31–40 of 55 posts
" A single document produces more then one embedding, depending on the complexity of the document it can produce hundreds or thousands of vectors." That typo up there is kind of endearing in the AI slop era.
[flagged]
``` We evaluated several precision pairings across our internal retrieval benchmark suite. Scores are NDCG@10 averaged across the suite, scaled to 0–100. NDCG@10 (Normalized Discounted Cumulative Gain at rank 10) measures how well the top 10 results are ordered against the ideal ranking, rewarding relevant documents more when they appear higher, with 100 being a perfect ranking. The full-precision baseline averages 9…
near lossless refers to being 89.65/90.26 = 99.32% of baseline, i'm pretty sure.
I would love to see real examples of what reduced quality means in practice. Are you able to recover a document from the vector in a human readable format? If so, what sort of changes come up? I could imagine a scenario where differences tend to be more substantive than you'd expect because of how less frequent words with fine distinctions in meaning - the very words that make the document special - may be embedded i…
Hey breadislove; amazing article, I’ll be sending mixedbread an email in the morning that may interest you (email will be @pm.me) I have also been working in compression and performance engineering, and managed to get a 99+% compression unlock versus conventional approaches (100+KB down to 1KB) in the scenario of 30 minute massive multiplayer game replays for a “game+engine” I’m developing I think there’s a synergy b…
I would love to see real examples of what reduced quality means in practice. Are you able to recover a document from the vector in a human readable format? If so, what sort of changes come up? I could imagine a scenario where differences tend to be more substantive than you'd expect because of how less frequent words with fine distinctions in meaning - the very words that make the document special - may be embedded i…
Most of the fine distinctions are already lost when a document is processed through a pile of linear algebra to turn it into a fixed-size list of floating-point numbers, as you can see from the NDCG@10. Vector search is not a tool for fine distinctions. It's a tool for reducing a large pile of documents to a smaller selection of candidates, which you can then check individually with some more expensive method.
" A single document produces more then one embedding, depending on the complexity of the document it can produce hundreds or thousands of vectors." That typo up there is kind of endearing in the AI slop era.
Not seeing a typo in your quote. Can you point it out?
In principle, binary x binary should be pretty fast since it just requires bitwise XNOR and popcount/reduction, but in practice it's slow unless you've really optimized it. And, as stated in the article, you'd still be losing a lot of accuracy that way.
Earlier quoted context omitted.
There is, after you define what you’re ready to loose and understand the lossy space. That’s how we came up with mobile cellphones, audio and video codecs etc. Literally powering all modern devices we use.
So then ... "lossy"