Why vector search is not enough and we need BM25

แชร์
ฝัง
  • เผยแพร่เมื่อ 14 พ.ย. 2024

ความคิดเห็น • 59

  • @endre777
    @endre777 หลายเดือนก่อน +14

    Thanks for the explanation, was super clear.
    We just planning to move from vector search to hybrid, and your explanation on BM25 helps a lot to understand what edge cases it can solve. Appreciate a lot!
    Guess we will see a surge on BM25 due to Anthropic Contextual retrieval paper .

  • @ChocolateMilkCultLeader
    @ChocolateMilkCultLeader หลายเดือนก่อน +6

    Great video. This is why when building a search engine- I like to use BM25 for sparse search, and use Vector based search later, once most of the corpus has been filtered out. This allows me to stay precise and efficient.
    One additional thing- people often assume that you need a Vector Db for vector search, but you can do completely without. Just store the vectors in a normal DB.

    • @notsojharedtroll23
      @notsojharedtroll23 หลายเดือนก่อน

      I mean, at the end of the day, the embedsings are data period

    • @stxnw
      @stxnw หลายเดือนก่อน

      It should be the other way around. Most prompts may not have exact matches. Use vector search first, then BM25 and rerank the results.

  • @oncedidactic
    @oncedidactic หลายเดือนก่อน +4

    Nice discussion, thanks! I wish there was more structure to the video so the “why” of the title I served as a main dish, ie let’s define the terms up front, explain how each works, then do why discussion and give a teaser for hybrid approach discussion. Instead there are some gaps and jumps around, which leaves it feeling incomplete or maybe not quite capturing the essence? I have a feeling this is partly a result of editing many clips, so don’t take this feedback too seriously. Cheers

  • @microburn
    @microburn หลายเดือนก่อน +4

    Nice video. I’ve been on the opposite side of the coin, but I like hearing the balanced argument to keep me educated

  • @jameswigglesworth8132
    @jameswigglesworth8132 หลายเดือนก่อน

    Thank you for delving into this important topic!

  • @matveyshishov
    @matveyshishov หลายเดือนก่อน

    Thanks, guys, YT recommended me this video, a very pleasant snippet of explanation.
    Trying to work through your website to understand what the service is.

  • @theepicosityofpizza
    @theepicosityofpizza หลายเดือนก่อน +13

    BM25 doesn't do anything to address any of the issues you bring up at the beginning of the video. TF IDF is dumber than vector search in every aspect. It's just much cheaper to run. Not saying it doesn't have value as part of the toolkit but not sure why you spend the first half setting all thes problems with vector search up as if BM25 addresses any of them.

    • @stxnw
      @stxnw หลายเดือนก่อน

      is English not your first language?

  • @dougunderwood569
    @dougunderwood569 หลายเดือนก่อน

    Great overview, thank you!

  • @aproperhooligan5950
    @aproperhooligan5950 หลายเดือนก่อน

    Excellent presentation/explanation. Very useful. Thank you!

  • @NicolasEmbleton
    @NicolasEmbleton หลายเดือนก่อน

    Wonderful explanation. Thank you.

  • @andydataguy
    @andydataguy หลายเดือนก่อน

    Great video! This is one of the most misunderstood concepts. Will def share this next time it comes up!

  • @roopad8742
    @roopad8742 หลายเดือนก่อน

    This is so easy to understand, thank you!

  • @marka5215
    @marka5215 หลายเดือนก่อน

    Great explanation. Thank you so much!

  • @badashphilosophy9533
    @badashphilosophy9533 หลายเดือนก่อน

    this is an amazing explanation. im an instant follower

  • @andrewwalker8985
    @andrewwalker8985 หลายเดือนก่อน +1

    Why don’t we include semantic dimensions in vectors

  • @weirdsciencetv4999
    @weirdsciencetv4999 หลายเดือนก่อน +1

    Oh man you are amazing!!
    Love channel I subscribed. Please do a video on working with such graphs using a vector database

  • @ashraf_isb
    @ashraf_isb หลายเดือนก่อน

    thats insightful, thank you so much boss

  • @amortalbeing
    @amortalbeing หลายเดือนก่อน

    thanks this was great!

