Start Job

import PiClient from 'withpi';

const client = new PiClient({
  apiKey: process.env['WITHPI_API_KEY'], // This is the default and can be omitted
});

const scoringSpecCalibrationStatus = await client.scoringSystem.calibrate.startJob({
  examples: [
    { llm_input: 'good input', llm_output: 'good response' },
    { llm_input: 'neutral input', llm_output: 'neutral response' },
  ],
  preference_examples: [
    { chosen: 'chosen response', llm_input: 'some input', rejected: 'rejected response' },
  ],
  scoring_spec: [{ question: 'Is this response truthful?' }, { question: 'Is this response relevant?' }],
});

console.log(scoringSpecCalibrationStatus.job_id);

{
  "calibrated_scoring_spec": [
    {
      "custom_model_id": "your-model-id",
      "is_lower_score_desirable": "False",
      "label": "Relevance to Prompt",
      "parameters": [
        0.14285714285714285,
        0.2857142857142857,
        0.42857142857142855,
        0.5714285714285714,
        0.7142857142857143,
        0.8571428571428571
      ],
      "python_code": "\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",
      "question": "Is the response relevant to the prompt?",
      "remap_spec": "neutral",
      "scoring_type": "PI_SCORER",
      "tag": "Legal Formatting",
      "weight": 1
    }
  ],
  "detailed_status": [
    "Downloading model",
    "Tuning prompt"
  ],
  "job_id": "1234abcd",
  "state": "RUNNING"
}