SvelteKit tutorial

In this tutorial, you’ll build Bargain Chef, a full-stack SvelteKit app where one SvelteKit project serves both your Genkit backend and the UI. It uses two AI patterns Genkit simplifies: streaming structured output and tool calling.

What you’ll build

The user types what they’re craving, Gemini drafts a recipe, and the model calls a tool to look up mock grocery sale prices so it can prefer on-sale ingredients. The recipe streams into the UI incrementally, so users see progress before the full recipe is ready.

You can find the finished code on GitHub.

Keeping the backend and UI in one project gives you shared TypeScript types, no CORS configuration during local development, and a single deployment path.

Already have a standalone Genkit backend?

Follow this tutorial for the SvelteKit UI structure, but point streamFlow at your existing backend route instead of the SvelteKit endpoint. See

Use a standalone backend instead

for the small changes required.

Prerequisites

• Node.js v20 or later
• npm
• Familiarity with SvelteKit and TypeScript

Set up the application

Create the SvelteKit project

npm

npx sv create my-genkit-sveltekit
cd my-genkit-sveltekit

pnpm

pnpm dlx sv create my-genkit-sveltekit
cd my-genkit-sveltekit

yarn

yarn dlx sv create my-genkit-sveltekit
cd my-genkit-sveltekit

bun

bunx sv create my-genkit-sveltekit
cd my-genkit-sveltekit

When prompted, pick the SvelteKit minimal template and choose Yes, using TypeScript syntax for type checking.

Install packages

npm

npm install genkit @genkit-ai/google-genai @genkit-ai/fetch
npm install -D genkit-cli tsx

pnpm

pnpm add genkit @genkit-ai/google-genai @genkit-ai/fetch
pnpm add -D genkit-cli tsx

yarn

yarn add genkit @genkit-ai/google-genai @genkit-ai/fetch
yarn add -D genkit-cli tsx

bun

bun add genkit @genkit-ai/google-genai @genkit-ai/fetch
bun add -d genkit-cli tsx

These packages include:

• genkit: Core Genkit SDK.
• @genkit-ai/google-genai: Plugin that connects Genkit to Google’s Gemini models.
• @genkit-ai/fetch: Wraps a Genkit flow as a Web Request/Response handler, which is exactly what SvelteKit endpoints use.
• genkit-cli: Genkit CLI tool that enables local testing and observability.

Configure a model API key

This tutorial uses the Gemini API from Google AI Studio.

Get a Gemini API Key

Set the GEMINI_API_KEY environment variable to your key:

export GEMINI_API_KEY=<your API key>

Prefer a different model?

This tutorial uses Gemini, but Genkit also supports Anthropic (Claude), OpenAI, and many other model providers.

Create the backend

The backend prompts Gemini to draft a recipe, lets the model call a tool to look up mock grocery sale prices, and streams the partial recipe back to the browser as it’s generated.

The core AI logic lives in a flow, which is a Genkit-managed function that adds observability, type safety, and tooling integration on top of a regular async function.

You’ll build the backend in four parts:

1. Initialize Genkit and register Gemini as the model provider.
2. Define a tool the model can call to fetch sale prices.
3. Describe the recipe shape with Zod so Genkit can validate the final output and stream partial recipe chunks.
4. Define the flow that ties everything together.

Create src/lib/genkit/bargainChefFlow.ts:

src/lib/genkit/bargainChefFlow.ts

import { googleAI } from '@genkit-ai/google-genai';
import { genkit, z } from 'genkit';

const ai = genkit({
  plugins: [googleAI()],
});

