AI ワークフローの定義

export const menuSuggestionFlow = ai.defineFlow(
  {
    name: 'menuSuggestionFlow',
  },
  async (restaurantTheme) => {
    const { text } = await ai.generate({
      model: gemini15Flash,
      prompt: `Invent a menu item for a ${restaurantTheme} themed restaurant.`,
    });
    return text;
  }
);

const MenuItemSchema = z.object({
  dishname: z.string(),
  description: z.string(),
});

export const menuSuggestionFlowWithSchema = ai.defineFlow(
  {
    name: 'menuSuggestionFlow',
    inputSchema: z.string(),
    outputSchema: MenuItemSchema,
  },
  async (restaurantTheme) => {
    const { output } = await ai.generate({
      model: gemini15Flash,
      prompt: `Invent a menu item for a ${restaurantTheme} themed restaurant.`,
      output: { schema: MenuItemSchema },
    });
    if (output == null) {
      throw new Error("Response doesn't satisfy schema.");
    }
    return output;
  }
);

export const menuSuggestionFlowMarkdown = ai.defineFlow(
  {
    name: 'menuSuggestionFlow',
    inputSchema: z.string(),
    outputSchema: z.string(),
  },
  async (restaurantTheme) => {
    const { output } = await ai.generate({
      model: gemini15Flash,
      prompt: `Invent a menu item for a ${restaurantTheme} themed restaurant.`,
      output: { schema: MenuItemSchema },
    });
    if (output == null) {
      throw new Error("Response doesn't satisfy schema.");
    }
    return `**${output.dishname}**: ${output.description}`;
  }
);

const { text } = await menuSuggestionFlow('bistro');

const { dishname, description } =
  await menuSuggestionFlowWithSchema('bistro');

export const menuSuggestionStreamingFlow = ai.defineStreamingFlow(
  {
    name: 'menuSuggestionFlow',
    inputSchema: z.string(),
    streamSchema: z.string(),
    outputSchema: z.object({ theme: z.string(), menuItem: z.string() }),
  },
  async (restaurantTheme, streamingCallback) => {
    const response = await ai.generateStream({
      model: gemini15Flash,
      prompt: `Invent a menu item for a ${restaurantTheme} themed restaurant.`,
    });

    if (streamingCallback) {
      for await (const chunk of response.stream) {
        // Here, you could process the chunk in some way before sending it to
        // the output stream via streamingCallback(). In this example, we output
        // the text of the chunk, unmodified.
        streamingCallback(chunk.text);
      }
    }

    return {
      theme: restaurantTheme,
      menuItem: (await response.response).text,
    };
  }
);

const response = menuSuggestionStreamingFlow('Danube');

for await (const chunk of response.stream) {
  console.log('chunk', chunk);
}

const output = await response.output;

genkit flow:run menuSuggestionFlow '"French"'

genkit flow:run menuSuggestionFlow '"French"' -s

genkit start -- tsx --watch src/your-code.ts

const PrixFixeMenuSchema = z.object({
  starter: z.string(),
  soup: z.string(),
  main: z.string(),
  dessert: z.string(),
});

export const complexMenuSuggestionFlow = ai.defineFlow(
  {
    name: 'complexMenuSuggestionFlow',
    inputSchema: z.string(),
    outputSchema: PrixFixeMenuSchema,
  },
  async (theme: string): Promise<z.infer<typeof PrixFixeMenuSchema>> => {
    const chat = ai.chat({ model: gemini15Flash });
    await chat.send('What makes a good prix fixe menu?');
    await chat.send(
      'What are some ingredients, seasonings, and cooking techniques that ' +
        `would work for a ${theme} themed menu?`
    );
    const { output } = await chat.send({
      prompt:
        `Based on our discussion, invent a prix fixe menu for a ${theme} ` +
        'themed restaurant.',
      output: {
        schema: PrixFixeMenuSchema,
      },
    });
    if (!output) {
      throw new Error('No data generated.');
    }
    return output;
  }
);

export const menuQuestionFlow = ai.defineFlow(
  {
    name: 'menuQuestionFlow',
    inputSchema: z.string(),
    outputSchema: z.string(),
  },
  async (input: string): Promise<string> => {
    const menu = await run('retrieve-daily-menu', async (): Promise<string> => {
      // Retrieve today's menu. (This could be a database access or simply
      // fetching the menu from your website.)

      // ...

      return menu;
    });
    const { text } = await ai.generate({
      model: gemini15Flash,
      system: "Help the user answer questions about today's menu.",
      prompt: input,
      docs: [{ content: [{ text: menu }] }],
    });
    return text;
  }
);

import { firebaseAuth } from '@genkit-ai/firebase/auth';
import { onFlow } from '@genkit-ai/firebase/functions';

export const menuSuggestion = onFlow(
  ai,
  {
    name: 'menuSuggestionFlow',
    authPolicy: firebaseAuth((user) => {
      if (!user.email_verified) {
        throw new Error('Verified email required to run flow');
      }
    }),
  },
  async (restaurantTheme) => {
    // ...
  }
);

export const menuSuggestionFlow = ai.defineFlow(
  {
    name: 'menuSuggestionFlow',
  },
  async (restaurantTheme) => {
    // ...
  }
);

ai.startFlowServer({
  flows: [menuSuggestionFlow],
});

curl -X POST "http://localhost:3400/menuSuggestionFlow" \
  -H "Content-Type: application/json"  -d '{"data": "banana"}'

export const flowA = ai.defineFlow({ name: 'flowA' }, async (subject) => {
  // ...
});

export const flowB = ai.defineFlow({ name: 'flowB' }, async (subject) => {
  // ...
});

ai.startFlowServer({
  flows: [flowB],
  port: 4567,
  cors: {
    origin: '*',
  },
});