כתיבת בודק של Genkit

const DELICIOUSNESS_VALUES = ['yes', 'no', 'maybe'] as const;

const DeliciousnessDetectionResponseSchema = z.object({
  reason: z.string(),
  verdict: z.enum(DELICIOUSNESS_VALUES),
});
type DeliciousnessDetectionResponse = z.infer<typeof DeliciousnessDetectionResponseSchema>;

const DELICIOUSNESS_PROMPT = ai.definePrompt(
  {
    name: 'deliciousnessPrompt',
    inputSchema: z.object({
      output: z.string(),
    }),
    outputSchema: DeliciousnessDetectionResponseSchema,
  },
  `You are a food critic. Assess whether the provided output sounds delicious, giving only "yes" (delicious), "no" (not delicious), or "maybe" (undecided) as the verdict.

  Examples:
  Output: Chicken parm sandwich
  Response: { "reason": "A classic and beloved dish.", "verdict": "yes" }

  Output: Boston Logan Airport tarmac
  Response: { "reason": "Not edible.", "verdict": "no" }

  Output: A juicy piece of gossip
  Response: { "reason": "Metaphorically 'tasty' but not food.", "verdict": "maybe" }

  New Output:
  {{output}}
  Response:
  `
);

import { BaseEvalDataPoint, Score } from 'genkit/evaluator';

/**
 * Score an individual test case for delciousness.
 */
export async function deliciousnessScore<
  CustomModelOptions extends z.ZodTypeAny,
>(
  judgeLlm: ModelArgument<CustomModelOptions>,
  dataPoint: BaseEvalDataPoint,
  judgeConfig?: CustomModelOptions
): Promise<Score> {
  const d = dataPoint;
  // Validate the input has required fields
  if (!d.output) {
    throw new Error('Output is required for Deliciousness detection');
  }

  //Hydrate the prompt
  const finalPrompt = DELICIOUSNESS_PROMPT.renderText({
    output: d.output as string,
  });

  // Call the LLM to generate an evaluation result
  const response = await generate({
    model: judgeLlm,
    prompt: finalPrompt,
    config: judgeConfig,
  });

  // Parse the output
  const parsedResponse = response.output;
  if (!parsedResponse) {
    throw new Error(`Unable to parse evaluator response: ${response.text}`);
  }

  // Return a scored response
  return {
    score: parsedResponse.verdict,
    details: { reasoning: parsedResponse.reason },
  };
}

import { BaseEvalDataPoint, EvaluatorAction } from 'genkit/evaluator';

/**
 * Create the Deliciousness evaluator action.
 */
export function createDeliciousnessEvaluator<
  ModelCustomOptions extends z.ZodTypeAny,
>(
  judge: ModelReference<ModelCustomOptions>,
  judgeConfig: z.infer<ModelCustomOptions>
): EvaluatorAction {
  return defineEvaluator(
    {
      name: `myAwesomeEval/deliciousness`,
      displayName: 'Deliciousness',
      definition: 'Determines if output is considered delicous.',
    },
    async (datapoint: BaseEvalDataPoint) => {
      const score = await deliciousnessScore(judge, datapoint, judgeConfig);
      return {
        testCaseId: datapoint.testCaseId,
        evaluation: score,
      };
    }
  );
}

import { BaseEvalDataPoint, Score } from 'genkit/evaluator';

const US_PHONE_REGEX =
  /^[\+]?[(]?[0-9]{3}[)]?[-\s\.]?[0-9]{3}[-\s\.]?[0-9]{4}$/i;

/**
 * Scores whether an individual datapoint matches a US Phone Regex.
 */
export async function usPhoneRegexScore(
  dataPoint: BaseEvalDataPoint
): Promise<Score> {
  const d = dataPoint;
  if (!d.output || typeof d.output !== 'string') {
    throw new Error('String output is required for regex matching');
  }
  const matches = US_PHONE_REGEX.test(d.output as string);
  const reasoning = matches
    ? `Output matched regex ${regex.source}`
    : `Output did not match regex ${regex.source}`;
  return {
    score: matches,
    details: { reasoning },
  };
}

import { BaseEvalDataPoint, EvaluatorAction } from 'genkit/evaluator';

