Uploaded image for project: 'Red Hat Enterprise Linux AI'
  1. Red Hat Enterprise Linux AI
  2. RHELAI-2503

Implement Ragas as an Evaluation Framework in instructlab/eval

XMLWordPrintable

    • RAG Eval Implementation
    • False
    • Hide

      None

      Show
      None
    • False
    • Not Selected
    • To Do
    • RHELAI-2397 - [eval] Downstream RAGAS as RAG Evaluation framework
    • RHELAI-2397[eval] Downstream RAGAS as RAG Evaluation framework
    • 100% To Do, 0% In Progress, 0% Done

      Goal:

      We want to implement the ability for InstructLab/RHEL AI to have the capacity to evaluate how well our supported models are performing in RAG settings.

       

      Acceptance Criteria:

      The acceptance criteria is a working implementation of a RAG evaluation suite which can be readily used within RHEL AI pipeline through which a model can be passed along with any other necessary values, and a result is returned indicating the model's performance.

       

      Open questions:

      • How well does Ragas perform against the existing evaluation notebook?

              osilkin@redhat.com Oleg Silkin
              osilkin@redhat.com Oleg Silkin
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

                Created:
                Updated: