Vector Databases and the Future of AI-powered Search - Sam Partee

[@JesusNoland]

Great speaking skills by Sam. Vector databases are going to partner with LLMs beautifully.

[@helpmathbit3481]

Vector addition is high level term?

[@aayushsmarten]

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?

[@PauloNascimento49]

Great explanation

[@David-hl1wo]

I can't find the blog

[@ozne_2358]

@5:00, bottom of the slide

[@greendsnow]

Good but, how does it compare against the other vector DBs?

[@ArunPunnath]

Is there a possibility if we can get the presentation deck?

[@johncult6948]

SingleStore DB has hybrid search capabilities.

[@SamPartee]

sickkkkk

[@BeTheFeatureNotTheBug]

1 minus cosine similarity? Why?

[@SamPartee]

You're calculating the distance between the vectors. when normalized, 1-distance = how similiar the vectors are.

[@ShaunRoot]

Come on people, his jokes weren't that bad.

[@SamPartee]

yea they were

[@datasciencetoday7127]

ai datab bases