/**
 * Configures a regex evaluator to match a US phone number.
 */
export function createUSPhoneRegexEvaluator(
  metrics: RegexMetric[]
): EvaluatorAction[] {
  return metrics.map((metric) => {
    const regexMetric = metric as RegexMetric;
    return defineEvaluator(
      {
        name: `myAwesomeEval/${metric.name.toLocaleLowerCase()}`,
        displayName: 'Regex Match',
        definition:
          'Runs the output against a regex and responds with 1 if a match is found and 0 otherwise.',
        isBilled: false,
      },
      async (datapoint: BaseEvalDataPoint) => {
        const score = await regexMatchScore(datapoint, regexMetric.regex);
        return fillScores(datapoint, score);
      }
    );
  });
}

export enum MyAwesomeMetric {
  WORD_COUNT = 'WORD_COUNT',
  US_PHONE_REGEX_MATCH = 'US_PHONE_REGEX_MATCH',
}

export interface PluginOptions {
  metrics?: Array<MyAwesomeMetric>;
}

export enum MyAwesomeMetric {
  DELICIOUSNESS = 'DELICIOUSNESS',
  US_PHONE_REGEX_MATCH = 'US_PHONE_REGEX_MATCH',
}

export interface PluginOptions<ModelCustomOptions extends z.ZodTypeAny> {
  judge: ModelReference<ModelCustomOptions>;
  judgeConfig?: z.infer<ModelCustomOptions>;
  metrics?: Array<MyAwesomeMetric>;
}

export function myAwesomeEval<ModelCustomOptions extends z.ZodTypeAny>(
  options: PluginOptions<ModelCustomOptions>
): PluginProvider {
  // Define the new plugin
  const plugin = (options?: MyPluginOptions<ModelCustomOptions>) => {
    return genkitPlugin(
    'myAwesomeEval',
    async (ai: Genkit) => {
      const { judge, judgeConfig, metrics } = options;
      const evaluators: EvaluatorAction[] = metrics.map((metric) => {
        switch (metric) {
          case DELICIOUSNESS:
            // This evaluator requires an LLM as judge
            return createDeliciousnessEvaluator(ai, judge, judgeConfig);
          case US_PHONE_REGEX_MATCH:
            // This evaluator does not require an LLM
            return createUSPhoneRegexEvaluator();
        }
      });
      return { evaluators };
    })
  }
  // Create the plugin with the passed options
  return plugin(options);
}
export default myAwesomeEval;

import { gemini15Flash } from '@genkit-ai/googleai';

const ai = genkit({
  plugins: [
    ...
    myAwesomeEval({
      judge: gemini15Flash,
      judgeConfig: {
        safetySettings: [
          {
            category: 'HARM_CATEGORY_HATE_SPEECH',
            threshold: 'BLOCK_NONE',
          },
          {
            category: 'HARM_CATEGORY_DANGEROUS_CONTENT',
            threshold: 'BLOCK_NONE',
          },
          {
            category: 'HARM_CATEGORY_HARASSMENT',
            threshold: 'BLOCK_NONE',
          },
          {
            category: 'HARM_CATEGORY_SEXUALLY_EXPLICIT',
            threshold: 'BLOCK_NONE',
          },
        ],
      },
      metrics: [
        MyAwesomeMetric.DELICIOUSNESS,
        MyAwesomeMetric.US_PHONE_REGEX_MATCH
      ],
    }),
  ],
  ...
});

[
  {
    "testCaseId": "delicous_mango",
    "input": "What is a super delicious fruit",
    "output": "A perfectly ripe mango – sweet, juicy, and with a hint of tropical sunshine."
  },
  {
    "testCaseId": "disgusting_soggy_cereal",
    "input": "What is something that is tasty when fresh but less tasty after some time?",
    "output": "Stale, flavorless cereal that's been sitting in the box too long."
  }
]

genkit eval:run deliciousness_dataset.json

genkit start