Vector Search: The Future of Data Querying Explained | Semantic Searching

แชร์
ฝัง
  • เผยแพร่เมื่อ 11 ม.ค. 2025

ความคิดเห็น • 41

  • @MongoDB
    @MongoDB  ปีที่แล้ว +4

    ✅ Sign-up for a free cluster at → mdb.link/free-1ZIYVNvRVsY
    ✅ Vector Search Documentation→ mdb.link/vector-search-1ZIYVNvRVsY

  • @mzf11125
    @mzf11125 ปีที่แล้ว +39

    Linear Algebra wasn't a waste of time after all

    • @aminemaghous
      @aminemaghous 6 หลายเดือนก่อน

      and Statistics!

  • @HungryWork-q4z
    @HungryWork-q4z ปีที่แล้ว +6

    Two Questions:
    1. I use embedding model from Huggingface, and calculate embeddings myself. Can that be done inside the function that you showed? This requires importing some libs.
    2. Are there other supported vector indexing algorithms? KNN has major issues with performance, I use HNSW (Hierarchical Small World Graph).

  • @istein654
    @istein654 11 หลายเดือนก่อน +1

    Hey there, great content! I code using Pythong but this video provided me direction. Btw, I think there was an up date in the interface of MongoDB and the code for creating a vector search might need to be updated.

  • @CyncSecure-o2y
    @CyncSecure-o2y ปีที่แล้ว +4

    What about searching in multiple fields inside a document? Is it possible to embed and search not only the plot of the movie but 20 more properties?

    • @jainsamyak970
      @jainsamyak970 11 หลายเดือนก่อน

      Hello! Did you find the answer to this ? Because I am also looking for this only. But not able to find anything.

    • @harikrishnansathyan4382
      @harikrishnansathyan4382 11 หลายเดือนก่อน

      Hii.. Any update on this, did you find any way to do this?

    • @bobuputheeckal2693
      @bobuputheeckal2693 11 หลายเดือนก่อน

      Did u guys think of vectorizing all the properties of the document?

  • @PhilippeBazinet
    @PhilippeBazinet ปีที่แล้ว +2

    I am really interested in implementing this in my microservices all written with Go.
    Can all of this be made programmatically with Mongo client for Go?
    Indexes can be created with the client, so I imagine that all of this can be done too.

  • @spectralvalkyrie
    @spectralvalkyrie ปีที่แล้ว +1

    Wow I really want to learn to do this!

  • @donalshijan5615
    @donalshijan5615 11 หลายเดือนก่อน

    I have a question, In this example it's going through plot which was saved as movie data. right? It then queries that plot for similar result, could it be done in a way where it goes through the actual movie and tries to figure out , oh there it is, a boy and a yellow dog, and then return that movie suggesting it might be the one we are referring to.

  • @Wooster23
    @Wooster23 ปีที่แล้ว +2

    Is there a score or some quantified notion of similarity that can be returned with each result?

    • @adityabhaskara581
      @adityabhaskara581 หลายเดือนก่อน

      You can, the relevance score is 1/1+distance. So higher the relevance score, the better is.

  • @hoangng16
    @hoangng16 8 หลายเดือนก่อน +1

    Can we create a new vector search index using code instead of going to the MongoDB UI?

  • @bobuputheeckal2693
    @bobuputheeckal2693 11 หลายเดือนก่อน

    This worked for me. But some searches didn’t work as expected. I asked which is the first Bond movie. It gave me a list of bond movies. I understand the vector is only on plot. But can we vectorize the whole document ?

  • @maverick-n6x
    @maverick-n6x ปีที่แล้ว +1

    cool. i will try it

  • @Konstantin19877
    @Konstantin19877 11 หลายเดือนก่อน

    The search output is an exact text from DB or model twicks it the way it wants?
    Do i understand correct, model is just a search mechanism it does not changes found data it gives it to you as is?

    • @ViciOuSKiddo
      @ViciOuSKiddo 11 หลายเดือนก่อน

      Correct. It's a search mechanism, but it's a "semantic" search engine. The results it returns are exactly what you saved. If you want the models to change it, you have to send it to an LLM to do that and ask it nicely.

  • @LêQuốcVương-c3y
    @LêQuốcVương-c3y 10 หลายเดือนก่อน

    Love you so much

  • @minhkhaitran1447
    @minhkhaitran1447 ปีที่แล้ว +1

    unfortunately, I just follow the guide from the doc, but I get this error |
    MongoServerError: $vectorSearch is not allowed or the syntax is incorrect, see the Atlas documentation for more information
    not sure why is that? anyone know? please help

    • @AndarManik
      @AndarManik ปีที่แล้ว

      Are you using the serverless?

  • @miralirafiyev4646
    @miralirafiyev4646 ปีที่แล้ว +1

    Is it free to use in VPS server ( out of atlas ) where mongodb installed ?

    • @MongoDB
      @MongoDB  ปีที่แล้ว

      This is only available through Atlas currently

  • @emanuelsosa5923
    @emanuelsosa5923 ปีที่แล้ว

    I love that!

  • @bobonaqa
    @bobonaqa ปีที่แล้ว

    So this is only working with dedicated servers and not supported with the serverless option?

  • @arturkre5793
    @arturkre5793 6 หลายเดือนก่อน

    9 months pass and nothing works. My serverless cluster does not support triggers and also there is no search tab in my cluster.

    • @MongoDB
      @MongoDB  6 หลายเดือนก่อน

      You are correct. Currently, serverless clusters have some limitations. If you would like to test out all features you can use a free forever M0 cluster which has these features enabled. Here is a list of the current limitations on serverless clusters: www.mongodb.com/docs/atlas/reference/serverless-instance-limitations/#unsupported-actions

  • @JaimeHRozo
    @JaimeHRozo ปีที่แล้ว

    It does not work on my Atlas cluster. The trigger log is showing the following error message even when uploading only one record:
    [
    "Processing document with id: 573a1390f29313caabcd4eaf",
    "Failed to receive embedding. Status code: 429"
    ]
    How can it be fixed?

    • @stevehoward2749
      @stevehoward2749 ปีที่แล้ว +1

      To me, the 429 looks like you exhausted some free resource, probably with openai.

    • @0xVeeda
      @0xVeeda ปีที่แล้ว

      Seems you got rate limited

    • @Masyukun
      @Masyukun 10 หลายเดือนก่อน

      I recommend re-running the REST call using your favorite client -- cURL, Bruno, Postman, etc. For me, it gave me more information -- I had no credit in my account.

  • @Masyukun
    @Masyukun 10 หลายเดือนก่อน

    Don't set your Trigger to trigger off updates too, or you'll create an infinite loop! Also... it's responseCode, not response_code.

  • @KingAtem1000
    @KingAtem1000 ปีที่แล้ว +1

    Thats pretty cool

  • @rudroroy1054
    @rudroroy1054 10 หลายเดือนก่อน

    This is just too much. I feel like I am so far behind.