Getting started with Azure Machine Learning Prompt Flow

Поділитися
Вставка
  • Опубліковано 29 вер 2024

КОМЕНТАРІ • 26

  • @manliomarchica4911
    @manliomarchica4911 3 місяці тому

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

  • @mpat1811
    @mpat1811 5 місяців тому

    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?

  • @ibrahimtaskintr
    @ibrahimtaskintr 28 днів тому

    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 ?

  • @abhishekk3971
    @abhishekk3971 Місяць тому

    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.

  • @davids19850131
    @davids19850131 3 місяці тому

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

  • @tanishk4960
    @tanishk4960 3 місяці тому

    how do I update my vector index with additional data?

  • @christaverner3560
    @christaverner3560 4 місяці тому +1

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

  • @kakanisantosh
    @kakanisantosh 8 місяців тому +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 4 місяці тому

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

  • @shalinisgoel6881
    @shalinisgoel6881 5 місяців тому +1

    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  5 місяців тому +1

      Awesome, thank you for the feedback!

  • @kiesviswa7665
    @kiesviswa7665 4 місяці тому

    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 5 місяців тому

    This is extraordinary content. Extremely well done.

  • @YuriFreitasNogara
    @YuriFreitasNogara 4 місяці тому

    Exactly what i needed. thanks!

  • @MicrosoftAzureAI
    @MicrosoftAzureAI 6 місяців тому

    Will the system automatically change the API versions when necessary?

    • @shepML
      @shepML  6 місяців тому

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

  • @hemdesai
    @hemdesai 9 місяців тому

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

  • @santosharakere
    @santosharakere 4 місяці тому

    Excellent Demo, thanks.

  • @srinivasanks8431
    @srinivasanks8431 9 місяців тому

    This is Awesome! Thanks.

  • @girishkurup3143
    @girishkurup3143 9 місяців тому

    Is it possible to control the chunking strategy in azure promt

    • @shepML
      @shepML  9 місяців тому

      Not if you are using the Vector Index Wizard

  • @s.sasisekhar4608
    @s.sasisekhar4608 9 місяців тому

    Awesome

  • @sarthakkaushik17
    @sarthakkaushik17 9 місяців тому

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

    • @shepML
      @shepML  9 місяців тому

      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 6 місяців тому

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

  • @pranitithape9934
    @pranitithape9934 8 місяців тому

    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: