open
#1,341 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

Users have requested the ability to build an IVFPQ index add a bunch of vectors to it, then extract the encoded verctors from each list so they can be stored separately. For example, a vector database that might want to persist the encoded vectors to files on disk.

We should expose these functions through Python because expecting the users to deal w/ interleaved PQ codes is brittle and can be daunting / challenging for users to figure out.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the IVFPQ unpack* functions and the existing Python bindings for IVFPQ. Trace how encoded vectors are represented per list and determine the Python-facing API needed to extract them without requiring users to handle interleaved PQ codes. Done means the unpack functions are accessible from Python and support storing encoded vectors separately.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
search
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.