videotomp3transcriptor/src/services/summarize.js

import OpenAI from 'openai';
import fs from 'fs';
import path from 'path';

let openai = null;

// Max characters per chunk for summarization
const MAX_CHUNK_CHARS = 30000;

/**
 * Get OpenAI client (lazy initialization)
 */
function getOpenAI() {
  if (!openai) {
    if (!process.env.OPENAI_API_KEY) {
      throw new Error('OPENAI_API_KEY environment variable is not set');
    }
    openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
  }
  return openai;
}

/**
 * Summarize text using GPT-4o
 */
export async function summarizeText(text, options = {}) {
  const {
    model = 'gpt-5.1', // GPT-5.1 - latest OpenAI model (Nov 2025)
    language = 'same', // 'same' = same as input, or specify language code
    style = 'concise', // 'concise', 'detailed', 'bullet'
    maxLength = null, // optional max length in words
  } = options;

  const client = getOpenAI();

  let styleInstruction = '';
  switch (style) {
    case 'detailed':
      styleInstruction = 'Provide a detailed summary that captures all important points and nuances.';
      break;
    case 'bullet':
      styleInstruction = 'Provide the summary as bullet points, highlighting the key points.';
      break;
    case 'concise':
    default:
      styleInstruction = 'Provide a concise summary that captures the main points.';
  }

  let languageInstruction = '';
  if (language === 'same') {
    languageInstruction = 'Write the summary in the same language as the input text.';
  } else {
    languageInstruction = `Write the summary in ${language}.`;
  }

  let lengthInstruction = '';
  if (maxLength) {
    lengthInstruction = `Keep the summary under ${maxLength} words.`;
  }

  const systemPrompt = `You are an expert summarizer. ${styleInstruction} ${languageInstruction} ${lengthInstruction}
Focus on the most important information and main ideas. Be accurate and objective.`;

  // Handle long texts by chunking
  if (text.length > MAX_CHUNK_CHARS) {
    return await summarizeLongText(text, { model, systemPrompt, style });
  }

  const response = await client.chat.completions.create({
    model,
    messages: [
      { role: 'system', content: systemPrompt },
      { role: 'user', content: `Please summarize the following text:\n\n${text}` },
    ],
    temperature: 0.3,
  });

  return {
    summary: response.choices[0].message.content,
    model,
    style,
    inputLength: text.length,
    chunks: 1,
  };
}

/**
 * Summarize long text by chunking and combining summaries
 */
async function summarizeLongText(text, options) {
  const { model, systemPrompt, style } = options;
  const client = getOpenAI();

  // Split into chunks
  const chunks = [];
  let currentChunk = '';
  const sentences = text.split(/(?<=[.!?。！？\n])\s*/);

  for (const sentence of sentences) {
    if ((currentChunk + sentence).length > MAX_CHUNK_CHARS && currentChunk) {
      chunks.push(currentChunk.trim());
      currentChunk = sentence;
    } else {
      currentChunk += ' ' + sentence;
    }
  }
  if (currentChunk.trim()) {
    chunks.push(currentChunk.trim());
  }

  console.log(`Summarizing ${chunks.length} chunks...`);

  // Summarize each chunk
  const chunkSummaries = [];
  for (let i = 0; i < chunks.length; i++) {
    console.log(`[${i + 1}/${chunks.length}] Summarizing chunk...`);
    const response = await client.chat.completions.create({
      model,
      messages: [
        { role: 'system', content: systemPrompt },
        { role: 'user', content: `Please summarize the following text (part ${i + 1} of ${chunks.length}):\n\n${chunks[i]}` },
      ],
      temperature: 0.3,
    });
    chunkSummaries.push(response.choices[0].message.content);
  }

  // Combine summaries if multiple chunks
  if (chunkSummaries.length === 1) {
    return {
      summary: chunkSummaries[0],
      model,
      style,
      inputLength: text.length,
      chunks: 1,
    };
  }

  // Create final combined summary
  const combinedText = chunkSummaries.join('\n\n---\n\n');
  const finalResponse = await client.chat.completions.create({
    model,
    messages: [
      { role: 'system', content: `You are an expert summarizer. Combine and synthesize the following partial summaries into a single coherent ${style} summary. Remove redundancy and ensure a smooth flow.` },
      { role: 'user', content: `Please combine these summaries into one:\n\n${combinedText}` },
    ],
    temperature: 0.3,
  });

  return {
    summary: finalResponse.choices[0].message.content,
    model,
    style,
    inputLength: text.length,
    chunks: chunks.length,
  };
}

/**
 * Summarize a text file
 */
export async function summarizeFile(filePath, options = {}) {
  if (!fs.existsSync(filePath)) {
    throw new Error(`File not found: ${filePath}`);
  }

  const { outputDir, ...otherOptions } = options;

  const text = fs.readFileSync(filePath, 'utf-8');
  const result = await summarizeText(text, otherOptions);

  // Save summary to file
  const dir = outputDir || path.dirname(filePath);
  const baseName = path.basename(filePath, path.extname(filePath));
  const summaryPath = path.join(dir, `${baseName}_summary.txt`);

  fs.writeFileSync(summaryPath, result.summary, 'utf-8');

  return {
    ...result,
    filePath,
    summaryPath,
  };
}

/**
 * Get available summary styles
 */
export function getSummaryStyles() {
  return {
    concise: 'A brief summary capturing main points',
    detailed: 'A comprehensive summary with nuances',
    bullet: 'Key points as bullet points',
  };
}