SvelteKit tutorial

In this tutorial, you’ll build the SvelteKit UI for Bargain Chef and connect it to your existing Genkit backend. 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.

You’ll call the existing bargainChefFlow over HTTP and render the streamed recipe as fields arrive.

Prerequisites

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

You should have already completed the Flask, FastAPI, or other backend tutorial. This tutorial picks up where those leave off and adds a SvelteKit UI to the bargainChefFlow you already built there. Make sure your backend is running and note the port it serves on, since you’ll need it later.

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 the Genkit web client, which lets the browser call your backend:

npm

npm install genkit

pnpm

pnpm add genkit

yarn

yarn add genkit

bun

bun add genkit

Your backend should already expose bargainChefFlow. For reference, here’s the shape the SvelteKit app expects:

// Input
{ craving: string }

// Streamed output (partial: fields fill in over time)
{
  title?: string;
  description?: string;
  servings?: number;
  ingredients?: { name: string; quantity: string; onSale: boolean }[];
  steps?: string[];
}

If your backend exposes a flow with a different name or shape, adjust the URL and the Recipe interface in the next section accordingly.

At this point, your SvelteKit app is ready to call the backend flow you already created.

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 FLOW_URL points to your backend, so adjust the port or route if your backend doesn’t run at http://localhost:8080/bargainChefFlow:

src/routes/+page.svelte

<script lang="ts">
  import { streamFlow } from 'genkit/beta/client';

  interface RecipeIngredient {
    name?: string;
    quantity?: string;
    onSale?: boolean;
  }

  interface Recipe {
    title?: string;
    description?: string;
    servings?: number;
    ingredients?: RecipeIngredient[];
    steps?: string[];
  }

  // Point this at the URL where your bargainChefFlow is served
  const FLOW_URL = 'http://localhost:8080/bargainChefFlow';

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

  async function generateRecipe() {
    if (!craving.trim()) return;
    recipe = null;
    isStreaming = true;
    try {
      const result = streamFlow({
        url: FLOW_URL,
        input: { craving },
      });
      // 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 as Recipe;
      }
      // 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>

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.

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 your Genkit backend in one terminal by following the run instructions in the backend tutorial you used. Then start the SvelteKit development server in another terminal:

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.

If the request fails, check the browser console first. The most common issue is a CORS error or a FLOW_URL that doesn’t match the backend route.

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.

If your backend is running under genkit start, the Developer UI is already running at http://localhost:4000.

In the Developer UI:

• The Traces tab shows every invocation of bargainChefFlow, including requests from 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.

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.