const fetch = require('node-fetch').default;
const { SECRET_KEYS, readSecret } = require('../endpoints/secrets');

/**
 * Gets the vector for the given text from gecko model
 * @param {string[]} texts - The array of texts to get the vector for
 * @param {import('../users').UserDirectoryList} directories - The directories object for the user
 * @returns {Promise<number[][]>} - The array of vectors for the texts
 */
async function getMakerSuiteBatchVector(texts, directories) {
    const promises = texts.map(text => getMakerSuiteVector(text, directories));
    const vectors = await Promise.all(promises);
    return vectors;
}

/**
 * Gets the vector for the given text from PaLM gecko model
 * @param {string} text - The text to get the vector for
 * @param {import('../users').UserDirectoryList} directories - The directories object for the user
 * @returns {Promise<number[]>} - The vector for the text
 */
async function getMakerSuiteVector(text, directories) {
    const key = readSecret(directories, SECRET_KEYS.MAKERSUITE);

    if (!key) {
        console.log('No Google AI Studio key found');
        throw new Error('No Google AI Studio key found');
    }

    const response = await fetch(`https://generativelanguage.googleapis.com/v1beta/models/embedding-gecko-001:embedText?key=${key}`, {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json',
        },
        body: JSON.stringify({
            text: text,
        }),
    });

    if (!response.ok) {
        const text = await response.text();
        console.log('Google AI Studio request failed', response.statusText, text);
        throw new Error('Google AI Studio request failed');
    }

    const data = await response.json();

    // Access the "value" dictionary
    const vector = data.embedding.value;

    return vector;
}

module.exports = {
    getMakerSuiteVector,
    getMakerSuiteBatchVector,
};