Vision Capabilities

// Method 1: From a URL (Node.js)
async function encodeImageFromUrl(imageUrl) {
    const response = await fetch(imageUrl);
    const buffer = await response.arrayBuffer();
    return Buffer.from(buffer).toString('base64');
}

// Method 2: From a local file (Node.js)
const fs = require('fs');
function encodeImageFromFile(imagePath) {
    const imageBuffer = fs.readFileSync(imagePath);
    return imageBuffer.toString('base64');
}

// Example: Encode Hong Kong image
const hongKongUrl = "https://ik.imgkit.net/3vlqs5axxjf/external/ik-seo/http://images.ntmllc.com/v4/destination/Hong-Kong/Hong-Kong-city/112086_SCN_HongKong_iStock466733790_Z8C705/Hong-Kong-Scenery.jpg?tr=w-680%2Ch-404%2Cfo-auto";

const base64Image = await encodeImageFromUrl(hongKongUrl);
console.log(`Base64 string length: ${base64Image.length}`);
console.log(`First 100 characters: ${base64Image.substring(0, 100)}...`);

# From a URL
curl -s "https://ik.imgkit.net/3vlqs5axxjf/external/ik-seo/http://images.ntmllc.com/v4/destination/Hong-Kong/Hong-Kong-city/112086_SCN_HongKong_iStock466733790_Z8C705/Hong-Kong-Scenery.jpg?tr=w-680%2Ch-404%2Cfo-auto" | base64 > hongkong_base64.txt

# From a local file
base64 -i /path/to/image.jpg > image_base64.txt

# View first 100 characters
head -c 100 hongkong_base64.txt

const API_KEY = process.env.SWARMS_API_KEY;
const BASE_URL = "https://api.swarms.world";

const headers = {
    "x-api-key": API_KEY,
    "Content-Type": "application/json"
};

// Encode the Hong Kong image from Step 2
const hongKongUrl = "https://ik.imgkit.net/3vlqs5axxjf/external/ik-seo/http://images.ntmllc.com/v4/destination/Hong-Kong/Hong-Kong-city/112086_SCN_HongKong_iStock466733790_Z8C705/Hong-Kong-Scenery.jpg?tr=w-680%2Ch-404%2Cfo-auto";

async function analyzeImage() {
    // Fetch and encode the image
    const imageResponse = await fetch(hongKongUrl);
    const arrayBuffer = await imageResponse.arrayBuffer();
    const base64Image = Buffer.from(arrayBuffer).toString('base64');

    // Prepare the payload
    const payload = {
        agent_config: {
            agent_name: "Vision Analyst",
            description: "AI agent with image analysis capabilities",
            system_prompt: "You are a vision analyst that can identify and describe images accurately.",
            model_name: "gpt-4o",
            max_tokens: 2048,
            temperature: 0.5
        },
        task: "What city is this?",
        img: base64Image
    };

    // Make the API request
    const response = await fetch(`${BASE_URL}/v1/agent/completions`, {
        method: 'POST',
        headers: headers,
        body: JSON.stringify(payload)
    });

    const result = await response.json();
    console.log("Agent Response:");
    console.log(result.outputs[0].content);

    // Expected output: "This image is of Hong Kong. The skyline, Victoria Harbour..."
}

analyzeImage();

# First, encode the image to base64
BASE64_IMAGE=$(curl -s "https://ik.imgkit.net/3vlqs5axxjf/external/ik-seo/http://images.ntmllc.com/v4/destination/Hong-Kong/Hong-Kong-city/112086_SCN_HongKong_iStock466733790_Z8C705/Hong-Kong-Scenery.jpg?tr=w-680%2Ch-404%2Cfo-auto" | base64)

# Make the API request
curl -X POST "https://api.swarms.world/v1/agent/completions" \
  -H "x-api-key: your-api-key-here" \
  -H "Content-Type: application/json" \
  -d "{
    \"agent_config\": {
      \"agent_name\": \"Vision Analyst\",
      \"description\": \"AI agent with image analysis capabilities\",
      \"system_prompt\": \"You are a vision analyst that can identify and describe images accurately.\",
      \"model_name\": \"gpt-4o\",
      \"max_tokens\": 2048,
      \"temperature\": 0.5
    },
    \"task\": \"What city is this?\",
    \"img\": \"${BASE64_IMAGE}\"
  }"