Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.raptordata.dev/llms.txt

Use this file to discover all available pages before exploring further.

​
Vercel AI SDK Integration

Perfect for Next.js apps. Add caching, security, and logging to your AI features with minimal code changes.

​
Install

npm install ai @ai-sdk/openai
# or for Claude
npm install ai @ai-sdk/anthropic

​
Setup Provider

// lib/ai.ts
import { createOpenAI } from '@ai-sdk/openai';

export const openai = createOpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  baseURL: 'https://proxy.raptordata.dev/v1',
  headers: {
    'X-Raptor-Api-Key': process.env.RAPTOR_API_KEY!,
    'X-Raptor-Workspace-Id': process.env.RAPTOR_WORKSPACE_ID!
  }
});

​
API Route (Streaming)

// app/api/chat/route.ts
import { openai } from '@/lib/ai';
import { streamText } from 'ai';

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

  const result = streamText({
    model: openai('gpt-4'),
    messages
  });

  return result.toDataStreamResponse();
}

​
React Component

'use client';
import { useChat } from 'ai/react';

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

  return (
    <div>
      {messages.map((m) => (
        <div key={m.id}>
          <b>{m.role}:</b> {m.content}
        </div>
      ))}
      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} />
      </form>
    </div>
  );
}

​
Non-Streaming

import { openai } from '@/lib/ai';
import { generateText } from 'ai';

const { text } = await generateText({
  model: openai('gpt-4'),
  prompt: 'What is 2+2?'
});

​
Structured Output

import { openai } from '@/lib/ai';
import { generateObject } from 'ai';
import { z } from 'zod';

const { object } = await generateObject({
  model: openai('gpt-4'),
  schema: z.object({
    name: z.string(),
    ingredients: z.array(z.string())
  }),
  prompt: 'Generate a recipe for cookies'
});

​
Using Anthropic

import { createAnthropic } from '@ai-sdk/anthropic';

const anthropic = createAnthropic({
  apiKey: process.env.ANTHROPIC_API_KEY,
  baseURL: 'https://proxy.raptordata.dev',  // No /v1 for Anthropic
  headers: {
    'X-Raptor-Api-Key': process.env.RAPTOR_API_KEY!,
    'X-Raptor-Workspace-Id': process.env.RAPTOR_WORKSPACE_ID!
  }
});

// Use like: anthropic('claude-sonnet-4-20250514')

​
Environment Variables

Add to .env.local: 
OPENAI_API_KEY=sk-...
RAPTOR_API_KEY=rpt_...
RAPTOR_WORKSPACE_ID=your-workspace-uuid

​
Full Example

// app/api/chat/route.ts
import { createOpenAI } from '@ai-sdk/openai';
import { streamText } from 'ai';

const openai = createOpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  baseURL: 'https://proxy.raptordata.dev/v1',
  headers: {
    'X-Raptor-Api-Key': process.env.RAPTOR_API_KEY!,
    'X-Raptor-Workspace-Id': process.env.RAPTOR_WORKSPACE_ID!
  }
});

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

  const result = streamText({
    model: openai('gpt-4'),
    system: 'You are a helpful assistant.',
    messages
  });

  return result.toDataStreamResponse();
}
All Vercel AI SDK features work: streaming, structured output, tools, and multi-provider support. Every request goes through Raptor for caching, security, and logging.