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

  Рет қаралды 10,569

Pinecone

Pinecone

6 ай бұрын

Zachary Proser, 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: 16
@barkingchicken
@barkingchicken 6 ай бұрын
Great job explaining and illustrating how RAG helps improve LLM responses and how Pinecone enables RAG at scale.
@zenfoil
@zenfoil 2 ай бұрын
Very great video explaining a complex concept
@saliexplore3094
@saliexplore3094 3 ай бұрын
Your explanation of embedding spaces was on point! Thanks for sharing.
@pinecone-io
@pinecone-io 3 ай бұрын
Thanks so much for the feedback, and glad it was useful!
@harshadnaidu4294
@harshadnaidu4294 2 ай бұрын
what an excellent explanation
@pieter5466
@pieter5466 6 ай бұрын
24:55 Doing this for human written summaries of show X is actually a great side project idea...
@pinecone-io
@pinecone-io 6 ай бұрын
Totally! If you create something along those lines be sure to let us know
@movieoh5
@movieoh5 6 ай бұрын
I like your subtitle style! I can focus on your voice more
@thelateknights
@thelateknights 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?
@Gabriel-wl9yy
@Gabriel-wl9yy Ай бұрын
Is this the official channel?
@maheshh989
@maheshh989 5 ай бұрын
Good content, but the PPT Slides are hazy.. hard to understand
@JeffreyMyersII
@JeffreyMyersII 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.
@donovanh7878
@donovanh7878 2 ай бұрын
Unwatchable with the baked-in closed captions. You are also subverting assistive technologies when not using proper closed captions.
@lixpiai
@lixpiai 2 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!!!!
@ytprodata
@ytprodata 2 ай бұрын
The baked-in subtitles are SO distracting. Really spoils an otherwise good presentation
@avidlearner8117
@avidlearner8117 6 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…. 😢
Vector Search: Powering the Next Generation of Applications
38:15
Vectoring Words (Word Embeddings) - Computerphile
16:56
Computerphile
Рет қаралды 273 М.
What Happens If You Trap Smoke In a Ball?
00:58
A4
Рет қаралды 17 МЛН
LangGraph 101: it's better than LangChain
32:26
James Briggs
Рет қаралды 24 М.
What is LangChain?
8:08
IBM Technology
Рет қаралды 93 М.
OpenAI Embeddings and Vector Databases Crash Course
18:41
Adrian Twarog
Рет қаралды 355 М.
The Rise of Vector Data
23:50
Pinecone
Рет қаралды 49 М.
Vector Search Isn’t Enough | BRKFP301H
44:21
Microsoft Developer
Рет қаралды 22 М.
Как открыть дверь в Jaecoo J8? Удобно?🤔😊
0:27
Суворкин Сергей
Рет қаралды 902 М.
КУПИЛ SAMSUNG GALAXY S24 ULTRA ЗА 88000 РУБЛЕЙ!
27:29