Uploaded image for project: 'Red Hat Enterprise Linux AI'
  1. Red Hat Enterprise Linux AI
  2. RHELAI-4061

step3: Automate generation of a qna file [L1]

XMLWordPrintable

    • Icon: Feature Feature
    • Resolution: Unresolved
    • Icon: Critical Critical
    • None
    • None
    • Fit and Finish
    • None
    • False
    • Hide

      None

      Show
      None
    • False
    • Not Selected
    • 100% To Do, 0% In Progress, 0% Done

      Feature Overview (mandatory - Complete while in New status)

      Seed example creation (qna file creation) is a crucial piece of the knowledge pipeline. So far, this process has been manual, time-consuming and error prone because users are expected to write yaml files and come up with relevant contexts, qna pairs. 

      Goals (mandatory - Complete while in New status)

      Provide high-level goal statement, providing user context and expected user outcome(s) for this Feature

      • Users can easily run the notebook 
      • Clearly explain the different fields in the qna.yaml (purpose of the domain, document outline, context etc) 
      • Allow for domain, document outline, use case, end-user expertise to be user-input based and we can use them to inform the generation of qna
      • document outline best practices to highlight: 
        • all documents related to a particular topic, pertaining to the same information, or coming from the same source should fall under one document outline and can be used to generate one or more qna.yamls
        • should be a summary of documents 
        • what can fall under the same document outline? FBI cargo theft information for 2014-2019 (because it covers similar information for different years), documentation for iPhone and iPad (similar source, potentially similar information) 
        • what ideally should be under different document outlines? RHEL and RHEL AI/OpenShift AI/OpenShift documentation - likely will cover very different information etc 
        • ideally, we can try to make this process extremely intuitive - rather than using keywords familiar to us, we can ask them questions to inform behavior and generate qna yamls
      • For this flow, we expect users to want to generate one of more qna.yaml files for a set of documents related to one document outline 
      • So, for docs that will be significantly different or goal is to teach model different things, users will have to run through the notebook multiple times. 

      Requirements (mandatory -_ Complete while in Refinement status):
      A list of specific needs, capabilities, or objectives that a Feature must deliver to satisfy the Feature. Some requirements will be flagged as MVP. If an MVP gets shifted, the Feature shifts. If a non MVP requirement slips, it does not shift the feature.
       

      Requirement Notes isMVP?
      Ask for user inputs on: use case, domain, expertise of end-user, stylistic elements, optionally number of contexts   Yes
      Generate a complete qna file - with domain, document outline, follow best practices on minimum numbers of contexts, qna pairs etc    Yes
      Let users review the qna file (or qna pairs) generated    Yes
      Notebook should provide workflows for both: 
      1.  single document
      2. multiple documents
      3. multiple folders of documents
        Yes
      Consider how this particular notebook’s inputs/outputs flow with the next notebook in the process - how is it all put together?
      Ensure file paths, output types etc are consistent
        Yes
      Potentially a demo showing: how will this be run on RHEL AI? with Elyra? Workbench container?   No
      Show how a user would work through a folder of documents - what happens if a user wants to generate a qna file for a collection of input documents?    No
      Provide different paths to get to this outcome: 
      1. User wants their complete qna file auto-generated
      2. User wants their qna file with a select number of contexts 
      3. User wants to select their own contexts and generate a qna file based on that
       
      Guide users through the process - especially if there are different paths provided  
        No

       

      Done - Acceptance Criteria (mandatory - Complete while in Refinement status):
      Acceptance Criteria articulates and defines the value proposition - what is required to meet the goal and intent of this Feature. The Acceptance Criteria provides a detailed definition of scope and the expected outcomes - from a users point of view.

       

      Use Cases - i.e. User Experience & Workflow: (Initial completion while in Refinement status):
      Include use case diagrams, main success scenarios, alternative flow scenarios.
      <your text here>

      Out of Scope {}{}(Initial completion while in Refinement status):
      High-level list of items or persona’s that are out of scope.
      <your text here>

      Documentation Considerations {}{}(Initial completion while in Refinement status):
      Provide information that needs to be considered and planned so that documentation will meet customer needs. If the feature extends existing functionality, provide a link to its current documentation..
      <your text here>

       

      Questions to Answer {}{}(Initial completion while in Refinement status):
      Include a list of refinement / architectural questions that may need to be answered before coding can begin.
      <your text here>

      Background and Strategic Fit (Initial completion while in Refinement status):
      Provide any additional context is needed to frame the feature.
      <your text here>

      Customer Considerations {}{}(Initial completion while in Refinement status):
      Provide any additional customer-specific considerations that must be made when designing and delivering the Feature.
      <your text here>

      Team Sign Off (Completion while in Planning status)

      • All required Epics (known at the time) are linked to the this Feature
      • All required Stories, Tasks (known at the time) for the most immediate Epics have been created and estimated
      • Add - Reviewers name, Team Name
      • Acceptance == Feature as “Ready” - well understood and scope is clear - Acceptance Criteria (scope) is elaborated, well defined, and understood
      • Note: Only set FixVersion/s: on a Feature if the delivery team agrees they have the capacity and have committed that capability for that milestone
      Reviewed By Team Name Accepted Notes
             
             
             
             

       

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

                Created:
                Updated: