Hi, I wanted to know about pricing of
Hi, I wanted to know about pricing of vectorization:
There are some confusing things in vectorization:
This is for a month:
Let's say I am making 10 queries of some documents where vector stored amount is: 10k and there are 100 those documents. and dimension is 376.
Then how will the queried vector dimension will be calculated:
- if we calculate queried vector dimension of 10 queries for one document then: it will be: (10,000+ 10)376 = 3763760
Now for 100 documents it will be: 3763760100 = 376376000
but now it consider whole 100 documents queries at one level:
total queries will be: (100 ) (10) = 1000
Queries dimension for all 100 : (10,000+1000)*376 = 4136000
Which one is correct ?
6 Replies
Hi @Utkarsh Saxena. Could you please explain what you mean by the document? Are you using the terms document and a Vectorize index interchangeably?
Let's take an example:
I have a array of 10k texts,.
I made vectorID as Hash of that text, so I will have 10k vectorIDs and for each there will 376 dimesnion array i stored.
So total saved vectors will be: 10k.
Now, two cases are let's say i made 10 queries of one text item, then according to formula in documentation it will be:
(10,000+ 10)*376 = 3763760
So, for 100 text element with 10 queries each it will be: 376376000
Another case if take 10 queries of each 100 text at one level it will be:
100(10) = 1000
Queries dimension for all 100 : (10,000+1000)376 = 4136000
Let me know if there is confusion in question! Thanks
If you have a Vectorize index with dimensionality 376 and 10k vectors stored, and if you make 10 queries against this index, the queried vector dims for that index would be:
(10000 + 10) * 376 = 3,763,760 dimensions
Still unsure what you mean by text elements. Do you mean to refer each text element as a separate Vectorize index with 10k vectors each?
My question is simply this, the query dimension formula takes query count as important factor, so simply the query count is aggregated monthly taken as one unit like 1000 queries per month to make formula look like: (10000+1000) * 376 or each query will result in queried dimension and that dimension is multiplied by 1000 like: (10000+1) * 376 * 1000
It will be the former
(10000+1000) * 376
^ This calculation is valid as long as we are scoping these vectors/queries within a single Vectorize index.ok, thanks