### Local Setup: Install Dependencies and Run

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-langchain/README.md

Steps to install project dependencies and run the development server locally. This involves installing packages and starting the application.

```bash
pnpm install
```

```bash
pnpm dev
```

--------------------------------

### Install, Build, and Run the AI SDK

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/fastify/README.md

Commands to install dependencies, build the project, and start the development server.

```sh
pnpm install
pnpm build
pnpm dev
```

--------------------------------

### Install Dependencies and Build Project

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/sveltekit-openai/README.md

Installs project dependencies using pnpm and builds the project. This is a prerequisite for running the example.

```bash
pnpm install
pnpm build
```

--------------------------------

### Local Development Setup

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-pages/README.md

Steps to run the example locally. This involves signing up for OpenAI, generating an API key, setting it as an environment variable, installing dependencies, and starting the development server.

```bash
# 1. Sign up at OpenAI's Developer Platform
# 2. Generate an API KEY from OpenAI's dashboard
# 3. Set the OPENAI_API_KEY environment variable in a .env.local file
# Example .env.local:
# OPENAI_API_KEY=your-openai-api-key

pnpm install
pnpm dev
```

--------------------------------

### Run sveltekit-openai Development Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/sveltekit-openai/README.md

Starts the sveltekit-openai example development server using pnpm. This command targets the specific sveltekit-openai package.

```bash
pnpm -F sveltekit-openai dev
```

--------------------------------

### Install AI SDK and Anthropic Provider

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/05-computer-use.mdx

Installs the necessary AI SDK core package and the Anthropic provider package using pnpm.

```shell
pnpm add ai @ai-sdk/anthropic
```

--------------------------------

### PNPM Project Setup

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/ai-core/README.md

Commands to install project dependencies and build the project using the PNPM package manager. These steps are necessary before running examples or tests.

```sh
pnpm install
pnpm build
```

--------------------------------

### Install, Build, and Run the AI SDK

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/hono/README.md

Installs dependencies, builds the project, and starts the development server. These commands are executed from the root directory of the AI SDK repository.

```Shell
pnpm install
pnpm build
pnpm dev
```

--------------------------------

### Install Dependencies and Run Development Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-fastapi/README.md

Commands to install project dependencies using pnpm and start the local development server for the Next.js application.

```bash
pnpm install
pnpm dev
```

--------------------------------

### Install Dependencies and Run Locally

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-telemetry-sentry/README.md

Commands to install project dependencies and start the development server for the Next.js AI example. Requires setting up environment variables for OpenAI and Sentry.

```bash
pnpm install
pnpm dev
```

--------------------------------

### Install, Build, and Run the AI SDK

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/express/README.md

Installs dependencies, builds the project, and starts the development server using pnpm. These commands are executed from the root directory of the AI SDK repository.

```sh
pnpm install
pnpm build
pnpm dev
```

--------------------------------

### Run Application

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/docs/02-getting-started/04-svelte.mdx

Command to start the Svelte AI chatbot application locally.

```shell
pnpm run dev
```

--------------------------------

### Install Dependencies and Run Locally

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-telemetry/README.md

Steps to install project dependencies using pnpm and start the development server for local testing. Requires an OpenAI API key to be set in the environment.

```bash
pnpm install
pnpm dev
```

--------------------------------

### Python Environment Setup for FastAPI

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-fastapi/README.md

Steps to set up a Python virtual environment, activate it, and install project dependencies using pip for the FastAPI server.

```bash
virtualenv venv
source venv/bin/activate
pip install -r requirements.txt
```

--------------------------------

### Install AI SDK Packages

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/24-o3.mdx

Command to install the necessary AI SDK packages for a project, including the core AI SDK, the OpenAI provider, and the React integration for building UI components.

```bash
pnpm install ai @ai-sdk/openai @ai-sdk/react
```

--------------------------------

### Install Dependencies and Setup Environment

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-kasada-bot-protection/README.md

Installs project dependencies using the pnpm package manager and copies an example environment file to `.env.local`. The `.env.local` file requires manual configuration with specific values for the application to run correctly.

```sh
pnpm i
cp .env.local.example .env.local # and fill in the required values
```

--------------------------------

### Environment Setup and Dependency Installation

Source: https://github.com/vercel/ai/blob/ai_5_0_0/CONTRIBUTING.md

Instructions for setting up the development environment, including installing Node.js and PNPM, and installing project dependencies using PNPM.

```bash
npm install -g pnpm@10
```

```bash
brew install pnpm
```

```bash
pnpm install
```

--------------------------------

### Install AI SDK and OpenAI Provider

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/22-gpt-4-5.mdx

Installs the necessary AI SDK packages and the OpenAI provider for use with frameworks like Next.js. This command is typically run in your project's terminal.

```bash
pnpm install ai @ai-sdk/openai @ai-sdk/react
```

--------------------------------

### Run Development Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/node-http-server/README.md

Starts the Node.js development server. This command should be executed after installing dependencies to launch the application.

```shell
pnpm dev
```

--------------------------------

### Build and Install dependencies

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/mcp/README.md

Installs dependencies and builds the project using pnpm.

```sh
pnpm install
pnpm build
```

--------------------------------

### Start SSE Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/mcp/README.md

Starts the SSE server for the legacy SSE transport example.

```sh
pnpm sse:server
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/sveltekit-openai/README.md

Sets up the necessary environment variables for the example. The OPENAI_API_KEY must be provided in a .env.local file in the example's directory.

```env
OPENAI_API_KEY=<your key>
```

--------------------------------

### Start Development Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/04-natural-language-postgres.mdx

Launches the local development server for the application. Once started, the application will typically be accessible at http://localhost:3000.

```bash
pnpm run dev
```

--------------------------------

### Install Dependencies

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/node-http-server/README.md

Installs all necessary project dependencies using the pnpm package manager. This command should be run from the root directory of the AI SDK repository.

```shell
pnpm install
```

--------------------------------

### Running the Example Application

Source: https://github.com/vercel/ai/blob/ai_5_0_0/packages/angular/README.md

Instructions for setting up and running the example application, which combines Angular and Express.js. It covers navigating to the example directory, setting up environment variables (like API keys), and starting the development servers.

```bash
# Navigate to example
cd examples/angular-chat

# Set up environment
echo "OPENAI_API_KEY=your_key_here" > .env

# Start development (Angular + Express)
pnpm start

# Starts:
# - Angular dev server: http://localhost:4200
# - Express API server: http://localhost:3000
# - Proxy routes /api/* to Express
```

--------------------------------

### Computer Tool Setup with Anthropic

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/05-computer-use.mdx

Defines a computer tool for the AI SDK using the Anthropic provider. This tool includes display dimensions and custom logic for executing actions like taking screenshots or performing other computer interactions. It also specifies how to convert tool results back into a model-understandable format.

```typescript
import { anthropic } from '@ai-sdk/anthropic';
import { getScreenshot, executeComputerAction } from '@/utils/computer-use';

const computerTool = anthropic.tools.computer_20250124({
  displayWidthPx: 1920,
  displayHeightPx: 1080,
  execute: async ({ action, coordinate, text }) => {
    switch (action) {
      case 'screenshot': {
        return {
          type: 'image',
          data: getScreenshot(),
        };
      }
      default: {
        return executeComputerAction(action, coordinate, text);
      }
    }
  },
  toModelOutput(result) {
    return typeof result === 'string'
      ? [{ type: 'text', text: result }]
      : [{ type: 'image', data: result.data, mediaType: 'image/png' }];
  },
});
```

--------------------------------

### Install AI SDK and OpenAI Provider Dependencies

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/docs/02-getting-started/06-nodejs.mdx

Installs the AI SDK (`ai@beta`), the OpenAI provider (`@ai-sdk/openai@beta`), and utility packages like `zod` and `dotenv`. Development dependencies for TypeScript compilation (`@types/node`, `tsx`, `typescript`) are also installed.

