Uploaded image for project: 'Red Hat Enterprise Linux AI'
  1. Red Hat Enterprise Linux AI
  2. RHELAI-3638

Use case-driven workflows/profiles

XMLWordPrintable

    • Icon: Epic Epic
    • Resolution: Done
    • Icon: Undefined Undefined
    • None
    • None
    • Fit and Finish
    • Customer use case to help drive building qna etc.
    • False
    • Hide

      None

      Show
      None
    • False
    • Not Selected
    • Done

      Goal:

      Provide high-level goal statement; providing user context and expected user outcome(s) for this Epic. 2-3 sentences... 

      Customers will see the most success if qna.yamls are written (and input docs are selected) keeping in mind the use case the model is being fine-tuned for as well as who is using the application. 

      • Should we ask users to add their use case?
      • Can we customize SDG pipelines based on this?
      • Can we recommend qna based on the use case? 
      • How do we evaluate selected docs/qna based on the use case?

      The user profiles eventually should abstract away details, providing users with the ability to select what they want to achieve at the end of the InstructLab session and allow them to get started, without having to dive deeper into the world of finding and editing yaml files and providing their own values for tasks. This will be especially useful for the citizen developers and, to a certain extent, some data scientists.

      Acceptance Criteria:

      The Acceptance Criteria provides a definition of scope and the expected outcomes - from a users point of view - defines the value proposition

      • <your text here>

       

      Open questions:

      Any additional details, questions or decisions that need to be made/addressed

      • <your text here>

              Unassigned Unassigned
              jepandit@redhat.com Jehlum Vitasta Pandit
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

                Created:
                Updated:
                Resolved: