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

แชร์
ฝัง
  • เผยแพร่เมื่อ 25 ธ.ค. 2024

ความคิดเห็น • 37

  • @MustafaElnagar
    @MustafaElnagar 15 วันที่ผ่านมา +1

    Absolutely love it! Thank you for breaking it all down step by step for us-I truly appreciate the effort you put into this. 😊

  • @barkingchicken
    @barkingchicken ปีที่แล้ว +8

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

  • @saliexplore3094
    @saliexplore3094 11 หลายเดือนก่อน +5

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

    • @pinecone-io
      @pinecone-io  11 หลายเดือนก่อน +1

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

  • @AhmedKorany
    @AhmedKorany 7 หลายเดือนก่อน +4

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

    • @pinecone-io
      @pinecone-io  7 หลายเดือนก่อน +1

      Thanks so much!

  • @zenfoil
    @zenfoil 10 หลายเดือนก่อน +4

    Very great video explaining a complex concept

  • @decryptifi2265
    @decryptifi2265 6 หลายเดือนก่อน

    Very nice explanation. Thanks Zack for sharing

    • @pinecone-io
      @pinecone-io  6 หลายเดือนก่อน

      Glad you found it useful! 🙏

  • @alishafii9141
    @alishafii9141 7 หลายเดือนก่อน +2

    your explanation was great thanks. please keep go on.

  • @thelateknights
    @thelateknights 9 หลายเดือนก่อน +1

    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?

  • @pieter5466
    @pieter5466 ปีที่แล้ว +2

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

    • @pinecone-io
      @pinecone-io  ปีที่แล้ว +1

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

  • @satish1012
    @satish1012 4 หลายเดือนก่อน

    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 ?

  • @harshadnaidu4294
    @harshadnaidu4294 10 หลายเดือนก่อน

    what an excellent explanation

    • @pinecone-io
      @pinecone-io  6 หลายเดือนก่อน

      So glad it was helpful!

  • @SageRap
    @SageRap 3 หลายเดือนก่อน +5

    Those subtitles are so incredibly annoying and entirely unnecessary. TH-cam already has an _optional_ captions function

  • @mateuszsmendowski2677
    @mateuszsmendowski2677 6 หลายเดือนก่อน

    Cool stuff :)

    • @pinecone-io
      @pinecone-io  6 หลายเดือนก่อน

      Glad you liked, thanks!

  • @Gabriel-wl9yy
    @Gabriel-wl9yy 9 หลายเดือนก่อน

    Is this the official channel?

    • @pinecone-io
      @pinecone-io  6 หลายเดือนก่อน

      It is, yes!

  • @movieoh5
    @movieoh5 ปีที่แล้ว +2

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

    • @pinecone-io
      @pinecone-io  6 หลายเดือนก่อน

      Glad you found it useful!

  • @maheshh989
    @maheshh989 ปีที่แล้ว

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

    • @pinecone-io
      @pinecone-io  6 หลายเดือนก่อน

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

  • @donovanj7878
    @donovanj7878 10 หลายเดือนก่อน +2

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

  • @lixpiai
    @lixpiai 10 หลายเดือนก่อน +5

    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
      @pinecone-io  6 หลายเดือนก่อน

      Understood, thanks for the feedback!

  • @avidlearner8117
    @avidlearner8117 ปีที่แล้ว +4

    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
    @JeffreyMyersII 9 หลายเดือนก่อน

    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
      @djpete2009 6 หลายเดือนก่อน

      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
      @JeffreyMyersII 6 หลายเดือนก่อน

      @@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
      @djpete2009 6 หลายเดือนก่อน

      @@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
    @ytprodata 10 หลายเดือนก่อน +3

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

    • @tedk-42
      @tedk-42 5 หลายเดือนก่อน

      You can turn them off by closing your eyes

  • @zuowang5185
    @zuowang5185 6 หลายเดือนก่อน

    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