Initial AI SDK Setup and Gemini Integration

Your first task is to initialize your AI SDK project and integrate Gemini 2.5 Pro for multimodal content generation. Set up a basic streaming chat endpoint. 

```typescript
import { createOpenAI } from '@ai-sdk/openai';
import { createGoogleGenerativeAI } from '@ai-sdk/google';
import { streamText } from 'ai';

const google = createGoogleGenerativeAI({ apiKey: process.env.GOOGLE_API_KEY });
const model = google('gemini-2.5-pro');

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

  const result = await streamText({
    model: model,
    messages,
    // You'll need to add tools for ad generation here later
  });

  return result.to Response();
}
```

Expand this to include a simple tool for 'generateAdContent' that takes user preferences and a conversational context, and returns a multimodal ad draft (text, image URL).