const getIngredientsOnSale = ai.defineTool(
  {
    name: 'getIngredientsOnSale',
    description:
      'Returns the ingredients on sale at the local grocery store, with prices. The sale set differs between weekdays and weekends.',
    inputSchema: z.object({
      dayType: z
        .enum(['weekday', 'weekend'])
        .describe('Whether to fetch weekday or weekend sale prices.'),
    }),
    outputSchema: z.array(
      z.object({
        name: z.string(),
        price: z.string(),
      }),
    ),
  },
  async ({ dayType }) => {
    // Mock data: in a real app, query a pricing database.
    return dayType === 'weekend'
      ? [
          { name: 'chicken breast', price: '$2.99/lb' },
          { name: 'pasta', price: '$0.79' },
          { name: 'canned tomatoes', price: '$0.99' },
          { name: 'garlic', price: '$0.50 / head' },
          { name: 'olive oil', price: '$6.99' },
        ]
      : [
          { name: 'eggs', price: '$3.49 / dozen' },
          { name: 'spinach', price: '$1.99' },
          { name: 'parmesan', price: '$4.99' },
          { name: 'lemons', price: '$0.50 each' },
          { name: 'rice', price: '$2.49' },
          { name: 'butter', price: '$3.99' },
        ];
  },
);

const BargainChefInputSchema = z.object({
  craving: z.string().describe('What the user feels like eating right now.'),
});

const RecipeSchema = z.object({
  title: z.string(),
  description: z.string(),
  servings: z.number(),
  ingredients: z.array(
    z.object({
      name: z.string(),
      quantity: z.string(),
      onSale: z.boolean(),
    }),
  ),
  steps: z.array(z.string()),
});

// Exported for the frontend to import as types.
export type BargainChefInput = z.infer<typeof BargainChefInputSchema>;
export type Recipe = z.infer<typeof RecipeSchema>;
export type PartialRecipe = Partial<Recipe>;

export const bargainChefFlow = ai.defineFlow(
  {
    name: 'bargainChefFlow',
    inputSchema: BargainChefInputSchema,
    outputSchema: RecipeSchema,
    streamSchema: RecipeSchema.partial(),
  },
  async ({ craving }, { sendChunk }) => {
    const today = new Date().toLocaleDateString('en-US', { weekday: 'long' });

    const { stream, response } = ai.generateStream({
      model: googleAI.model('gemini-flash-latest', {
        temperature: 0.7,
        thinkingConfig: { thinkingLevel: 'MINIMAL' },
      }),
      prompt: `Today is ${today}. The user is craving: ${craving}.

Call the getIngredientsOnSale tool with the dayType that matches today. Saturday and Sunday are weekends; all other days are weekdays. Then propose ONE recipe that takes advantage of those deals. For each ingredient, set onSale=true if it appears in the tool's response, false otherwise.`,
      tools: [getIngredientsOnSale],
      output: { schema: RecipeSchema },
    });

    for await (const chunk of stream) {
      if (chunk.output) sendChunk(chunk.output);
    }

    const { output } = await response;
    if (!output) throw new Error('Failed to generate recipe');
    return output;
  },
);

A few details are worth noting before you connect the UI:

• Final output and streamed chunks: outputSchema is the complete recipe the flow returns at the end. streamSchema is the same shape with every field optional (RecipeSchema.partial()), because early chunks might only include the title or description.
• Shared TypeScript types: Recipe, PartialRecipe, and BargainChefInput are inferred from the Zod schemas with z.infer<...> and re-exported for the SvelteKit page to import. Because the page imports them with import type, Genkit and the model plugin stay out of the browser bundle.
• The getIngredientsOnSale tool: The model decides when to call it based on the prompt, and the typed inputSchema forces the model to pass dayType: 'weekday' or 'weekend'. In a real app, the tool would query a pricing database, inventory system, or third-party API.
• sendChunk: Each call pushes the latest partial recipe to the browser, giving the UI a typed view of the generated JSON as it grows.

Add the SvelteKit endpoint

Expose the flow as a SvelteKit POST endpoint by creating src/routes/api/bargainChefFlow/+server.ts:

src/routes/api/bargainChefFlow/+server.ts

import type { RequestHandler } from './$types';
import { fetchHandler } from '@genkit-ai/fetch';
import { bargainChefFlow } from '$lib/genkit/bargainChefFlow';

const handle = fetchHandler(bargainChefFlow);

export const POST: RequestHandler = ({ request }) => handle(request);

SvelteKit endpoints receive a standard Web Request and return a Response, so fetchHandler wraps the flow directly. When the browser sends Accept: text/event-stream, the handler streams partial recipe chunks back as server-sent events.

Check the project layout

Verify that your project layout matches the structure below:

• package.json
• svelte.config.js
• … other SvelteKit config files
• Directorysrc

  • Directorylib

    • Directorygenkit

      • bargainChefFlow.ts
  • Directoryroutes

    • Directoryapi

      • DirectorybargainChefFlow

        • +server.ts
    • +page.svelte
  • … other SvelteKit source files

Optional: install the Genkit agent skills

If you’re coding with an AI assistant, install the Genkit Agent Skills so it has structured guidance on Genkit APIs, patterns, and common errors:

npx skills add genkit-ai/skills

See Develop with AI for tool-specific installation instructions.

Build the SvelteKit UI

The SvelteKit page calls the flow with streamFlow from genkit/beta/client, then stores each partial recipe in a $state rune so the template re-renders as fields arrive.

Update the page component

Replace the contents of src/routes/+page.svelte with the following. The page imports the flow’s TypeScript types with import type, so the UI and backend stay in sync without adding server code to the browser bundle:

src/routes/+page.svelte

<script lang="ts">
  import { streamFlow } from 'genkit/beta/client';
  import type {
    BargainChefInput,
    PartialRecipe,
    Recipe,
  } from '$lib/genkit/bargainChefFlow';

  // API route where your bargainChefFlow is served.
  const FLOW_URL = '/api/bargainChefFlow';

  let craving = $state('something warm with chicken');
  let recipe = $state<PartialRecipe | null>(null);
  let isStreaming = $state(false);

  async function generateRecipe() {
    if (!craving.trim()) return;
    recipe = null;
    isStreaming = true;
    try {
      const input: BargainChefInput = { craving };
      // streamFlow's generics are <FinalOutput, StreamChunk>.
      const result = streamFlow<Recipe, PartialRecipe>({
        url: FLOW_URL,
        input,
      });
      // result.stream is an async iterable of partial recipes.
      // Each chunk is the accumulated output so far.
      for await (const partial of result.stream) {
        recipe = partial;
      }
      // Wait for the final validated output and surface any errors.
      await result.output;
    } catch (err) {
      console.error('Failed to generate recipe', err);
    } finally {
      isStreaming = false;
    }
  }
</script>

<main>
  <h1>Bargain Chef</h1>
  <p class="tagline">Tell me what you feel like eating and I'll suggest a recipe built around today's grocery deals.</p>

  <form class="prompt" onsubmit={(e) => { e.preventDefault(); generateRecipe(); }}>
    <input
      type="text"
      bind:value={craving}
      name="craving"
      placeholder="What are you in the mood for?"
      disabled={isStreaming}
    />
    <button type="submit" disabled={isStreaming}>
      {isStreaming ? 'Cooking…' : 'Suggest a recipe'}
    </button>
  </form>

  {#if recipe}
    <article>
      {#if recipe.title}<h2>{recipe.title}</h2>{/if}
      {#if recipe.description}<p class="description">{recipe.description}</p>{/if}
      {#if recipe.servings}<p class="serves"><strong>Serves:</strong> {recipe.servings}</p>{/if}

      {#if recipe.ingredients?.length}
        <h3>Ingredients</h3>
        <ul class="ingredients">
          {#each recipe.ingredients as ing}
            <li>
              {ing.quantity} {ing.name}
              {#if ing.onSale}<span class="badge">on sale</span>{/if}
            </li>
          {/each}
        </ul>
      {/if}

      {#if recipe.steps?.length}
        <h3>Steps</h3>
        <ol class="steps">
          {#each recipe.steps as step}
            <li>{step}</li>
          {/each}
        </ol>
      {/if}
    </article>
  {/if}
</main>

streamFlow returns an object with two useful properties: stream, an async iterable of partial recipe objects, and output, a promise that resolves with the final validated recipe. The component stores each partial recipe in a $state rune, so the template re-renders on every update.

Each recipe section is wrapped in {#if} so it only renders after that field arrives in the stream. The result is a UI that fills in progressively: title first, then description, then ingredients, then steps. Wrapping the input and button in a <form> lets the user submit by pressing Enter, and the onsubmit handler calls preventDefault() so the browser doesn’t reload the page before starting the streaming request.

Add styles

Add the following styles to the bottom of src/routes/+page.svelte:

src/routes/+page.svelte

<style>
  :global(body) {
    font-family:
      -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue',
      Arial, sans-serif;
    color: #1a1a1a;
    background: #fafafa;
    min-height: 100vh;
    margin: 0;
  }

  main {
    max-width: 640px;
    margin: 0 auto;
    padding: 3rem 1.5rem;
  }

  h1 {
    font-size: 2rem;
    margin: 0 0 0.25rem;
    letter-spacing: -0.01em;
  }

  .tagline {
    color: #555;
    margin: 0 0 2rem;
  }

  .prompt {
    display: flex;
    gap: 0.5rem;
    margin-bottom: 2.5rem;
  }

  .prompt input {
    flex: 1;
    font: inherit;
    font-size: 1rem;
    padding: 0.75rem 1rem;
    border: 1px solid #d0d0d0;
    border-radius: 8px;
    background: #fff;
    transition: border-color 120ms ease, box-shadow 120ms ease;
  }

  .prompt input:focus {
    outline: none;
    border-color: #2563eb;
    box-shadow: 0 0 0 3px rgba(37, 99, 235, 0.15);
  }

  .prompt input:disabled {
    background: #f1f1f1;
    color: #888;
  }

  .prompt button {
    font: inherit;
    font-size: 1rem;
    font-weight: 500;
    padding: 0.75rem 1.25rem;
    border: 0;
    border-radius: 8px;
    background: #1a1a1a;
    color: #fff;
    cursor: pointer;
    transition: background 120ms ease;
    white-space: nowrap;
  }

  .prompt button:hover:not(:disabled) {
    background: #2563eb;
  }

  .prompt button:disabled {
    background: #999;
    cursor: not-allowed;
  }

  article {
    background: #fff;
    border: 1px solid #e5e5e5;
    border-radius: 12px;
    padding: 1.5rem 1.75rem;
  }

  article h2 {
    font-size: 1.5rem;
    margin: 0 0 0.5rem;
  }

  article h3 {
    font-size: 1rem;
    text-transform: uppercase;
    letter-spacing: 0.06em;
    color: #666;
    margin: 1.5rem 0 0.5rem;
  }

  .description {
    color: #444;
    margin: 0 0 1rem;
  }

  .serves {
    color: #555;
    margin: 0;
    font-size: 0.95rem;
  }

  .ingredients,
  .steps {
    padding-left: 1.25rem;
    line-height: 1.6;
  }

  .ingredients li {
    margin-bottom: 0.25rem;
  }

  .steps li {
    margin-bottom: 0.5rem;
  }

  .badge {
    display: inline-block;
    margin-left: 0.4rem;
    padding: 0.05rem 0.5rem;
    font-size: 0.75rem;
    font-weight: 500;
    background: #e8f5e9;
    color: #2e7d32;
    border-radius: 999px;
  }

  @media (max-width: 480px) {
    .prompt {
      flex-direction: column;
    }
    .prompt button {
      width: 100%;
    }
  }
</style>

Run the app

Start the SvelteKit development server:

npm

npm run dev

pnpm

pnpm run dev

yarn

yarn dev

bun

bun run dev

Open http://localhost:5173, enter a craving like something warm with chicken, and submit. The title should appear first, followed by the description, ingredients, and steps. Ingredients that the model sourced from the getIngredientsOnSale tool will show an “on sale” badge.

