What is a vector database? Why are they critical infrastructure for

No video

What is a vector database? Why are they critical infrastructure for

Рет қаралды 20,053

10 ай бұрын

‪@zackproser‬ , developer advocate at Pinecone.io, explains what #vectors are from the ground up using straightforward examples.
Zack explains why vector databases such as Pinecone enable #semantic search, a core pattern for intelligent applications that understand the intent behind the end user's queries.
Zack also explains how vector databases and the Retrieval Augmented Generation #RAG pattern fixes #llm hallucinations.

Пікірлер: 34

@barkingchicken 9 ай бұрын

Great job explaining and illustrating how RAG helps improve LLM responses and how Pinecone enables RAG at scale.

@AhmedKorany 3 ай бұрын

I really enjoyed your explanation of what is the vector DB is and it’s role in LLM world.

@pinecone-io 3 ай бұрын

Thanks so much!

@saliexplore3094 6 ай бұрын

Your explanation of embedding spaces was on point! Thanks for sharing.

@pinecone-io 6 ай бұрын

Thanks so much for the feedback, and glad it was useful!

@zenfoil 6 ай бұрын

Very great video explaining a complex concept

@alishafii9141 3 ай бұрын

your explanation was great thanks. please keep go on.

@decryptifi2265 2 ай бұрын

Very nice explanation. Thanks Zack for sharing

@pinecone-io Ай бұрын

Glad you found it useful! 🙏

@satish1012 6 күн бұрын

One question What I understand is the plain text is send to LLM and LLM will return the summarized text . But if we are sending confidential info to LLM, then it would be a breach. In that case we can create our own LLM ?

@pieter5466 10 ай бұрын

24:55 Doing this for human written summaries of show X is actually a great side project idea...

@pinecone-io 10 ай бұрын

Totally! If you create something along those lines be sure to let us know

@thelateknights 5 ай бұрын

One question -- it seems to me like each embedding / vector would contain a different number of dimensions. Trying to establish a master-type vector template with every single conceivable dimension represented would involve mainly blank space and be a computational nightmare (hence PCA and other dimensional reduction techniques). So if something complex like "the US Constitution" has thousands of dimensions and something like "grass" has hundreds of dimensions, how can they be compared, seeing as they reside in spaces with different numbers of dimensions? Like, you can't find the distance between an object that resides in 7 dimensional space and an object that resides in 11 dimensional space, right?

@mateuszsmendowski2677 2 ай бұрын

Cool stuff :)

@pinecone-io Ай бұрын

Glad you liked, thanks!

@harshadnaidu4294 6 ай бұрын

what an excellent explanation

@pinecone-io Ай бұрын

So glad it was helpful!

@movieoh5 10 ай бұрын

I like your subtitle style! I can focus on your voice more

@pinecone-io Ай бұрын

Glad you found it useful!

@Gabriel-wl9yy 5 ай бұрын

Is this the official channel?

@pinecone-io Ай бұрын

It is, yes!

@maheshh989 9 ай бұрын

Good content, but the PPT Slides are hazy.. hard to understand

@pinecone-io Ай бұрын

Thanks for the feedback - I'll look to improve that next time around!

@donovanh7878 5 ай бұрын

Unwatchable with the baked-in closed captions. You are also subverting assistive technologies when not using proper closed captions.

@lixpiai 6 ай бұрын

Thanks! But please don't use the on-screen text, it's horrible! Can't watch the video because of it, soooo annoying!!!!

@pinecone-io Ай бұрын

Understood, thanks for the feedback!

@avidlearner8117 10 ай бұрын

Your subtitles, for ADHD people like me, makes it very, very hard to focus on the actual content. To be able to turn it off would be great. Also, it hides content and is unreadable, it’s so quick an$ distracting…. 😢

@JeffreyMyersII 5 ай бұрын

What? Since when did English become an ambiguous language? From my understanding, it's the opposite. Ambiguous languages are those like Semitic languages. Just the fact you can use a different English word to clarify an ambiguous English word is unambiguous.

@djpete2009 Ай бұрын

In terms of machine learning, English is ambiguous. We communicate mostly contextually. If you give one set of prompts to two or three different LLMs, the output will be wildly different. Especially in Image generation and the likes.

@JeffreyMyersII Ай бұрын

@@djpete2009 True, but I wouldn't call English an ambiguous language. Sure, ambiguity exists, but compared to other natural languages, it's rather unambiguous.

@djpete2009 Ай бұрын

@@JeffreyMyersII English is spoken differently in England, NI, Wales and Scotland. The regional differences alone is so variegated its not even the same language. But it is. Intrinsically.

@ytprodata 5 ай бұрын

The baked-in subtitles are SO distracting. Really spoils an otherwise good presentation

@tedk-42 21 күн бұрын

You can turn them off by closing your eyes

@zuowang5185 Ай бұрын

Do I have to use a vector database, how about using gpt to generate a ElasticSearch query and having the proprietary data in ES and then do the factual context padded gen model query @zackproser