Generate
Generates a scoring spec
Authorizations
Body
The application description to generate a scoring spec for.
"Write a children's story communicating a simple life lesson."
The number of questions that the generated scoring system should contain. If <= 0, then the number is auto selected.
"10"
If true, try to generate python code for the generated questions.
false
Response
The yes/no question to ask Pi Scoring System.
"Is the response relevant to the prompt?"
The ID of the custom model associated with the CUSTOM_MODEL_SCORER scoring_type.
"your-model-id"
Indicates whether a lower score represents a better outcome (e.g., fewer errors, less toxicity)
"False"
The label of the question.
"Relevance to Prompt"
The learned parameters for the scoring question define a piecewise linear interpolation over the range [0, 1]. This transformation adjusts the score distribution to better match your preferences—for example, by pulling scores below 0.5 closer to 0, and scores above 0.5 closer to 1.
[
0.14285714285714285,
0.2857142857142857,
0.42857142857142855,
0.5714285714285714,
0.7142857142857143,
0.8571428571428571
]
The PYTHON code associated with the PYTHON_CODE scoring_type.
"\ndef score(response_text: str, input_text: str, kwargs: dict) -> dict:\n word_count = len(response_text.split())\n if word_count > 10:\n return {\"score\": 0.2, \"explanation\": \"Response has more than 10 words\"}\n elif word_count > 5:\n return{\"score\": 0.6, \"explanation\": \"Response has more than 5 words\"}\n else:\n return {\"score\": 1, \"explanation\": \"Response has 5 or fewer words\"}\n"
The type of scoring performed for this question. Default: PI_SCORER.
PI_SCORER
, PYTHON_CODE
, CUSTOM_MODEL_SCORER
"PI_SCORER"
The tag or the group to which this question belongs.
"Legal Formatting"
The weight of the question which reflects its relative importance. The sum of question weights will be normalized to one internally. A higher weight counts for more when aggregating this subdimension into the parent dimension.
1