lance-format/lance
Allow users to set a distance threshold to consider two vectors a "very similiar"
クローズ
#875 opened on 2023/05/17
A-indexA-pythonenhancementgood first issuehelp wanted
Repository metrics
- Stars
- (6,582 個のスター)
- PR merge metrics
- (平均マージ 6d 1h) (30d で 219 merged PRs)
説明
Problem Statement
For example, I have lots of images that are resized jpgs and gifs -- the hashes are technically different, but the vector l2 distance is tiny then there's deduplicating things like images and watermarked images -- i also want this to be grouped together and to pick just one which basically uses the vector distance again, but with a looser threshold