```bash
pnpm add ai@beta @ai-sdk/openai@beta zod dotenv
pnpm add -D @types/node tsx typescript
```

--------------------------------

### Setup Project Directory and Initialize with pnpm

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/docs/02-getting-started/06-nodejs.mdx

Creates a new project directory and initializes a Node.js project using `pnpm init`. This sets up the basic `package.json` file required for the project.

```bash
mkdir my-ai-app
cd my-ai-app
pnpm init
```

--------------------------------

### Running AI SDK Examples

Source: https://github.com/vercel/ai/blob/ai_5_0_0/CONTRIBUTING.md

Steps to navigate to example directories and execute AI SDK examples using PNPM, including specific commands for AI SDK Core and other framework examples.

```bash
cd examples/ai-core
```

```bash
pnpm tsx src/stream-text/openai.ts
```

```bash
pnpm dev
```

--------------------------------

### Start Nest.js AI Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/nest/README.md

Starts the Nest.js development server in watch mode. This command requires pnpm to be installed and the project dependencies to be set up.

```sh
pnpm run start:dev
```

--------------------------------

### Create SvelteKit Application

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/docs/02-getting-started/04-svelte.mdx

Scaffolds a new SvelteKit project using the `create-svelte` command. This command initializes a basic SvelteKit application structure, ready for further customization.

```shell
npx sv create my-ai-app
```

--------------------------------

### Bootstrap Nuxt OpenAI Example

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/nuxt-openai/README.md

Use create-nuxt to bootstrap the example project from a GitHub template. This command initializes a new Nuxt project with the specified AI SDK example.

```bash
npx create-nuxt -t github:vercel/ai/examples/nuxt-openai nuxt-openai
```

--------------------------------

### Install AI SDK and Anthropic Provider

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/20-sonnet-3-7.mdx

Installs the AI SDK and the Anthropic provider using pnpm. This is a prerequisite for building AI-powered applications with Anthropic models in a Next.js environment.

```bash
pnpm install ai @ai-sdk/anthropic
```

--------------------------------

### Bootstrap Next.js App with AI SDK Example

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-upstash-rate-limits/README.md

Use create-next-app with npm to quickly set up the project. This command clones the specified example repository into a new directory.

```bash
npx create-next-app --example https://github.com/vercel/ai/tree/main/examples/next-openai-rate-limits next-openai-rate-limits-app
```

--------------------------------

### Bootstrap Next.js App with AI SDK Example (pnpm)

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-upstash-rate-limits/README.md

Use create-next-app with pnpm to quickly set up the project. This command clones the specified example repository into a new directory.

```bash
pnpm create next-app --example https://github.com/vercel/ai/tree/main/examples/next-openai-rate-limits next-openai-rate-limits-app
```

--------------------------------

### Install AI SDK and DeepSeek Provider

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/25-r1.mdx

Installs the necessary AI SDK packages and the DeepSeek provider using pnpm. This command sets up your project to use AI SDK functionalities with DeepSeek models.

```bash
pnpm install ai @ai-sdk/deepseek @ai-sdk/react
```

--------------------------------

### Install AI SDK and Google Provider

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/17-gemini-2-5.mdx

Command to install the core AI SDK and the Google Generative AI provider package using pnpm. This is a prerequisite for using Gemini models with the AI SDK.

```bash
pnpm install ai @ai-sdk/google
```

--------------------------------

### Install AI SDK and Anthropic Provider (pnpm)

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/18-claude-4.mdx

Installs the necessary AI SDK core library and the Anthropic provider package using the pnpm package manager. This is the first step to integrate AI capabilities into your project.

```bash
pnpm install ai @ai-sdk/anthropic
```

--------------------------------

### Install AI SDK Dependencies

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/docs/02-getting-started/04-svelte.mdx

Installs the necessary AI SDK packages (`ai`, `@ai-sdk/openai`, `@ai-sdk/svelte`) along with `zod` for schema validation. These dependencies are crucial for integrating AI functionalities and OpenAI's models into your Svelte application.

