Build Semantic-Search with Elastic search and BERT vector embeddings. ( From scratch )

แชร์
ฝัง
  • เผยแพร่เมื่อ 18 ธ.ค. 2024

ความคิดเห็น • 76

  • @AbidSaudagar
    @AbidSaudagar  ปีที่แล้ว +1

    You can checkout New Advanced Semantic Search Video by using GPT 3.5 Turbo and ElasticSearch: th-cam.com/video/frnKiugyFRI/w-d-xo.html

  • @ganeshkumarmr1
    @ganeshkumarmr1 4 หลายเดือนก่อน +1

    I appreciate your will and dedication to rerecord the video second time

  • @margipatel7768
    @margipatel7768 ปีที่แล้ว +1

    Thank you for sharing! Very clear, thorough, well-paced and learner centered. What an amazing educator!

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      Thank you!! Glad you found it valuable!

  • @sulaiman3975
    @sulaiman3975 ปีที่แล้ว +3

    I think you should consistently upload videos .
    More video like this very helpful ✅
    ❤❤❤🙌🏻

  • @khyr-hl9yt
    @khyr-hl9yt วันที่ผ่านมา +1

    Excellent boss

  • @tejasruthivaranasi8293
    @tejasruthivaranasi8293 2 หลายเดือนก่อน

    SAVIER!!!!!!.. you literally saved my day.........

  • @ephermalinsights
    @ephermalinsights 4 หลายเดือนก่อน

    That's very nice .. glad I searched and got your video

  • @yogeshnaik9803
    @yogeshnaik9803 2 หลายเดือนก่อน

    Thank you so much Abid sir
    This video has been so much helpful
    Please I request keep uploading such project and even some complicated high level machine learning projects ❤

  • @bigm8872
    @bigm8872 ปีที่แล้ว

    Wow! This is amazing work you did here. Your work is very clear, the process well well explained 👏. I was looking into setting up vector embeding search with Elastic and you've clarified the whole process and fundamental understanding of such a solution.

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      Thank You. I'm glad it was helpful!

  • @gustavojuantorena
    @gustavojuantorena 7 วันที่ผ่านมา

    wow this is a great tutorial! Thank you

  • @judepops8015
    @judepops8015 7 หลายเดือนก่อน

    Incredible video, you are amazing! Thank you for the concise outline of the video and explanations of all the key concepts. You have a new sub :)

  • @snehancoghosh7322
    @snehancoghosh7322 6 หลายเดือนก่อน +2

    Hey man great video. it would be amazing if you could teach us how to do the same thing using Opensearch and docker

  • @syedikramuddin7218
    @syedikramuddin7218 ปีที่แล้ว

    GREAT ❤ WELCOME BACK ... BURHANIS...

  • @dkobia
    @dkobia ปีที่แล้ว

    Nicely done. Thanks for the walkthrough

  • @afederici75
    @afederici75 ปีที่แล้ว +1

    This was a great video! Thank you so much. I enjoyed the format (very much to the point, with a nice clarification at the beginning) and you presented it really well. I would love to see a video in the future that maybe explains how picking a custom model could help being charged a lot by ES's ML nodes. In other words, how do you think we could use custom models to be able to use smaller ES ML nodes (e.g. 1GB or 2GB, vs the 4GB ESRE) and be charged less? Thanks again

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว +2

      Glad it was helpful.
      I'll need to look into the smaller node usgae stuff. Never used it before. Will try to make video about it future for sure.
      Thanks for such detailed comment. Really Appreciate it!

  • @mehul4mak
    @mehul4mak ปีที่แล้ว +1

    How to run this as different services for es and streamlit via docker compose? Also if I need to use any other vectordb is there any way to do it?

  • @godfreyogbeide2340
    @godfreyogbeide2340 9 หลายเดือนก่อน +1

    Very good tutorial

    • @godfreyogbeide2340
      @godfreyogbeide2340 9 หลายเดือนก่อน

      Like a semantics search ,as chatting with your Json data privately?. I love ur tutorials

  • @souvikdas4941
    @souvikdas4941 6 หลายเดือนก่อน

    I have watched the video, need advice from you on a similar use case. So I have API log data and for that I want to create a similar search application. Is it possible for the search application to answer questions like the ones below? -
    "List all failed transactions between Merchant_B and any bank.",
    "Find transactions between Merchant_A and Bank_X." etc.

  • @mercy9198
    @mercy9198 ปีที่แล้ว

    great tutorial, wanted to ask if elastic search is the best option for basic l2 or cosine vector similarity insted of some online or offline vector db based methods as it uses approximate nearest neighbours ( ANN ), also this approach cannot be used in cases where false positives are not acceptable such as cache implementation or medical data semantics, can you suggest something that resolves these problem statements 😢

  • @valentind.5398
    @valentind.5398 ปีที่แล้ว

    Thank you for sharing, it really was a pleasure to follow that tutorial. I just had a video recommendation about the latest improvements of ElasticSearch and now I am wondering if that video is still relevant as of today considering the improvements that have been made (ELSER) ?

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      Glad you find the video helpful Valentin.
      Thanks for the suggestion. I'll surely look at ELSER.
      Today I'll be posting a video where I have used OpenAI Embedding in Elasticsearch 8.11 as they have updated the vector dimension limit to 4096.

    • @valentind.5398
      @valentind.5398 ปีที่แล้ว +1

      @@AbidSaudagar Hey Abid, thanks for coming back to me. Regarding ELSER, it requires a ml node so one has to have a licence that most likely costs thousands of dollars so I will stick to vector embedding.
      Bell activated, waiting for the video!

  • @ankurtyagi1440
    @ankurtyagi1440 11 หลายเดือนก่อน

    Superb 😊

  • @thelocalguide4429
    @thelocalguide4429 7 หลายเดือนก่อน

    Hello abid Is it possible to convert a specific field in elasticsearch that already contains data into vector and then use semantic search in it. Great Content

  • @mzsandlist
    @mzsandlist ปีที่แล้ว

    great work amigo
    i just had one question please :
    what should i do in order to search by all the fileds (price , brand , gender ...ect ) ???

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      You can make all field you wanna search for as dense_vector field, then search on all of them separately and then combine the results manually. This is the simplest way.

  • @AustinMark
    @AustinMark ปีที่แล้ว

    great video. I was also wondering what vs code plugin you used that color coded your python indentations?

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว +1

      Thank You Austin.
      Plugin name is indent-rainbow.

  • @leamon9024
    @leamon9024 10 หลายเดือนก่อน

    Hi, thanks for the tutorial. Could you also make one to compare elasticSearch with other vector database solution in terms of semantic/vector search?

    • @AbidSaudagar
      @AbidSaudagar  10 หลายเดือนก่อน

      Great suggestion! I'll surely put it in my next videos list.

  • @clouds187
    @clouds187 ปีที่แล้ว

    Any chance you would show us how to implement this but using cosine similarity? :), Amazing video, helped me learn a lot!!

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว +1

      We just need to change the similarity parameter in indexMapping file.
      I have used l2_norm here. Just change it to "cosine".
      Here is reference link: www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-similarity:~:text=dimensions%20per%20vector.-,cosine,in%20this%0Acase.,-max_inner_product

  • @IIGrudge
    @IIGrudge ปีที่แล้ว

    Phenomenal tutorial! Can you up the audio? It's low.

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      Thanks for kind words and also feedback regarding audio. I have increased audio levels in later videos.

  • @waseem901
    @waseem901 ปีที่แล้ว

    Great video brother👍👌👌

  • @jasleenkalra9009
    @jasleenkalra9009 ปีที่แล้ว

    Great Video 👏Nice to see you back

  • @syednomaan877
    @syednomaan877 ปีที่แล้ว

    Great content

  • @vishnuvallabhyathavakilla2693
    @vishnuvallabhyathavakilla2693 หลายเดือนก่อน

    Can we use multilevel nested JSON as database and implement sematicsearch with elasticsearch??

    • @AbidSaudagar
      @AbidSaudagar  หลายเดือนก่อน

      Yes we can do that.

  • @parvejkhanpathan7792
    @parvejkhanpathan7792 ปีที่แล้ว

    Nice to see you sir

  • @eduardovarela1177
    @eduardovarela1177 ปีที่แล้ว +1

    At final part of code i have this error BadRequestError(400, 'illegal_argument_exception', 'Invalid type: expecting [_doc] but got [_knn_search]')

    • @MuhammadAdnan-tq3fx
      @MuhammadAdnan-tq3fx 10 หลายเดือนก่อน

      same error in my side even i am using 7.17.17 version of es which support knn_search

    • @iamnoob844
      @iamnoob844 3 หลายเดือนก่อน

      In your mapping there are some issues

  • @geethumaria6055
    @geethumaria6055 11 หลายเดือนก่อน

    great video

    • @AbidSaudagar
      @AbidSaudagar  11 หลายเดือนก่อน

      Glad you found it helpful.

  • @varunkalyan3135
    @varunkalyan3135 11 หลายเดือนก่อน

    Totally loved it! Code access link for referral please?

    • @AbidSaudagar
      @AbidSaudagar  10 หลายเดือนก่อน +1

      github.com/abidsaudagar/semantic-search-elastic-search-and-BERT-vector-embedding

  • @Timecapsuletuesday
    @Timecapsuletuesday ปีที่แล้ว

    you didnot provide the repository link to work with, or the dataset path . please share the repository in git. it would be quite helpful coz i am currently working on it

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      Sorry I forgot to add the link. Here is the link.
      github.com/abidsaudagar/semantic-search-elastic-search-and-BERT-vector-embedding

  • @satyashah3045
    @satyashah3045 8 หลายเดือนก่อน

    ObjectApiResponse({'acknowledged': True, 'shards_acknowledged': False, 'index': 'series120'}) I am getting this error
    How can I solve this?

  • @rajeevmishra7486
    @rajeevmishra7486 ปีที่แล้ว

    hi @abid, thanks for the video, can you help me in combining multiple column data for vector search instead of just one as somtimes the description does not contain everything and the customer may look for things from other column. i hope, you got it. please help.

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      This can be done with multiple approaches.
      1. We can aggregate the text data from multiple field into one and then create the vector.
      2. If for some reason you do not want to aggregate the data in one field. We can use LTR plugin: chat.openai.com/share/01ef9614-af6e-47e4-be1d-c0697eee6bd7

  • @chinmayjena2600
    @chinmayjena2600 8 หลายเดือนก่อน

    Sir how to run multiple nodes

    • @AbidSaudagar
      @AbidSaudagar  8 หลายเดือนก่อน +1

      You can use docker to easily run multiple containers of ElasticSearch.
      Without docker is also possible.
      I'm gonna make video about it soon.

    • @chinmayjena2600
      @chinmayjena2600 8 หลายเดือนก่อน

      @@AbidSaudagar thank you sir ....plz upload that video

  • @ibrahimabolel1543
    @ibrahimabolel1543 ปีที่แล้ว

    Appreciate your effort Abid, but when i run the search query code at 28:42 as shown in the video it shows this error :
    "BadRequestError(400, 'search_phase_execution_exception', 'failed to create query: [knn] queries are only supported on [dense_vector] fields')"
    I'm using the same dataset you're using with the same mappings,
    Could you please assist, thank you in advance!

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว +1

      Can you confirm that the field you are searching on, has field type as dense vector.

    • @ibrahimabolel1543
      @ibrahimabolel1543 ปีที่แล้ว

      @@AbidSaudagar Appreciate your response Abid, i managed to solve the snippet error and prepared the index properly but however the code runs without any trouble in the vs code and the Ai model is working but when i launch it using streamlit it pops up the same error regarding the [dense_vector fields] and i've made sure the field of the query is a type of dense vector,.

  • @sameergaikwad222
    @sameergaikwad222 ปีที่แล้ว

    where is the Kaggle file link in description ??

    • @AbidSaudagar
      @AbidSaudagar  ปีที่แล้ว

      github.com/abidsaudagar/semantic-search-elastic-search-and-BERT-vector-embedding
      You can download from my Github.

  • @devanshgoel3433
    @devanshgoel3433 10 หลายเดือนก่อน

    thanks bro!

  • @mm-rr2ei
    @mm-rr2ei 7 หลายเดือนก่อน

    awesome

  • @hemanthkumar4580
    @hemanthkumar4580 ปีที่แล้ว

    👏

  • @AbidSaudagar
    @AbidSaudagar  ปีที่แล้ว

    Coding a privateGPT using LANGCHAIN, HuggingFace Embeddings and FREE LLM
    th-cam.com/video/kUxfr2i2zn8/w-d-xo.html