@arizeai/phoenix-evals

npm install @arizeai/phoenix-evals

import { createClassifier } from "@arizeai/phoenix-evals/llm";
import { openai } from "@ai-sdk/openai";

const model = openai("gpt-4o-mini");

const promptTemplate = `
In this task, you will be presented with a query, a reference text and an answer. The answer is
generated to the question based on the reference text. The answer may contain false information. You
must use the reference text to determine if the answer to the question contains false information,
if the answer is a hallucination of facts. Your objective is to determine whether the answer text
contains factual information and is not a hallucination. A 'hallucination' refers to
an answer that is not based on the reference text or assumes information that is not available in
the reference text. Your response should be a single word: either "factual" or "hallucinated", and
it should not include any other text or characters.

    [BEGIN DATA]
    ************
    [Query]: {{input}}
    ************
    [Reference text]: {{reference}}
    ************
    [Answer]: {{output}}
    ************
    [END DATA]

Is the answer above factual or hallucinated based on the query and reference text?
`;

// Create the classifier
const evaluator = await createClassifier({
  model,
  choices: { factual: 1, hallucinated: 0 },
  promptTemplate: promptTemplate,
});

// Use the classifier
const result = await evaluator({
  output: "Arize is not open source.",
  input: "Is Arize Phoenix Open Source?",
  reference: "Arize Phoenix is a platform for building and deploying AI applications. It is open source.",
});

console.log(result);
// Output: { label: "hallucinated", score: 0 }

import { 
  createHallucinationEvaluator,
} from "@arizeai/phoenix-evals/llm";
import { openai } from "@ai-sdk/openai";
import { anthropic } from "@ai-sdk/anthropic";

const model = openai("gpt-4o-mini");
// or use any other AI SDK provider
// const model = anthropic("claude-3-haiku-20240307");

// Hallucination Detection
const hallucinationEvaluator = createHallucinationEvaluator({
  model,
});


// Use the evaluators
const result = await hallucinationEvaluator({
  input: "What is the capital of France?",
  context: "France is a country in Europe. Paris is its capital city.",
  output: "The capital of France is London.",
});

console.log(result);
// Output: { label: "hallucinated", score: 0, explanation: "..." }

npm install @arizeai/phoenix-client

import { createHallucinationEvaluator } from "@arizeai/phoenix-evals/llm";
import { openai } from "@ai-sdk/openai";
import { createDataset } from "@arizeai/phoenix-client/datasets";
import { asEvaluator, runExperiment } from "@arizeai/phoenix-client/experiments";

// Create your evaluator
const hallucinationEvaluator = createHallucinationEvaluator({
  model: openai("gpt-4o-mini"),
});

// Create a dataset for your experiment
const dataset = await createDataset({
  name: "hallucination-eval",
  description: "Evaluate the hallucination of the model",
  examples: [
    {
      input: {
        question: "Is Phoenix Open-Source?",
        context: "Phoenix is Open-Source.",
      },
    },
    // ... more examples
  ],
});

// Define your experimental task
const task = async (example) => {
  // Your AI system's response to the question
  return "Phoenix is not Open-Source";
};

// Create a custom evaluator to validate results
const hallucinationCheck = asEvaluator({
  name: "hallucination",
  kind: "LLM",
  evaluate: async ({ input, output }) => {
    // Use the hallucination evaluator from phoenix-evals
    const result = await hallucinationEvaluator({
      input: input.question,
      context: input.context, // Note: uses 'context' not 'reference'
      output: output,
    });
    
    return result; // Return the evaluation result
  },
});

// Run the experiment with automatic tracing
runExperiment({
  experimentName: "hallucination-eval",
  experimentDescription: "Evaluate the hallucination of the model",
  dataset: dataset,
  task,
  evaluators: [hallucinationCheck],
});