video2document/services/modules/llm-gemini/gemini.js

const fs = require('fs');
const path = require('path');

const outputDir = path.join(__dirname, "../../../storage/documents"); // path for output directory

if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
}

// Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
let GEMINI_API_KEY; // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
const GEMINI_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent"; // URL for the REST call, used model and action

const module_exports = {
    name: "llm-gemini",
    type: "llm",
    displayname: "Gemini LLM",
    description: "Generates documents using Google Gemini LLM",

    async function(parameter) {
        GEMINI_API_KEY = process.env.GOOGLE_API_KEY;
        return new Promise(async (resolve, reject) => {
            try {
                // console.log("Gemini LLM module invoked with parameters:", parameter);

                resolve(await this.createDocumentFromTranscript( //Call the function to create document with transcript, document type and language
                    parameter.inputTranscriptPath, // Path to input transcript file
                    parameter.documentTypePath, // Path to document type file which is chosen in the front end by the user
                    parameter.language // Language for the document which is chosen in the front end by the user
                ));

            } catch (error) {
                // console.error("Error in Gemini LLM module:", error);
                reject(error)
            }
        })

    },

    createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
        return new Promise(async(resolve, reject) => {
            try {
                const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
                const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
                const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed

                // --- REST CALL ---
                const response = await fetch(`${GEMINI_URL}?key=${GEMINI_API_KEY}`, { //safe model response in variable
                    method: "POST",
                    headers: {
                        "Content-Type": "application/json"
                    },
                    body: JSON.stringify({
                        contents: [
                            {
                                parts: [
                                    { text: promptText } // Input prompt for content generation
                                ]
                            }
                        ]
                    })
                });

                if (!response.ok) { //ok is true when a responce was successfull
                    const text = await response.text();
                    throw new Error(`Gemini API error (${response.status}): ${text}`);
                }

                const data = await response.json();

                // Get generated text from response or default to empty string (if null)
                const output = data?.candidates?.[0]?.content?.parts?.[0]?.text || "";
                let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file 
                // console.log(inputTranscriptName);
                const outPath = path.join(outputDir, `${inputTranscriptName}.html`); // Output file path & name to make naming dynamic. Pulled from input transcript name
                fs.writeFileSync(outPath, output, "utf8"); // Write output to file

                // console.log("Generated document written to:", outPath);
                resolve(outPath)

            } catch (error) {
                // console.error("Error generating Gemini content:", error);
                reject(error)
            }
        })
    }
};

module.exports = module_exports;

// CLI Mode: Allow direct execution
if (require.main === module) {
    (async () => {
        const args = process.argv.slice(2);
        
        if (args.length < 2) {
            console.error("Usage: node llm-gemini.js <transcriptPath> <documentTypePath> [language]");
            console.error("Example: node llm-gemini.js ./transcript.json ./docType.txt de");
            process.exit(1);
        }

        const [transcriptPath, documentTypePath, language] = args;

        // Check if API key is set
        if (!GEMINI_API_KEY) {
            console.error("ERROR: GOOGLE_API_KEY environment variable is not set!");
            console.error("Please set it with: export GOOGLE_API_KEY='your_api_key_here'");
            process.exit(1);
        }

        // Check if files exist
        if (!fs.existsSync(transcriptPath)) {
            console.error(`ERROR: Transcript file not found: ${transcriptPath}`);
            process.exit(1);
        }

        if (!fs.existsSync(documentTypePath)) {
            console.error(`ERROR: Document type file not found: ${documentTypePath}`);
            process.exit(1);
        }

        console.log("Starting document generation...");
        console.log(`Transcript: ${transcriptPath}`);
        console.log(`Document Type: ${documentTypePath}`);
        console.log(`Language: ${language || 'en (default)'}`);
        
        await module_exports.createDocumentFromTranscript(
            transcriptPath,
            documentTypePath,
            language || 'en'
        );
        
        console.log("Done!");
    })();
}