Model selection

async function processTextQuestion(question, apiKey, modelName = 'gemini-2.0-flash-lite') {
  // ...
  const model = userGenAI.getGenerativeModel({ model: modelName });
}

const modelOptions = [
  'gemini-2.0-flash-lite',  // Faster
  'gemini-2.0-flash'       // Balanced
];

// Model slider change event with improved feedback
modelSlider.addEventListener('input', function() {
  const selectedModelName = modelOptions[this.value];
  selectedModel.textContent = selectedModelName;
  
  // Add visual feedback
  selectedModel.style.opacity = '0.7';
  setTimeout(() => {
    selectedModel.style.opacity = '1';
  }, 150);
});

// Load saved model preference
const savedModel = localStorage.getItem('geminiModel');
if (savedModel) {
  const modelIndex = modelOptions.indexOf(savedModel);
  if (modelIndex !== -1) {
    modelSlider.value = modelIndex;
    selectedModel.textContent = savedModel;
  }
}

const selectedModel = localStorage.getItem('geminiModel') || 'gemini-2.0-flash-lite';
formData.append('model', selectedModel);

const modelName = req.body.model || 'gemini-2.0-flash-lite';

const prompt = `Quiz question: "${question}"
Provide ONLY the correct answer(s). If there are choices, only pick from them. Be extremely concise.`;

const prompt = 'Quiz question image. Identify and provide ONLY the correct answer(s). If there are choices, only pick from them. Be extremely concise.';

const RATE_LIMIT_WINDOW = 5000; // 5 seconds between calls
const MAX_RETRIES = 3;
const INITIAL_RETRY_DELAY = 1000; // 1 second

function isRateLimited(clientId) {
  const now = Date.now();
  const lastCallTime = apiCallTimestamps.get(clientId) || 0;
  
  if (now - lastCallTime < RATE_LIMIT_WINDOW) {
    return true; // Rate limited
  }
  
  // Update the timestamp for this client
  apiCallTimestamps.set(clientId, now);
  return false; // Not rate limited
}

async function processImageQuestion(imagePath, apiKey, modelName = 'gemini-2.0-flash-lite') {
  const userGenAI = new GoogleGenerativeAI(apiKey);
  const model = userGenAI.getGenerativeModel({ model: modelName });
  
  const result = await callGeminiAPI(() => 
    model.generateContent([prompt, imagePart])
  );
  return result.response.text();
}