كتابة تقييم Genkit

import { z } from "genkit";

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

const DeliciousnessDetectionResponseSchema = z.object({
  reason: z.string(),
  verdict: z.enum(DELICIOUSNESS_VALUES),
});

function getDeliciousnessPrompt(ai: Genkit) {
  return  ai.definePrompt({
      name: 'deliciousnessPrompt',
      input: {
        schema: z.object({
          responseToTest: z.string(),
        }),
      },
      output: {
        schema: 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: {{ responseToTest }}
    Response:
    `
  );
}

import { ModelArgument, z } from 'genkit';
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 and generate an evaluation result
  const deliciousnessPrompt = getDeliciousnessPrompt(ai);
  const response = await deliciousnessPrompt(
    {
      responseToTest: d.output as string,
    },
    {
      model: judgeLlm,
      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 { Genkit, z } from 'genkit';
import { BaseEvalDataPoint, EvaluatorAction } from 'genkit/evaluator';

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

export const BaseEvalDataPoint = z.object({
  testCaseId: z.string(),
  input: z.unknown(),
  output: z.unknown().optional(),
  context: z.array(z.unknown()).optional(),
  reference: z.unknown().optional(),
  testCaseId: z.string().optional(),
  traceIds: z.array(z.string()).optional(),
});

export const EvalResponse = z.object({
  sampleIndex: z.number().optional(),
  testCaseId: z.string(),
  traceId: z.string().optional(),
  spanId: z.string().optional(),
  evaluation: z.union([ScoreSchema, z.array(ScoreSchema)]),
});

const ScoreSchema = z.object({
  id: z.string().describe('Optional ID to differentiate multiple scores').optional(),
  score: z.union([z.number(), z.string(), z.boolean()]).optional(),
  error: z.string().optional(),
  details: z
    .object({
      reasoning: z.string().optional(),
    })
    .passthrough()
    .optional(),
});

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

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

/**
 * Scores whether a datapoint output contains a US Phone number.
 */
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 US_PHONE_REGEX`
    : `Output did not match US_PHONE_REGEX`;
  return {
    score: matches,
    details: { reasoning },
  };
}

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

/**
 * Configures a regex evaluator to match a US phone number.
 */
export function createUSPhoneRegexEvaluator(ai: Genkit): EvaluatorAction {
  return ai.defineEvaluator(
    {
      name: `myCustomEvals/usPhoneRegexEvaluator`,
      displayName: "Regex Match for US PHONE NUMBER",
      definition: "Uses Regex to check if output matches a US phone number",
      isBilled: false,
    },
    async (datapoint: BaseEvalDataPoint) => {
      const score = await usPhoneRegexScore(datapoint);
      return {
        testCaseId: datapoint.testCaseId,
        evaluation: score,
      };
    }
  );
}

import { GenkitPlugin, genkitPlugin } from 'genkit/plugin';

export function myCustomEvals<
  ModelCustomOptions extends z.ZodTypeAny
>(options: {
  judge: ModelArgument<ModelCustomOptions>;
  judgeConfig?: ModelCustomOptions;
}): GenkitPlugin {
  // Define the new plugin
  return genkitPlugin("myCustomEvals", async (ai: Genkit) => {
    const { judge, judgeConfig } = options;

    // The plugin instatiates our custom evaluators within the context
    // of the `ai` object, making them available
    // throughout our Genkit application.
    createDeliciousnessEvaluator(ai, judge, judgeConfig);
    createUSPhoneRegexEvaluator(ai);
  });
}
export default myCustomEvals;

import { gemini15Pro } from '@genkit-ai/googleai';

const ai = genkit({
  plugins: [
    vertexAI(),
    ...
    myCustomEvals({
      judge: gemini15Pro,
    }),
  ],
  ...
});

[
  {
    "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."
  }
]

# Start your genkit runtime
genkit start -- <command to start your app>
genkit eval:run deliciousness_dataset.json --evaluators=myCustomEvals/deliciousnessEvaluator