vibezcheckv0.3.0
llms.txt
Documentation/Core Concepts/Declarative 1-Line API

Declarative 1-Line API

Universal model wrapper supporting string IDs, provider instances, and gateways.

Declarative 1-Line API

The `vibezcheck(model, options)` function acts as a universal decorator for any AI model.

---

1-Line Syntax

You can pass a string model identifier or any Vercel AI SDK language model instance:

typescript
import { generateText } from 'ai';
import { vibezcheck } from 'vibezcheck';

const { text } = await generateText({
  model: vibezcheck('openai/gpt-4o-mini', {
    customer: 'user@example.com',
  }),
  prompt: 'What is love?',
});

---

Vercel AI SDK Primitives

`vibezcheck` is 100% compatible with all Vercel AI SDK primitives: * `generateText({ model, prompt })` * `streamText({ model, messages })` * `generateObject({ model, schema, prompt })` * `streamObject({ model, schema, prompt })` * Tool calls & function executions

---

Custom Provider Instances (`createOpenAI`)

If you configure custom headers, organizations, or gateways in `createOpenAI`, pass the instance directly:

typescript
import { createOpenAI } from '@ai-sdk/openai';
import { streamText } from 'ai';
import { vibezcheck } from 'vibezcheck';

const openai = createOpenAI({
  apiKey: process.env.AI_GATEWAY_API_KEY,
  baseURL: 'https://ai-gateway.vercel.sh/v1',
});

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

  return streamText({
    model: vibezcheck(openai('gpt-4o-mini'), { customer: 'alex@company.com' }),
    messages,
  }).toTextStreamResponse();
}