Uploaded image for project: 'OpenShift Pipelines'
  1. OpenShift Pipelines
  2. SRVKP-9148

Conversational Pipeline Authoring

XMLWordPrintable

    • Icon: Feature Feature
    • Resolution: Unresolved
    • Icon: Major Major
    • None
    • None
    • AI
    • False
    • Hide

      None

      Show
      None
    • False

      Goals

      To lower the learning curve, reduce user errors, and accelerate pipeline modifications by enhancing the OCP Pipeline Builder with generative AI capabilities, allowing OCP users to define pipelines using natural language, removing YAML as a barrier to adoption (e.g., “add a vulnerability scan after the 'build' task”).

      Requirements

      Requirements Notes IS MVP
      • User opens a pipeline in the Builder and interacts with the OpenShift LightSpeed Prompt, the chat automatically uses the open pipeline's content as context.
      • User can input a natural language prompt into OpenShift LightSpeed, aka OLS, (e.g., “add a vulnerability scan after the 'build' task”).
      • OLS successfully parses the prompt and generates a syntactically valid OpenShift Pipelines YAML.
      • OLS provides a relevant, context-aware YAML snippet (or diff) that the user can apply to their pipeline.
      • The generated YAML is presented to the user for review and can be directly loaded into the Builder.
      		    

      Out of scope

      • Fine-Tuned LLM model
      • Provide domain-specific docs for a RAG (Retrieval Augmented Generation) system for pipeline analysis.

      Dependencies

      • OpenShift LightSpeed
      • OpenShift Webconsole UX Design.
      • Tekton MCP Server (if case OLS cannot produce high quality OSP Yaml snippets)

      Assumptions

      Customer Considerations

      • LLM capable to produce OpenShift Pipelines YAML snippets
      • OpenShift LightSpeed enabled with a connection to a LLM

      Done Checklist

      • Requirements are met
      • Non-functional properties of the Feature have been validated (such as performance, resource, UX, security or privacy aspects)
      • User Journey automation is delivered
      • Support and SRE teams are provided with enough skills to support the feature in production environment

              Unassigned Unassigned
              rh-ee-csalinas Carlos Salinas Gancedo
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

                Created:
                Updated: