Azure AI Studio - Prompt Flow RAG

Поделиться
HTML-код
  • Опубликовано: 21 ноя 2024

Комментарии • 25

  • @anthonyorzechowski8475
    @anthonyorzechowski8475 3 месяца назад

    Excellent video. Very practical and down to earth for non-CS folks. Great job!

  • @ImranKhan-nc7wp
    @ImranKhan-nc7wp 4 месяца назад

    That was the best tutorial I've watched so far. Thanks a lot.

  • @fabianzambrano7061
    @fabianzambrano7061 Месяц назад +1

    great tutorial, thanks!

  • @gouthamvijay9551
    @gouthamvijay9551 22 дня назад +1

    Excellent video, I have followed the exact same procedure except I did indexing in AI search and used the same in prompt flow. When i ran it by asking a question, the bot is loading forever without replying to the question. Any idea or suggestion?

  • @denizwhite8414
    @denizwhite8414 3 месяца назад +1

    Thank you Mr. Lino

  • @behrouzbeheshti
    @behrouzbeheshti 3 месяца назад +1

    Thank you for the nice video!

  • @Gamezone-kq5sx
    @Gamezone-kq5sx 2 месяца назад +1

    Very informative

  • @pawel8144
    @pawel8144 Месяц назад +1

    Thank you!

  • @TadjouLionelIT
    @TadjouLionelIT 2 месяца назад

    Thanks @LinoTV for this great tutorial. The default number of tokens for chunking is 1024 tokens. Do you have any idea on how to change this value for example to 256 tokens?

    • @LinoTadrosTV
      @LinoTadrosTV  Месяц назад

      Chunking does not require any tokens. The embedding does.

  • @farzadsunavala5553
    @farzadsunavala5553 2 месяца назад +1

    Nice video!

  • @behrouzbeheshti
    @behrouzbeheshti 3 месяца назад +1

    I noticed you had to wait for some time for the indexing to finish. Do you recommend indexing the documents (separately) on Azure Search Service-which should be faster-and then connecting the index? Thanks!

    • @LinoTadrosTV
      @LinoTadrosTV  3 месяца назад +1

      You can, if you would like. I found the speed sporadic based on the state of things in Azure at the time. There is no guarantee that it will be faster executing the index directly.

  • @itpe_exercise
    @itpe_exercise Месяц назад

    very nice. i have a one question. what should i do, if i change the chunking size when the ai search created?

    • @LinoTadrosTV
      @LinoTadrosTV  Месяц назад

      You will have to recreate the index as the 1536 floats that represent each chunk will be different during the embedding stage

  • @SendhurapandiS
    @SendhurapandiS 3 месяца назад +1

    Excellent video!, Is there any limitations to upload file size. example this much mb files only it will support like that.

    • @LinoTadrosTV
      @LinoTadrosTV  3 месяца назад

      I found that based on documentation from the OpenAI assistant that the limit is 20 files and each can not be more than 512 MB. By testing I could not upload a file much smaller than that. So I think it is a work in progress.

  • @yahiachammemi8267
    @yahiachammemi8267 4 месяца назад

    Thank you for sharing !

  • @denizwhite8414
    @denizwhite8414 3 месяца назад +1

    Please upload different videos about prompt flow

  • @Gamezone-kq5sx
    @Gamezone-kq5sx 2 месяца назад +1

    Subscribed🎉🎉

  • @Gamezone-kq5sx
    @Gamezone-kq5sx 2 месяца назад +1

    Please upload more videos

  • @nguyenvanly6958
    @nguyenvanly6958 4 дня назад

    Azure AI is really a pain in ass. Errors, synchronization issues and warnings everywhere. And super expensive. Do Microsoft know that this product is garbage ?

    • @LinoTadrosTV
      @LinoTadrosTV  3 дня назад

      Truth be told, it is unstable. But they are working on it very hard to bring it to a level where it can be solid and productive. Some days I see we are moving forward and some days it goes backward. The price we pay when GENAI is moving at the speed of light and everyone is trying to catch up, even Microsoft