AI Functions Examples

The examples/ai-functions/ directory contains scripts for validating, testing, and iterating on AI SDK functions across providers.

Example Categories

Examples are organized by AI SDK function in examples/ai-functions/src/:

File Naming Convention

Examples follow the pattern: {provider}-{feature}.ts

Example Structure

All examples use the run() wrapper from lib/run.ts which:

• Loads environment variables from .env
• Provides error handling with detailed API error logging

Basic Template

typescript
1import { providerName } from "@ai-sdk/provider-name";
2import { generateText } from "ai";
3
4import { run } from "../lib/run";
5
6run(async () => {
7  const result = await generateText({
8    model: providerName("model-id"),
9    prompt: "Your prompt here.",
10  });
11
12  console.warn(result.text);
13  console.warn("Token usage:", result.usage);
14  console.warn("Finish reason:", result.finishReason);
15});

Streaming Template

typescript
1import { providerName } from "@ai-sdk/provider-name";
2import { streamText } from "ai";
3
4import { printFullStream } from "../lib/print-full-stream";
5import { run } from "../lib/run";
6
7run(async () => {
8  const result = streamText({
9    model: providerName("model-id"),
10    prompt: "Your prompt here.",
11  });
12
13  await printFullStream({ result });
14});

Tool Calling Template

typescript
1import { providerName } from "@ai-sdk/provider-name";
2import { generateText, tool } from "ai";
3import { z } from "zod";
4
5import { run } from "../lib/run";
6
7run(async () => {
8  const result = await generateText({
9    model: providerName("model-id"),
10    tools: {
11      myTool: tool({
12        description: "Tool description",
13        inputSchema: z.object({
14          param: z.string().describe("Parameter description"),
15        }),
16        execute: async ({ param }) => {
17          return { result: `Processed: ${param}` };
18        },
19      }),
20    },
21    prompt: "Use the tool to...",
22  });
23
24  console.warn(JSON.stringify(result, null, 2));
25});

Structured Output Template

typescript
1import { providerName } from "@ai-sdk/provider-name";
2import { generateObject } from "ai";
3import { z } from "zod";
4
5import { run } from "../lib/run";
6
7run(async () => {
8  const result = await generateObject({
9    model: providerName("model-id"),
10    schema: z.object({
11      name: z.string(),
12      items: z.array(z.string()),
13    }),
14    prompt: "Generate a...",
15  });
16
17  console.warn(JSON.stringify(result.object, null, 2));
18  console.warn("Token usage:", result.usage);
19});

Running Examples

From the examples/ai-functions directory:

bash
1pnpm tsx src/generate-text/openai.ts
2pnpm tsx src/stream-text/openai-tool-call.ts
3pnpm tsx src/agent/openai-generate.ts

When to Write Examples

Write examples when:

1. Adding a new provider: Create basic examples for each supported API (generateText, streamText, generateObject, etc.)

2. Implementing a new feature: Demonstrate the feature with at least one provider example

3. Reproducing a bug: Create an example that shows the issue for debugging

4. Adding provider-specific options: Show how to use providerOptions for provider-specific settings

5. Creating test fixtures: Use examples to generate API response fixtures (see capture-api-response-test-fixture skill)

Utility Helpers

The lib/ directory contains shared utilities:

Using print utilities

typescript
1import { print } from "../lib/print";
2
3// Pretty print objects without undefined values
4print("Result:", result);
5print("Usage:", result.usage, { depth: 2 });

Using printFullStream

typescript
1// import { printFullStream } from '../lib/print-full-stream';
2
3// const result = streamText({ ... });
4// await printFullStream({ result }); // Colored output for text, tool calls, reasoning

Reusable Tools

The tools/ directory contains reusable tool definitions:

typescript
1import { weatherTool } from "../tools/weather-tool";
2
3const result = await generateText({
4  model: openai("gpt-4o"),
5  tools: { weather: weatherTool },
6  prompt: "What is the weather in San Francisco?",
7});

Best Practices

1. Keep examples focused: Each example should demonstrate one feature or use case

2. Use descriptive prompts: Make it clear what the example is testing

3. Handle errors gracefully: The run() wrapper handles this automatically

4. Use realistic model IDs: Use actual model IDs that work with the provider

5. Add comments for complex logic: Explain non-obvious code patterns

6. Reuse tools when appropriate: Use weatherTool or create new reusable tools in tools/