AIServer/server/AIRequest/img2text.js

const { OpenAI } = require('openai');
const config = require('../config');

const client = new OpenAI({
  apiKey: config.API_KEY,
  baseURL: config.BASE_URL
});

async function img2text(prompt, imageUrl) {
  try {
    if (!prompt) {
      throw new Error('Missing prompt');
    }
    if (!imageUrl) {
      throw new Error('Missing imageUrl');
    }

    const response = await client.chat.completions.create({
      model: 'gpt-4o',
      messages: [
        {
          role: 'user',
          content: [
            { type: 'text', text: prompt },
            {
              type: 'image_url',
              image_url: {
                url: imageUrl,
                detail: 'high'
              }
            }
          ]
        }
      ],
      max_tokens: 300,
      stream: false
    });

    return { success: true, data: response };
  } catch (error) {
    throw error;
  }
}

module.exports = img2text;