Using LSH to Accelerate Embedding Similarity Search

Open
#29 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Stale
Tech stack
swift
Domain
mobile, search

Research direction

The issue proposes filtering images with LSH before cosine calculations over embedding vectors, but names no files, tests, or entry points. Start by locating the existing embedding similarity-search path in the Swift iOS project and determine the expected scope and evaluation method. Done should include an agreed implementation plan and evidence that the proposed search changes meet the project's needs.

Written by the indexing model from the issue text.

Description

Why not first filter the images with LSH, and then perform cosine calculations with vectors?

Dominant language
Swift
Stars
3k
Forks
448
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

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.

More from mazzzystar/Queryable

All issues in mazzzystar/Queryable

Similar issues

More Swift issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.