embed "what are the feedbacks about the show length"...by "embed" here, does that mean "store"? So this is something I'd store in Vectorize, rather than merely query it against it?
I
jina-embeddings-v3 or mxbai-embed-large-v1 or similar (OpenAI has their own too, basically every big provider does).I
MIIMI
_$gte and $lte matching. Are those operators on the roadmap?MMdimensions and metric parameters when creating an index. The RAG tutorial suggests 768 and cosine, while the Get started suggests a mere 32 and Euclidian. Could anyone help me understand how to choose here? Is it a trade-off of some kind? Thank you.Itext-embedding-3-large model which outputs dimension 3,072, or text-embedding-3-small which outputs 1,536, etc. When you embed 1 text they will give you back an array of <n> numbers where <n> is the dimension. With OpenAI you can request smaller embeddings by specifying the dimension you want, but they'll lose some accuracy as a result.cosine unless the model/provider tells you otherwise (OpenAI recommends cosine for their models). Euclidian also works and will give identical numbers to cosine (if the embeddings are normalized which they often are) but cosine is a bit faster and has some other benefits.MIII1536 for dimension.I1536 then you'll obviously have to somehow reduce it to 1536 but if it's lower then you just have to use the lower dimension. 512 or 1024 is common for open source models.MMIMIMIIIMMII
Represent this sentence for searching relevant passages:IRepresent this sentence for searching relevant passages: give me all the items about toilets and when you query Vectorize it should give you all the toilet-related feedback itemsMMIIMIM
G
Vectorize update: 
V
M
R
A
jina-embeddings-v3mxbai-embed-large-v1$gte$ltedimensionsmetrictext-embedding-3-large3,072text-embedding-3-small1,536cosinecosinecosinecosine1536153615365121024Represent this sentence for searching relevant passages:Represent this sentence for searching relevant passages: give me all the items about toilets