  • @MLGJuggernautgaming
    @MLGJuggernautgaming หลายเดือนก่อน

    I believe a vector search is still better for rag applications. Bm25 is better for more literal matches. Also what does this have to do with LLMs doing math?

  • @broccoli322
    @broccoli322 หลายเดือนก่อน

    Thanks for the video.

  • @MathsSciencePhilosophy
    @MathsSciencePhilosophy หลายเดือนก่อน

    The mathematics behind chatGPT is amazing

  • @BleachWizz
    @BleachWizz หลายเดือนก่อน

    Oh no, this is going to make texts like I do!!!
    ok, drama aside, I do believe this will improve things a lot.
    I still see some caveats that would be left for luck, but huges amount of data might overcome that.
    I do believe we already have enough with GPT and a few previous ideas, still improving the language model itself is always a plus.

  • @Isaacmellojr
    @Isaacmellojr หลายเดือนก่อน

    Otima exemplificacao de como word2vec não é a solucao definitiva.

  • @АндрейАндреевич-з7т
    @АндрейАндреевич-з7т หลายเดือนก่อน

    BM25. Frequency-weighted by sponsored-definition-tag vector search. Yeah google search do that too, you know. If you ever did seo optimization for your website or some kind of smm you know that it works

  • @Howoulduknow841
    @Howoulduknow841 หลายเดือนก่อน

    This is something Anthropic has shared with their contextual retrieval.

  • @pratikerande4808
    @pratikerande4808 หลายเดือนก่อน

    super

  • @shizheliang2679
    @shizheliang2679 25 วันที่ผ่านมา

    wait...I think I am in love...

  • @tempname-dr2bm
    @tempname-dr2bm 26 วันที่ผ่านมา

    Poland mentioned

  • @themax2go
    @themax2go หลายเดือนก่อน +1

    ty for the insight to "pair" numerical rep (vector) w/ MB25... can the same be achieved w/ just using a knowledge graph? i'm experimenting w/ sci/phi triplex... what do you think, do you have any preliminary ideas, or have you already tested it and found using "entities_and_triples" not as effective / not effective at all? 6 mo ago you did a vid on knowledge graphs, i haven't watched it yet, i'll check it out...

  • @bmm8213
    @bmm8213 หลายเดือนก่อน

    Golden nugget

  • @knucker3
    @knucker3 หลายเดือนก่อน +4

    TURN YOUR VOLUME UP

  • @NLPprompter
    @NLPprompter หลายเดือนก่อน

    i love this bot...

  • @815TypeSirius
    @815TypeSirius หลายเดือนก่อน

    But vs is enough to scam dummies and create a market bubble.

  • @ValidatingUsername
    @ValidatingUsername หลายเดือนก่อน

    Try tokenizing engendered languages 😂

  • @rontheoracle
    @rontheoracle หลายเดือนก่อน +12

    Excuse me, but your volume is just too low. Just saying.

    • @martin777xyz
      @martin777xyz หลายเดือนก่อน +22

      Seems fine to me

    • @sladeTek
      @sladeTek หลายเดือนก่อน +12

      No it’s not, your device is the issue

    • @rontheoracle
      @rontheoracle หลายเดือนก่อน

      @@sladeTek It's just this video and a few others that play with very low volume. I try other videos in youtube, in general, they sound acceptably loud. Dunno why.

    • @rontheoracle
      @rontheoracle หลายเดือนก่อน +1

      @@sladeTek Try watching the video in youtube with this title:
      "The Best RAG Technique Yet? Anthropic’s Contextual Retrieval Explained!"
      It is significantly much louder. Just my 2 cents.

    • @csmac3144a
      @csmac3144a หลายเดือนก่อน +1

      Her audio is fine. Turn up your volume.

  • @Ruhgtfo
    @Ruhgtfo หลายเดือนก่อน +1

    Contributed 3blue1brown