```pnpm
pnpm add -D ai @ai-sdk/openai @ai-sdk/svelte zod
```

```npm
npm install -D ai @ai-sdk/openai @ai-sdk/svelte zod
```

```yarn
yarn add -D ai @ai-sdk/openai @ai-sdk/svelte zod
```

--------------------------------

### Install AI SDK 5 Beta

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/docs/01-announcing-ai-sdk-5-beta/index.mdx

Installs the AI SDK 5 Beta and related provider/framework packages using npm. This command is essential for setting up the SDK in your project.

```bash
npm install ai @ai-sdk/openai @ai-sdk/react
```

--------------------------------

### Bootstrap Next.js App with AI SDK Example

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-langchain/README.md

Instructions for bootstrapping a new Next.js project using the AI SDK example from GitHub. This command sets up the project structure and initial dependencies.

```bash
npx create-next-app --example https://github.com/vercel/ai/tree/main/examples/next-langchain next-langchain-app
```

```bash
yarn create next-app --example https://github.com/vercel/ai/tree/main/examples/next-langchain next-langchain-app
```

```bash
pnpm create next-app --example https://github.com/vercel/ai/tree/main/examples/next-langchain next-langchain-app
```

--------------------------------

### Start HTTP Server

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/mcp/README.md

Starts the HTTP server for the streamable HTTP transport example.

```sh
pnpm http:server
```

--------------------------------

### Bootstrap Next.js App with AI SDK Example (Yarn)

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/next-openai-upstash-rate-limits/README.md

Use create-next-app with Yarn to quickly set up the project. This command clones the specified example repository into a new directory.

```bash
yarn create next-app --example https://github.com/vercel/ai/tree/main/examples/next-openai-rate-limits next-openai-rate-limits-app
```

--------------------------------

### Run Stdio Client

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/mcp/README.md

Runs the stdio client example.

```sh
pnpm stdio:client
```

--------------------------------

### Setup Angular AI Chat Application

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/angular/README.md

This snippet demonstrates the steps to set up the Angular AI Chat application. It includes installing dependencies using pnpm, creating a .env file for the OpenAI API key, and starting the application. The setup process launches both the Angular frontend and the Express backend.

```bash
# Install dependencies
pnpm install

# Create .env file with your OpenAI API key
echo "OPENAI_API_KEY=your_key_here" > .env

# Start the app
pnpm start
```

--------------------------------

### Install Dependencies with pnpm

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/nuxt-openai/README.md

Installs all the necessary project dependencies using the pnpm package manager. This step is crucial before running the development server or building the project.

```bash
pnpm install
```

--------------------------------

### Node.js Braintrust Span Processor Setup

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/providers/05-observability/braintrust.mdx

Configures the OpenTelemetry Node.js SDK with the BraintrustSpanProcessor for tracing LLM applications. Installs necessary packages and starts the SDK. Requires `ai`, `@ai-sdk/openai`, `braintrust`, `@opentelemetry/sdk-node`, `@opentelemetry/sdk-trace-base`, and `zod`.

```bash
npm install ai @ai-sdk/openai braintrust @opentelemetry/sdk-node @opentelemetry/sdk-trace-base zod
```

```typescript
import { NodeSDK } from '@opentelemetry/sdk-node';
import { generateText, tool } from 'ai';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';
import { BraintrustSpanProcessor } from 'braintrust';

const sdk = new NodeSDK({
  spanProcessors: [
    new BraintrustSpanProcessor({
      parent: 'project_name:your-project-name',
      filterAISpans: true,
    }),
  ],
});

sdk.start();

async function main() {
  const result = await generateText({
    model: openai('gpt-4o-mini'),
    messages: [
      {
        role: 'user',
        content: 'What are my orders and where are they? My user ID is 123',
      },
    ],
    tools: {
      listOrders: tool({
        description: 'list all orders',
        parameters: z.object({ userId: z.string() }),
        execute: async ({ userId }) =>
          `User ${userId} has the following orders: 1`,
      }),
      viewTrackingInformation: tool({
        description: 'view tracking information for a specific order',
        parameters: z.object({ orderId: z.string() }),
        execute: async ({ orderId }) =>
          `Here is the tracking information for ${orderId}`,
      }),
    },
    experimental_telemetry: {
      isEnabled: true,
      functionId: 'my-awesome-function',
      metadata: {
        something: 'custom',
        someOtherThing: 'other-value',
      },
    },
    maxSteps: 10,
  });

  await sdk.shutdown();
}

main().catch(console.error);
```

--------------------------------

### Generate Text with OpenAI o3-mini

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/24-o3.mdx

Demonstrates how to call the `generateText` function from the AI SDK to interact with the OpenAI o3-mini model. It shows the basic setup for sending a prompt and receiving a text response.

