LLM-as-Judge

import { Judge } from 'praisonai';

// Simple accuracy check
const result = await new Judge().run({
  output: "4",
  expected: "4", 
  input: "What is 2+2?"
});
console.log(`Score: ${result.score}/10, Passed: ${result.passed}`);

# Judge with expected output
praisonai eval judge --input "The answer is 4" --expected "4"

# Judge with criteria
praisonai eval judge --input "Hello, how can I help?" --criteria "Response is helpful"

import { Judge } from 'praisonai';

const judge = new Judge();
const result = await judge.run({
  output: "Python is a high-level programming language",
  expected: "Python is a programming language",
  input: "What is Python?"
});

console.log(`Score: ${result.score}/10`);
console.log(`Reasoning: ${result.reasoning}`);

import { Judge } from 'praisonai';

const judge = new Judge({ 
  criteria: "Response is helpful, accurate, and concise" 
});
const result = await judge.run({
  output: "Hello! I'm here to help you with any questions."
});

if (result.passed) {
  console.log("✅ Output meets criteria");
} else {
  console.log("❌ Output needs improvement");
  result.suggestions.forEach(s => console.log(`  • ${s}`));
}

import { RecipeJudge } from 'praisonai';

const judge = new RecipeJudge({ mode: "context" });
const result = await judge.run({
  output: "Final workflow output...",
  expected: "Complete analysis with citations"
});

import { Judge, JudgeConfig } from 'praisonai';

const config: JudgeConfig = {
  model: "gpt-4o",
  temperature: 0.0,
  threshold: 8.0,
  criteria: "Response must be technically accurate"
};

const judge = new Judge({ config });

import { Agent, Judge } from 'praisonai';

const agent = new Agent({
  name: "Math Helper",
  instructions: "You solve math problems"
});

const judge = new Judge();
const result = await judge.run({
  agent,
  input: "What is 15 * 7?",
  expected: "105"
});

console.log(`Agent scored: ${result.score}/10`);

import { Judge, addJudge, getJudge, listJudges } from 'praisonai';

class CodeQualityJudge extends Judge {
  constructor(options = {}) {
    super({
      ...options,
      criteria: "Code is clean, efficient, and well-documented"
    });
  }
}

// Register
addJudge("code_quality", CodeQualityJudge);

// Use
const JudgeClass = getJudge("code_quality");
const judge = new JudgeClass();

// List all judges
console.log(listJudges()); // ['accuracy', 'criteria', 'recipe', 'code_quality']

import { Judge, JudgeCriteriaConfig } from 'praisonai';

const config: JudgeCriteriaConfig = {
  name: "water_flow",
  description: "Evaluate water flow optimization",
  promptTemplate: `Evaluate the water flow configuration:
{output}

Score based on:
- Flow rate efficiency
- Pressure optimization
- Resource conservation

SCORE: [1-10]
REASONING: [explanation]
SUGGESTIONS: [improvements]`,
  scoringDimensions: ["flow_rate", "pressure", "efficiency"],
  threshold: 7.0
};

const judge = new Judge({ criteriaConfig: config });
const result = await judge.run({ 
  output: "Flow rate: 50L/min, Pressure: 2.5 bar" 
});

import { Judge } from 'praisonai';

async function evaluateOutputs() {
  const judge = new Judge({ criteria: "Response is helpful" });
  
  const outputs = [
    "Hello! How can I help?",
    "I don't know.",
    "Let me help you with that!"
  ];
  
  const results = await Promise.all(
    outputs.map(output => judge.runAsync({ output }))
  );
  
  outputs.forEach((output, i) => {
    console.log(`${output.slice(0, 30)}... → ${results[i].score}/10`);
  });
}

evaluateOutputs();