SUTRA-V2 Vercel AI SDK Integration Guide

🧠 Build with SUTRA-V2 using Vercel AI SDK

Welcome to the SUTRA-V2 Integration Guide for the Vercel AI SDK — designed to help developers leverage SUTRA-V2’s advanced multilingual and reasoning capabilities in Vercel-hosted applications.

🔍 What is SUTRA-V2?

SUTRA-V2 is a powerful multilingual AI model optimized for:

  • Multi-step logical inference
  • Structured problem-solving
  • Deep contextual analysis
  • High-performance conversational AI across 50+ languages

Perfect for applications in:

  • Legal & policy interpretation
  • Business intelligence
  • Scientific reasoning
  • Complex query answering

🧪 Quickstart with Vercel AI SDK

Prerequisites

  • A Vercel project with a Next.js or Node.js application.
  • SUTRA API key from https://developer.two.ai.
  • Vercel AI SDK installed in your project.

Step 1: Install Dependencies

In your Vercel project, install the Vercel AI SDK:

# SUTRA models are OpenAI API compatible
npm install ai @ai-sdk/openai

Step 2: Configure the OpenAI Provider

Set your SUTRA API key as an environment variable in Vercel’s dashboard (e.g., SUTRA_API_KEY). Then, configure the Vercel AI SDK to use the OpenAI provider with the SUTRA endpoint:

// app/api/completion/route.ts (Next.js API route)
import { generateText } from 'ai';
import { createOpenAI } from '@ai-sdk/openai';

const sutra = createOpenAI({
  baseURL: "https://api.two.ai/v2",
  apiKey: process.env.SUTRA_API_KEY,
});

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

  const { text } = await generateText({
    model: sutra("sutra-v2"),
    system: "You are a helpful assistant.",
    prompt,
  });

  return Response.json({ text });
}

Step 3: Basic Completion in a Next.js Component

Create a frontend component to interact with SUTRA-V2:

// app/page.tsx
"use client";

import { useState } from "react";

export default function Page() {
  const [generation, setGeneration] = useState("");
  const [isLoading, setIsLoading] = useState(false);

  return (
    <div>
      <div
        onClick={async () => {
          setIsLoading(true);

          await fetch("/api/completion", {
            method: "POST",
            body: JSON.stringify({
              prompt: "Why is the sky blue?",
            }),
          }).then((response) => {
            response.json().then((json) => {
              setGeneration(json.text);
              setIsLoading(false);
            });
          });
        }}
      >
        Generate
      </div>

      {isLoading ? "Loading..." : generation}
    </div>
  );
}

🔁 Streaming Response Example

Stream responses for real-time interaction:

// app/api/chat/route.ts (Next.js API route)
import { streamText, UIMessage } from 'ai';
import { createOpenAI } from '@ai-sdk/openai';

const sutra = createOpenAI({
  baseURL: "https://api.two.ai/v2",
  apiKey: process.env.SUTRA_API_KEY,
});

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

  const result = streamText({
    model: sutra("sutra-v2"),
    system: "You are a helpful assistant.",
    messages,
  });

  return result.toDataStreamResponse();
}

In your frontend:

// app/chat.tsx
"use client";

import { useChat } from "ai/react";

export default function StreamChat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat({
    api: "/api/chat",
  });

  return (
    <div>
      <h1>SUTRA-V2 Streaming Chat</h1>
      {messages.map((m) => (
        <div key={m.id}>
          <strong>{m.role}: </strong>
          {m.content}
        </div>
      ))}
      <form onSubmit={handleSubmit}>
        <input
          value={input}
          onChange={handleInputChange}
          placeholder="Ask SUTRA-V2 something..."
        />
        <button type="submit">Send</button>
      </form>
    </div>
  );
}

🌐 Multilingual Support Example

Leverage SUTRA-V2’s multilingual capabilities with the Vercel AI SDK:

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

const sutra = createOpenAI({
  baseURL: "https://api.two.ai/v2",
  apiKey: process.env.SUTRA_API_KEY,
});

export async function POST(req: Request) {
  const prompts = [
    { prompt: "नमस्ते, आप कैसे हैं?", lang: "Hindi" },
    { prompt: "¿Qué es la inteligencia artificial?", lang: "Spanish" },
  ];

  const responses = await Promise.all(
    prompts.map(async ({ prompt, lang }) => {
      const response = await generateText({
        model: sutra("sutra-v2"),
        messages: [{ role: "user", content: prompt }],
        max_tokens: 1024,
        temperature: 0.7,
      });
      return { lang, content: response.text };
    })
  );

  return Response.json(responses);
}

🧠 Ideal Use Cases with Vercel AI SDK

ScenarioExample
Legal AnalysisInterpret complex legal documents in web apps
Business IntelligenceBuild dashboards for market trend analysis
Scientific ReasoningCreate tools for research data evaluation
Multilingual Q&ADevelop chatbots supporting 50+ languages
ParameterPurposeRecommended for V2
temperatureControls randomness0.7 for balanced output
max_tokensLimits response length512–1024
presence_penaltyReduces repetition0.0–0.6

🔗 API Access (cURL)

Test the SUTRA-V2 endpoint directly:

curl -X POST https://api.two.ai/v2/chat/completions \
-H "Authorization: Bearer $SUTRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "sutra-v2",
  "messages": [
    {"role": "user", "content": "Explain how blockchain improves supply chain transparency."}
  ]
}'

🛠 Troubleshooting

  • Invalid API Key: Ensure SUTRA_API_KEY is set in Vercel’s environment variables.
  • Rate Limit Exceeded: Check your SUTRA-V2 plan limits or reduce request frequency.
  • Empty Response: Increase max_tokens or refine your prompt.
  • Vercel AI SDK Compatibility: Verify the SDK supports custom baseURL for OpenAI provider.

LangGraph with SUTRA

SUTRA With AISuite

On this page

🧠 Build with SUTRA-V2 using Vercel AI SDK
🔍 What is SUTRA-V2?
🧪 Quickstart with Vercel AI SDK
Prerequisites
Step 1: Install Dependencies
Step 2: Configure the OpenAI Provider
Step 3: Basic Completion in a Next.js Component
🔁 Streaming Response Example
🌐 Multilingual Support Example
🧠 Ideal Use Cases with Vercel AI SDK
⚙️ Recommended Parameters
🔗 API Access (cURL)
🛠 Troubleshooting