Skip to content
Glitch

Vercel AI SDK

The Vercel AI SDK emphasizes developer experience and streaming. Use Glitch as the underlying client to secure inputs, retrieved context, and streaming outputs.

Configuration

Section titled “Configuration”
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';


// Configure OpenAI provider with Glitch
const glitchModel = openai('gpt-4', {
  baseURL: 'https://api.golabrat.ai/v1',
  apiKey: process.env.GLITCH_API_KEY!,  // Your Glitch API key
});

Basic Example

Section titled “Basic Example”
import { openai } from '@ai-sdk/openai';
import { generateText, streamText } from 'ai';


// Configure with Glitch
const model = openai('gpt-4', {
  baseURL: 'https://api.golabrat.ai/v1',
  apiKey: process.env.GLITCH_API_KEY!,
});


// Generate text - automatically secured
const result = await generateText({
  model,
  prompt: 'What is the capital of France?',
});


console.log(result.text);


// Streaming is also secured
const stream = await streamText({
  model,
  prompt: 'Write a poem about AI',
});


for await (const chunk of stream.textStream) {
  process.stdout.write(chunk);
}

Error Handling

Section titled “Error Handling”

Handle security blocks gracefully:

import { generateText } from 'ai';


try {
  const result = await generateText({
    model,
    prompt: userInput,
  });
  return result.text;
} catch (error: any) {
  if (error?.status === 403 || error?.statusCode === 403) {
    // Security block - handle gracefully
    return "I can't process that request.";
  }
  throw error;
}

Streaming Support

Section titled “Streaming Support”

Glitch fully supports streaming responses with the Vercel AI SDK:

import { streamText } from 'ai';


const stream = await streamText({
  model,
  prompt: 'Write a long story',
});


for await (const chunk of stream.textStream) {
  process.stdout.write(chunk);
}

Next Steps

Section titled “Next Steps”