Test and inspect the app

The Genkit Developer UI is a local console for testing flows and inspecting traces. It records every tool call, model invocation, and streamed chunk, so you can see what the model called, what it received back, and how the recipe was assembled.

Start the Developer UI from your project root:

npm

npx genkit start -- tsx --watch src/lib/genkit/bargainChefFlow.ts

pnpm

pnpm dlx genkit start -- tsx --watch src/lib/genkit/bargainChefFlow.ts

yarn

yarn dlx genkit start -- tsx --watch src/lib/genkit/bargainChefFlow.ts

bun

bunx genkit start -- tsx --watch src/lib/genkit/bargainChefFlow.ts

This launches the Developer UI at http://localhost:4000 by default.

Add a script

To make starting the Developer UI easier, add the above command to your project’s scripts, such as in package.json.

In the Developer UI:

• The Traces tab shows every invocation of bargainChefFlow, including the ones triggered by your SvelteKit app. Open one and you’ll see the getIngredientsOnSale tool call with the dayType the model chose, the model invocation, and each streamed chunk that the browser received.

• The Flows tab lets you run bargainChefFlow directly with custom input, which is useful for iterating on the prompt without round-tripping through the UI. Try sample input like:

  { "craving": "something warm with chicken" }

Or call the flow with curl

You can also test the SvelteKit endpoint directly. Use the -N flag and an Accept: text/event-stream header to consume the streamed response:

curl -N -X POST http://localhost:5173/api/bargainChefFlow \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -d '{"data":{"craving":"something warm with chicken"}}'

The { "data": ... } wrapper is required: Genkit’s HTTP handler reads the flow input from the request body’s data field.

The response arrives as a series of SSE data: events, each containing the partial recipe accumulated so far.

Use a standalone backend instead

This tutorial uses a SvelteKit server endpoint for the shortest first-run path. To use the same UI against a standalone backend instead, change four things:

1. Skip the @genkit-ai/fetch package and the ## Create the backend section. A standalone setup keeps its flow and endpoint in a separate project, so you only need the Genkit web client:

   npm

   npm install genkit

   pnpm

   pnpm add genkit

   yarn

   yarn add genkit

   bun

   bun add genkit

2. Delete src/routes/api/bargainChefFlow/+server.ts. The browser calls your standalone backend directly instead of a SvelteKit endpoint.

3. In src/routes/+page.svelte, define local TypeScript interfaces matching your flow’s streamed output instead of importing shared types.

4. Point FLOW_URL at your backend route:

   const FLOW_URL = 'http://localhost:8080/bargainChefFlow';

Then enable CORS on your backend so it accepts requests from http://localhost:5173:

Enable CORS on the backend

Your SvelteKit dev server runs on http://localhost:5173 and your Genkit backend runs on a different port, so the browser will block requests unless the backend explicitly allows that origin. If you haven't configured CORS on your backend yet, do that before running the SvelteKit app. See your backend framework's CORS documentation for the exact configuration.

What you built

You now have a working Genkit app that streams structured output from Gemini into a SvelteKit UI incrementally, calls a tool during generation to ground the model’s response in mock sale-price data, validates input and output against schemas, and surfaces every step in a local trace UI.

Next steps

• Creating flows: Compose multi-step flows, branch on input, and chain model calls.
• Generating content: Swap Gemini for another provider, tune sampling parameters, and work with multimodal input.
• Deploy your app: Ship to Cloud Run, Vercel, Firebase, or your own infrastructure.
• Developer tools: Dig deeper into the Developer UI, tracing, and evaluation.