type ContextEvaluatorType = "entities-recall" | "precision" | "recall" | "relevance";

type ModelGradedData = {
  prompt: string;
  completion: string;
  expectedCompletion?: string;  // Ignored for this evaluator type
}
 
const modelEval = createEvaluator({
  client: oai,
  model: "gpt-4-turbo",
  evaluationDescription: "Rate the response"
});
 
 
await modelEval({
  data: [{
    prompt: "What is TypeScript?",
    completion: "TypeScript is a typed superset of JavaScript"
  }]
});

type AccuracyData = {
  completion: string;
  expectedCompletion: string;  // Required for accuracy comparison
}
 
const accuracyEval = createAccuracyEvaluator({
  weights: { factual: 0.5, semantic: 0.5 }
});
 
await accuracyEval({
  data: [{
    completion: "TypeScript adds types to JavaScript",
    expectedCompletion: "TypeScript is JavaScript with type support"
  }]
});

type ContextData = {
  prompt: string;
  completion: string;
  groundTruth: string;   // Required for context evaluation
  contexts: string[];    // Required for context evaluation
}
 
// Entities Recall - Checks named entities
const entitiesEval = createContextEvaluator({ 
  type: "entities-recall" 
});
 
// Precision - Checks accuracy against context
const precisionEval = createContextEvaluator({ 
  type: "precision" 
});
 
// Recall - Checks information coverage
const recallEval = createContextEvaluator({ 
  type: "recall" 
});
 
// Relevance - Checks contextual relevance
const relevanceEval = createContextEvaluator({ 
  type: "relevance" 
});
 
// Example usage
const data = {
  prompt: "What did the CEO say about Q3?",
  completion: "CEO Jane Smith reported 15% growth in Q3 2023",
  groundTruth: "The CEO announced strong Q3 performance",
  contexts: [
    "CEO Jane Smith presented Q3 results",
    "Company saw 15% revenue growth in Q3 2023"
  ]
};
 
await entitiesEval({ data: [data] });   // Focuses on "Jane Smith", "Q3", "2023"
await precisionEval({ data: [data] });  // Checks factual accuracy
await recallEval({ data: [data] });     // Checks information completeness
await relevanceEval({ data: [data] });  // Checks contextual relevance

// Can combine different evaluator types
const compositeEval = createWeightedEvaluator({
  evaluators: {
    entities: createContextEvaluator({ type: "entities-recall" }),
    accuracy: createAccuracyEvaluator({
      weights: { 
        factual: 0.9,   // High weight on exact matches
        semantic: 0.1    // Low weight on similar terms
      }
    }),
    quality: createEvaluator({
      client: oai,
      model: "gpt-4-turbo",
      evaluationDescription: "Rate quality"
    })
  },
  weights: {
    entities: 0.3,
    accuracy: 0.4,
    quality: 0.3
  }
});
 
// Must provide all required fields for each evaluator type
await compositeEval({
  data: [{
    prompt: "Summarize the earnings call",
    completion: "CEO Jane Smith announced 15% growth",
    expectedCompletion: "The CEO reported strong growth",
    groundTruth: "CEO discussed Q3 performance",
    contexts: [
      "CEO Jane Smith presented Q3 results",
      "Company saw 15% growth in Q3 2023"
    ]
  }]
});