```typescript
import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const { text } = await generateText({
  model: openai('o3-mini'),
  prompt: 'Explain the concept of quantum entanglement.',
});
```

--------------------------------

### Clone AI SDK Slackbot Repository

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/03-slackbot.mdx

Clones the AI SDK Slackbot repository from GitHub and checks out the starter branch. This is the initial step for setting up the project locally.

```bash
git clone https://github.com/vercel-labs/ai-sdk-slackbot.git
cd ai-sdk-slackbot
git checkout starter
```

--------------------------------

### Stream Llama 3.1 Response

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/21-llama-3_1.mdx

Shows how to stream the model's response as it is generated using the AI SDK's `streamText` function. This example uses the DeepInfra provider for the Llama 3.1 405B Instruct model.

```typescript
import { streamText } from 'ai';
import { deepinfra } from '@ai-sdk/deepinfra';

const { textStream } = streamText({
  model: deepinfra('meta-llama/Meta-Llama-3.1-405B-Instruct'),
  prompt: 'What is love?',
});
```

--------------------------------

### Call Llama 3.1 with DeepInfra

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/21-llama-3_1.mdx

Demonstrates how to use the AI SDK to call the Llama 3.1 405B Instruct model via the DeepInfra provider. This example uses the `generateText` function to retrieve a text response for a given prompt.

```typescript
import { deepinfra } from '@ai-sdk/deepinfra';
import { generateText } from 'ai';

const { text } = await generateText({
  model: deepinfra('meta-llama/Meta-Llama-3.1-405B-Instruct'),
  prompt: 'What is love?',
});
```

--------------------------------

### Next.js Chat API Route Handler with Gemini

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/17-gemini-2-5.mdx

Example of a Next.js API route handler (`app/api/chat/route.ts`) that streams text responses from the Gemini 2.5 Flash model. It processes incoming messages and returns a UI message stream.

```tsx
import {
  google
} from '@ai-sdk/google';
import { streamText, UIMessage, convertToModelMessages } from 'ai';

// Allow streaming responses up to 30 seconds
export const maxDuration = 30;

export async function POST(req: Request) {
  const { messages }: { messages: UIMessage[] } = await req.json();

  const result = streamText({
    model: google('gemini-2.5-flash'),
    messages: convertToModelMessages(messages),
  });

  return result.toUIMessageStreamResponse();
}
```

--------------------------------

### Build Chat Interface with useChat Hook

Source: https://github.com/vercel/ai/blob/ai_5_0_0/content/cookbook/00-guides/24-o3.mdx

Example of a root page component (`app/page.tsx`) using the `useChat` hook from AI SDK UI. It manages chat messages, user input, and submission, rendering the conversation and a form for user interaction.

```tsx
'use client';

import { useChat } from '@ai-sdk/react';

export default function Page() {
  const { messages, input, handleInputChange, handleSubmit, error } = useChat();

  return (
    <>
      {messages.map(message => (
        <div key={message.id}>
          {message.role === 'user' ? 'User: ' : 'AI: '}
          {message.content}
        </div>
      ))}
      <form onSubmit={handleSubmit}>
        <input name="prompt" value={input} onChange={handleInputChange} />
        <button type="submit">Submit</button>
      </form>
    </>
  );
}
```

--------------------------------

### Run SSE Client

Source: https://github.com/vercel/ai/blob/ai_5_0_0/examples/mcp/README.md

Runs the SSE client example.

```sh
pnpm sse:client
```