Keep descriptive outputs

[rlancemartin]

answerScore and retrievalScore descriptive outputs can be kept as collapsible columns in the table.

They will be verbose if grade_prompt != "Fast".

You can see the templates here.

GRADE_DOCS_PROMPT will ask the model to explain itself:

template = """ 
    Given the question: \n
    {query}
    Decide if the following retreived context is relevant: \n
    {result}
    Answer in the following format: \n
    "Context is relevant: True or False." \n 
    And explain why it supports or does not support the correct answer: {answer}"""

GRADE_DOCS_PROMPT = PromptTemplate(input_variables=["query", "result", "answer"], template=template)

[vercel]

@barniker is attempting to deploy a commit to the evaluator Team on Vercel.

To accomplish this, @barniker needs to request access to the Team.

Afterwards, an owner of the Team is required to accept their membership request.

If you're already a member of the respective Vercel Team, make sure that your Personal Vercel Account is connected to your GitHub account.