Can we search through the documents "which targets specific information"? Suppose, I want to search for the articles which talk about "young males in their 20s". Now, that doesn't necessarily look for that phrase because it is unlikely that it will be the case. Then how would I search like that? Should I pass metadata? How to pass additional information that can be used to filter the documents for the retrival?
Great speaking skills by Sam. Vector databases are going to partner with LLMs beautifully.
Good but, how does it compare against the other vector DBs?
I can't find the blog
@5:00, bottom of the slide
Can we search through the documents "which targets specific information"? Suppose, I want to search for the articles which talk about "young males in their 20s". Now, that doesn't necessarily look for that phrase because it is unlikely that it will be the case. Then how would I search like that? Should I pass metadata? How to pass additional information that can be used to filter the documents for the retrival?
Is there a possibility if we can get the presentation deck?
Vector addition is high level term?
Come on people, his jokes weren't that bad.
yea they were
Great explanation
SingleStore DB has hybrid search capabilities.
sickkkkk
1 minus cosine similarity? Why?
You're calculating the distance between the vectors. when normalized, 1-distance = how similiar the vectors are.
ai datab bases