Getting started with Azure Machine Learning Prompt Flow

Поделиться
HTML-код
  • Опубликовано: 21 ноя 2024

Комментарии • 26

  • @shalinisgoel6881
    @shalinisgoel6881 6 месяцев назад +2

    I have never added a comment on any video before, but this is really amazing and exactly what i was looking for. Thanks for sharing. well done.

    • @shepML
      @shepML  6 месяцев назад +1

      Awesome, thank you for the feedback!

  • @christaverner3560
    @christaverner3560 6 месяцев назад +1

    This video is incredible, exactly what I needed and so clearly explained - thank you!

  • @kiesviswa7665
    @kiesviswa7665 6 месяцев назад

    Thanks a lot. Bumped across Prompt flow in Azure AI studio today without having any idea. Loved your video. Can you please tell me why we'd need a text embedding model?

  • @mtomazza
    @mtomazza 7 месяцев назад

    This is extraordinary content. Extremely well done.

  • @hemdesai
    @hemdesai 11 месяцев назад

    This is really fantastic recipe. Thank you for recording this!

  • @davids19850131
    @davids19850131 5 месяцев назад

    Incredible video, thanks. What is an alternative for Azure openAI resource?

  • @ibrahimtaskintr
    @ibrahimtaskintr 2 месяца назад

    Great content thanks. I have a question. I want to forward the result to an endpoint. Can I add a http request after the result ?

  • @YuriFreitasNogara
    @YuriFreitasNogara 6 месяцев назад

    Exactly what i needed. thanks!

  • @santosharakere
    @santosharakere 6 месяцев назад

    Excellent Demo, thanks.

  • @kakanisantosh
    @kakanisantosh 9 месяцев назад +1

    Very nice session
    but one question Can't we use azure alone instead of azure open AI ?
    is there any alternative than using Azure Open AI as its asks for registering etc.,

    • @moeeljawad5361
      @moeeljawad5361 6 месяцев назад

      if you are using a free azure account, then most probably you are not able to create an azure open ai service.

  • @manliomarchica4911
    @manliomarchica4911 5 месяцев назад

    I have a different flows created. No embeddings but a lookup after modify_query_with_history

  • @srinivasanks8431
    @srinivasanks8431 10 месяцев назад

    This is Awesome! Thanks.

  • @abhishekk3971
    @abhishekk3971 3 месяца назад

    what role do I need to be assigned to create a runtime? I have contributor role but the runtime create option is disabled. Please help.

  • @tanishk4960
    @tanishk4960 5 месяцев назад

    how do I update my vector index with additional data?

  • @mpat1811
    @mpat1811 7 месяцев назад

    I used a similar prompt as yours however the model is still answering out of context questions. Is there a way to ensure that the model strictly answers the topics related to the docs in Azure AI?

  • @s.sasisekhar4608
    @s.sasisekhar4608 11 месяцев назад

    Awesome

  • @MicrosoftAzureAI
    @MicrosoftAzureAI 8 месяцев назад

    Will the system automatically change the API versions when necessary?

    • @shepML
      @shepML  8 месяцев назад

      learn.microsoft.com/en-us/azure/ai-services/openai/how-to/working-with-models?tabs=powershell

  • @sarthakkaushik17
    @sarthakkaushik17 11 месяцев назад

    Can we creat a interface for end user to upload a doc and do RAG in Azure ?

    • @shepML
      @shepML  11 месяцев назад

      Yes you can, but you will need to write all the code yourself, security, read the docs in, chunking, run through forms recognizer if needed, process through embedding model, store in vector db etc...

    • @longislandicetea4537
      @longislandicetea4537 7 месяцев назад

      @@shepMLgreat video, do you plan to do any other videos to create a UI and show this flow? It would be really useful

  • @girishkurup3143
    @girishkurup3143 11 месяцев назад

    Is it possible to control the chunking strategy in azure promt

    • @shepML
      @shepML  11 месяцев назад

      Not if you are using the Vector Index Wizard

  • @pranitithape9934
    @pranitithape9934 10 месяцев назад

    Getting this error can you help
    Prompt flow deployment "ml-workspace-service-xyz" of endpoint "ml-workspace-service-xyz" failed
    Creating deployment
    Hide details
    ResourceNotReady: User container has crashed or terminated: Liveness probe failed: