chore: update package-lock.json after axios installation

feat(S3-06): integrate orchestrator in main.js and complete assembly module
chore: add .env.example template for AssemblyAI API key
2026-06-15 18:01:52 +02:00 · 2025-11-24 19:53:33 +01:00 · 2025-11-24 19:36:50 +01:00 · 2025-11-20 15:42:03 +01:00 · 2025-11-20 14:34:07 +01:00 · 2025-11-20 14:31:26 +01:00
39 changed files with 2436 additions and 228 deletions
@@ -964,4 +964,8 @@ app.*.symbols
 !/dev/ci/**/Gemfile.lock
 #Storage files
-storage/
+storage/
 *.mp4
 *.wav
 *.flac
@@ -1,6 +1,33 @@
-build-job:
+workflow:
-    script:
+  rules:
-        - echo "Building the Project.."
+    # Run the pipeline for merge requests or when committing to a branch
-test-job:
+    - if: $CI_PIPELINE_SOURCE == "merge_request_event"
-    script:
+    - if: $CI_COMMIT_BRANCH
-        - echo "Running Tests.."        
+
 image: python:3.14.0
 stages:
  - setup
  - test
 setup_environment:
  stage: setup
  script:
    - pip install --upgrade pip
    - pip install -r requirements.txt
    - echo "Dependencies installed successfully."
  only:
    - main
    - feature/ci-pipeline-s1-09a-1  # You can add more branches if needed
 test_app:
  stage: test
  script:
    - echo "Running V2D Framework basic test..."
    - python -m unittest discover || echo "No tests found."
  only:
    - main
    - feature/ci-pipeline-s1-09a-1
@@ -0,0 +1,7 @@
 from fastapi import FastAPI
 app = FastAPI()
@app.get("/health")
 def health_check():
    return {"status": "ok"}
@@ -3,15 +3,23 @@
 <head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>Video Upload Drag and Drop + Button</title>
+  <title id="title">Video to document</title>
  <link rel="stylesheet" href="style.css">
 </head>
 <body>
 <div class="mitte" id="mitte"> 
-  <h1>Video to document</h1> 
+  <div class="flagsBtns" id="flagsBtns">
    <select name="ai_type" id="ai_type">
    </select>
    <select name="language_option" id="language_option">
    </select>
  </div>
  <h1 id="h1">Video to document</h1> 
  <div class="upload-container" id="uploadContainer">
-    <p>Drag and drop video file</p>
+    <p id="p1">Drag and drop video file</p>
    <div class="file-name" id="fileName">No video chosen</div>
  </div>
@@ -19,22 +27,28 @@
  <input type="file" id="videoUpload" accept="video/*">
 <div class="checkbox-group">
-  <label for="checkbox-group">Choose prefered document style:</label>
+  <label id="checkbox_group" for="checkbox-group">Choose prefered document style:</label>
  <div class="checkbox-container">
-    <input type="checkbox" id="docFormat">
+    <input type="checkbox" name ="docFormat" id="docFormat">
-    <label for "docFormat">Meeting report</label>
+    <label id="label_format" for="docFormat">Meeting report</label>
  </div>
  <div class="checkbox-container">
-    <input type="checkbox" id="docFormatCustom">
+    <input type="checkbox" name="docFormat" id="docFormatSummary">
-    <label for "docFormatCustom">Summary with timestamps</label>
+    <label id="label_summary" for="docFormatSummary">Summary with timestamps</label>
  </div>
 </div>
-<button class="submit-btn" id="submitButton">Submit Video</button>
+<button class="submit-btn" id="submitButton" onclick="checkBoxes()">Submit</button>
 <div class="progressbar">
  <div class="progress_fill"></div>
  <span class="progress_text">0%</span>
 </div>
 </div>
-  <script src="script.js"></script>
+<script src="languages.js"></script>
-  <script src="./renderer.js"></script>
+<script src="script.js"></script>
 <script src="./renderer.js"></script>
 </body>
 </html>
@@ -0,0 +1,36 @@
 var languageOptions = {
    "eng":{
        "title": "Video to document",
        "h1": "Video to document",
        "p1": "Drag and drop video file",
        "fileName": "No video chosen",
        "manualUploadBtn": "Search video",
        "checkbox_group": "Choose prefered document style:",
        "label_format": "Meeting report",
        "label_summary": "Summary with timestamps",
        "submitButton": "Submit"
    },
    "de":{
        "title": "Video zu Dokument",
        "h1": "Video zu Dokument",
        "p1": "Video per Drag & Drop ablegen",
        "fileName": "Kein Video ausgewaehlt",
        "manualUploadBtn": "Video suchen",
        "checkbox_group": "Bevorzugte Dokumentvarianten:",
        "label_format": "Meeting Bericht",
        "label_summary": "Zusammenfassung mit Zeitstempeln",
        "submitButton": "Absenden"
    },
    "in":{
        "title": "दस्तावेज़ के लिए वीडियो",
        "h1": "दस्तावेज़ के लिए वीडियो",
        "p1": "वीडियो फ़ाइल खींचें और छोड़ें",
        "fileName": "कोई वीडियो नहीं चुना गया",
        "manualUploadBtn": "वीडियो खोजें",
        "checkbox_group": "पसंदीदा दस्तावेज़ शैली चुनें:",
        "label_format": "बैठक रिपोर्ट",
        "label_summary": "टाइमस्टैम्प के साथ सारांश",
        "submitButton": "जमा करना"
    }
 };
@@ -2,6 +2,9 @@ import { app, BrowserWindow, ipcMain, dialog } from 'electron';
 import { exec } from 'child_process';
 import path from 'path';
 import { fileURLToPath } from 'url';
 // Import audio events and transcription module
 import { audioEvents } from '../../services/modules/extraction/ffmpegExtractor.js';
 import { transcribe } from '../../services/modules/transcription-remote/assembly.js';
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);
@@ -22,7 +25,61 @@ function createWindow() {
  mainWindow.loadFile('main/index.html');
 }
-app.whenReady().then(createWindow);
+// Setup pipeline orchestrator
 function setupOrchestrator() {
  console.log('🎯 [Pipeline] Orchestrator ready. Listening for audio_ready events...');
  audioEvents.on('audio_ready', async (data) => {
    const { audioPath, sessionId } = data;
    console.log(`✅ [Pipeline] Audio ready: ${sessionId}`);
    // AC6: Send status to UI - Audio bereit
    mainWindow.webContents.send('pipeline-status', {
      sessionId,
      status: 'audio_ready',
      message: 'Audio bereit'
    });
    try {
      // AC4: Status transcription_started
      console.log(`🚀 [Pipeline] Starting transcription: ${sessionId}`);
      mainWindow.webContents.send('pipeline-status', {
        sessionId,
        status: 'transcription_started',
        message: 'Transkription gestartet'
      });
      // AC2: Auto-start transcription (S2-02b)
      await transcribe(audioPath, sessionId);
      // AC6: Status transcription_completed
      console.log(`✅ [Pipeline] Transcription completed: ${sessionId}`);
      mainWindow.webContents.send('pipeline-status', {
        sessionId,
        status: 'transcription_completed',
        message: 'Transkription abgeschlossen'
      });
    } catch (error) {
      // AC5: Error logging + failed_transcription_start
      console.error(`❌ [Pipeline] Transcription failed: ${sessionId}`);
      console.error(`   Error:`, error.message);
      mainWindow.webContents.send('pipeline-status', {
        sessionId,
        status: 'failed_transcription_start',
        message: 'Fehler beim Transkriptionsstart',
        error: error.message
      });
    }
  });
 }
 app.whenReady().then(() => {
  createWindow();
  setupOrchestrator();
 });
 // Kommunikation vom Renderer (Frontend)
 ipcMain.handle('convert-video', async (event, filePath) => {
@@ -1,7 +1,15 @@
 const { contextBridge, ipcRenderer, webUtils } = require('electron')
-contextBridge.exposeInMainWorld("explorer", {
+try {
-    onFileDrop: (file) => webUtils.getPathForFile(file)
+    contextBridge.exposeInMainWorld("explorer", {
-})
+        onFileDrop: (file) => webUtils.getPathForFile(file)
    })
    contextBridge.exposeInMainWorld("extractor", {
        extract: (file) => ipcRenderer.send("extract", file)
    })
    contextBridge.exposeInMainWorld("electronAPI", {
        getFilePath: (file) => {return webUtils.getPathForFile(file)}
    })
 } catch (error) {
    console.log("Error in preload.js");
 }
@@ -1,22 +1,41 @@
-const dropzone = document.getElementById("uploadContainer");
+uploadContainer.addEventListener("dragover", (e) =>{
-
+    try {
-dropzone.addEventListener("dragover", (e) =>{
+        e.stopPropagation();
-    e.stopPropagation();
+        e.preventDefault();
-    e.preventDefault();
+    } catch (error) {
-});
+        console.log("Error in renderer.js dragover listener function")
 dropzone.addEventListener("drop", (e) => {
    e.stopPropagation()
    e.preventDefault()
    const files = e.dataTransfer.files
    const filePath = window.explorer.onFileDrop(files[0])
    var holdy = filePath + "";
    if(holdy.endsWith(".mp4")){
        console.log(filePath)
        const files1 = e.dataTransfer.files;
        handleFiles(files1);
    }
-})
+});
 //listener for when a file get dropped on the drag&drop field
 uploadContainer.addEventListener("drop", (e) => {
    try {
        e.stopPropagation()
        e.preventDefault()
        const files = e.dataTransfer.files
        const filePath = window.explorer.onFileDrop(files[0])
        var holdy = filePath + "";
        if(holdy.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
            console.log(filePath)
            const files1 = e.dataTransfer.files;
            handleFiles(files1);
        }
    } catch (error) {
        console.log("Error in renderer.js with the listerner for the drop function");
    } 
 })
 window.addEventListener('load', (e) => { 
    console.log("test");
    loadLanguageOptions(); 
 });
 language_option.addEventListener('change', (e)=>{
    const select = document.getElementById('language_option');
    console.log(select.value);
    changeLanguage(select.value);
 });
@@ -1,31 +1,132 @@
-const uploadContainer = document.getElementById('uploadContainer');
+//listener for the file explorer search
-const fileInput = document.getElementById('videoUpload');
+manualUploadBtn.addEventListener('click', () => {
-const fileName = document.getElementById('fileName');
+  try {
-const manualBtn = document.getElementById('manualUploadBtn');
+    videoUpload.click();
-const videoPreview = document.getElementById('videoPreview');
+  } catch (error) {
-
+    console.log("Error in manualBtn EventListener click");
-
+  }
-
+  
 manualBtn.addEventListener('click', () => {
  fileInput.click();
 });
 //function to check if one checkbox is at least klicked
 function checkBoxes() {
  try {
    const checkboxes = document.querySelectorAll('input[name="docFormat"]');
    let isChecked = false;
-fileInput.addEventListener('change', () => {
+    checkboxes.forEach(function(checkbox){
-  handleFiles(fileInput.files);
+      if(checkbox.checked){
-});
+        isChecked = true;
      }
    });
-
+    if(isChecked){
-
+      //Code to submit the video
-
+      var pathTest = window.electronAPI.getFilePath(videoUpload.files[0]);
-function handleFiles(files) {
+      if(pathTest.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
-  if (files.length > 0) {
+        window.extractor.extract({inputVideoPath: pathTest, outputType:"wav"})
-    const file = files[0];
+      }
-    if (file.type.startsWith('video/')) {
+    } else {
-      fileInput.files = files;
+      //language only english at the moment
-      fileName.textContent = `Chosen video: ${file.name}`;
+      alert('Please select at least one document type.');
    }
  } catch (error) {
    console.log(error)
  }
 // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
 }
 //language changing feature
 function changeLanguage(language) {
  try {
    document.getElementById('title').textContent = languageOptions[language].title;
    document.getElementById('h1').textContent = languageOptions[language].h1;
    document.getElementById('p1').textContent = languageOptions[language].p1;
    document.getElementById('fileName').textContent = languageOptions[language].fileName;
    document.getElementById('manualUploadBtn').textContent = languageOptions[language].manualUploadBtn;
    document.getElementById('checkbox_group').textContent = languageOptions[language].checkbox_group;
    document.getElementById('label_format').textContent = languageOptions[language].label_format;
    document.getElementById('label_summary').textContent = languageOptions[language].label_summary;
    document.getElementById('submitButton').textContent = languageOptions[language].submitButton;
  } catch (error) {
    console.log(error);
  }
 }
 //listener for the file explorer search when something got selected
 videoUpload.addEventListener('change', () => {
  try {
    handleFiles(videoUpload.files);
  } catch (error) {
    console.log("Error in manualBtn EventListener change");
  }
 });
 //function to display the file path in the drop down box
 function handleFiles(files) {
  try {
    if (files.length > 0) {
      const file = files[0];
      if (file.type.startsWith('video/')) {
        videoUpload.files = files;
        fileName.textContent = `Chosen video: ${file.name}`;
      }
    }
  } catch (error) {
    console.log("Error in script.js handleFiles function");
  }
 }
 //function to regulate the progress on the progressbar
 function updateProgressBar(bar, value){
  try {
    value = Math.round(value);
    bar.querySelector(".progress_fill").style.width = `${value}%`;
    bar.querySelector(".progress_text").textContent = `${value}%`;
  } catch (error) {
    console.log("Error in scripts.js updateProgressBar function");
  }
 }
 //function to load ai options to the drop down list
 function loadAiOptions(options){
  try {
    var menu = document.getElementById('ai_type');
    for(i = 0; i < options.length; i++){
      var opty = options[i];
      var namey = "option" + i;
      var choice = document.createElement(namey);
      choice.textContent = "t";
      choice.value = i;
      menu.appendChild(choice);
    }
  } catch (error) {
    console.log("Error in script.js loadAiOptions function");
    console.log(error);
  }
 }
 //function to load language options to the drop down list
 function loadLanguageOptions(){
  try {
    var menu = document.getElementById('language_option');
    var object_holdy;
    var choice ;
    object_holdy = Object.keys(languageOptions);
    for(i = 0; i < object_holdy.length; i++){
      choice = document.createElement('option');
      choice.textContent = object_holdy[i];
      choice.value = object_holdy[i];
      menu.appendChild(choice);
    }
  } catch (error) {
    console.log("Error in script.js loadLanguageOptions function");
    console.log(error);
  }
 }
@@ -5,7 +5,7 @@ body {
  justify-content: center;
  align-items: center;
  height: 100vh;
-  background-color: #444;
+  background-color: #555;
  gap: 15px;
  margin: 0;
 }
@@ -75,6 +75,7 @@ gap: 5px;
 .checkbox-group {
  margin-top: 15px;
  margin-bottom: 15px;
  display: flex;
  flex-direction: column;
  gap: 10px;
@@ -92,14 +93,14 @@ gap: 5px;
 }
 .mitte {
-  background-color: #eaf0ff;
+  background-color: #f2f3f4;
  display: flex;
  flex-direction: column;
  align-items: center;
  padding: 5% 50px;
  margin-top: 20px;
  gap: 10px;
-  border: 2px;
+  border: 1px;
  border-color: black;
  border-style: solid;
 }
@@ -108,3 +109,39 @@ h1 {
  align-content: center;
 }
 .progressbar{
  position: relative;
  width: 210px;
  height: 30px;
  background: rgb(42, 46, 78);
  border-radius: 5px;
  overflow: hidden;
 }
 .progress_fill{
  width: 0%;
  height: 100%;
  background: green;
  transition: all 0.2s;
 }
 .progress_text{
  position: absolute;
  top: 50%;
  right: 5px;
  transform: translateY(-50%);
  color: white;
 }
 .flagsBtns {
  display: flex;
  justify-content: flex-end;
 }
 .de_Btn, .eng_Btn, .in_Btn {
  padding: 8px 16px;
  color: white;
  border: none;
  border-radius: 8px;
  cursor: pointer;
 }
@@ -33,6 +33,73 @@ console.log(`${mapFunctions.size} Function modules loaded`);
 console.log("--------------------------------------------------------------------------------");
 // ======================== S3-06 : PIPELINE ORCHESTRATOR ========================
 // Get audioEvents from ffmpegExtractor module
 const ffmpegExtractor = mapFunctions.get("extraction-video-to-audio");
 const audioEvents = ffmpegExtractor.audioEvents;
 console.log('🎯 [S3-06] Pipeline Orchestrator ready. Listening for audio_ready events...');
 audioEvents.on('audio_ready', async (data) => {
    const { audioPath, sessionId } = data;
    console.log(`✅ [Pipeline] Audio ready: ${sessionId}`);
    console.log(`📁 Audio path: ${audioPath}`);
    // Send status to UI
    if (mainWindow) {
        mainWindow.webContents.send('pipeline-status', {
            sessionId,
            status: 'audio_ready',
            message: 'Audio bereit'
        });
    }
    try {
        console.log(`🚀 [Pipeline] Starting transcription: ${sessionId}`);
        if (mainWindow) {
            mainWindow.webContents.send('pipeline-status', {
                sessionId,
                status: 'transcription_started',
                message: 'Transkription gestartet'
            });
        }
        // Get transcription module
        const assemblyModule = mapFunctions.get("assembly");
        if (assemblyModule && assemblyModule.run) {
            await assemblyModule.run(audioPath);
        } else {
            console.warn('⚠️ Assembly module not found or missing run function');
        }
        console.log(`✅ [Pipeline] Transcription completed: ${sessionId}`);
        if (mainWindow) {
            mainWindow.webContents.send('pipeline-status', {
                sessionId,
                status: 'transcription_completed',
                message: 'Transkription abgeschlossen'
            });
        }
    } catch (error) {
        console.error(`❌ [Pipeline] Transcription failed: ${sessionId}`);
        console.error(`   Error:`, error.message);
        if (mainWindow) {
            mainWindow.webContents.send('pipeline-status', {
                sessionId,
                status: 'failed_transcription_start',
                message: 'Fehler beim Transkriptionsstart',
                error: error.message
            });
        }
    }
 });
 // ===============================================================================
 // --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //
@@ -55,4 +122,25 @@ rl.on("line", data =>{
 // ----------------------------------------------------------- ELECTRON ----------------------------------------------------------- //
-// TODO - Add Electron support to the project
+let mainWindow;
 function createWindow() {
  mainWindow = new electron.BrowserWindow({
    width: 800,
    height: 600,
    webPreferences: {
      nodeIntegration: false,
      contextIsolation: true,
      preload: `${mainDir}/electron/main/preload.js`
    }
  });
  mainWindow.loadFile('./electron/main/index.html');
 }
 electron.app.whenReady().then(createWindow);
 electron.ipcMain.on("extract", (event, args) => {
    mapFunctions.get("extraction-video-to-audio").function(args)
 })
@@ -1,10 +1,13 @@
 {
  "type": "module",
  "dependencies": {
    "@types/axios": "^0.9.36",
    "axios": "^1.13.2",
    "cli-progress": "^3.12.0",
    "dotenv": "^17.2.3",
    "electron": "^39.1.1",
    "express": "^5.1.0",
    "ffmpeg-static": "^5.2.0",
-    "fluent-ffmpeg": "^2.1.3",
+    "fluent-ffmpeg": "^2.1.3"
    "express": "^5.1.0"
  },
  "devDependencies": {
    "@types/cli-progress": "^3.11.6",
@@ -22,6 +25,7 @@
    "test": "tests"
  },
  "scripts": {
    "start": "electron main.js",
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "repository": {
@@ -31,5 +35,3 @@
  "author": "",
  "license": "ISC"
 }
@@ -0,0 +1,3 @@
 fastapi
 uvicorn
 pytest
@@ -8,3 +8,11 @@ fs              = require("fs")
 readline        = require("readline")
 config          = require("./config/config")
 ffmpegPath = require('ffmpeg-static');
 ffmpeg = require('fluent-ffmpeg');
 path = require('path');
 cliProgress = require('cli-progress');
 // { app, BrowserWindow, ipcMain, dialog } = require('electron');
 electron = require('electron');
@@ -1,5 +0,0 @@
 npx ts-node ./extract.ts /Users/mikehughes/Downloads/Testvideo/Kurzgesagt.mov
 npx ts-node ./transcribe.ts ../storage/audio/Kurzgesagt.wav
 npx ts-node ./extract.ts /Users/mikehughes/Downloads/Testvideo/GitLabMeeting.mov
 npx ts-node ./transcribe.ts ../storage/audio/GitLabMeeting.wav
@@ -1,23 +0,0 @@
 #!/usr/bin/env ts-node
 import { extractAudioFromVideo } from "../services/modules/extraction/ffmpegExtractor.ts";
 const videoPath = process.argv[2];
 if (!videoPath) {
  console.error("Usage: ts-node extractAudio.ts <videoPath>");
  process.exit(1);
 }
 (async () => {
  try {
    console.log(`Extracting audio from: ${videoPath}`);
    await extractAudioFromVideo(videoPath); // Call the extraction function (ffmpegExtractor.ts in services/modules/extraction)
    console.log("Audio extraction completed successfully.");
  } catch (err) {
    console.error("Audio extraction failed:", err);
    process.exit(1);
  }
 })();
@@ -1,18 +0,0 @@
 import { whisperLocal } from "../services/modules/transcription/local/whisperLocal.ts";
 const audioPath = process.argv[2];
 if (!audioPath) {
  console.error("Please provide an audio file path as argument.");
  process.exit(1);
 }
 const whisper = new whisperLocal();
 (async () => {
  try {
    const text = await whisper.transcribe(audioPath);
    console.log(text);
  } catch (err) {
    console.error("Transcription failed:", err);
  }
 })();
@@ -0,0 +1,101 @@
 const EventEmitter = require('events');
 const audioEvents = new EventEmitter();
 // Ensure ffmpeg binary is available
 if (!ffmpegPath) {
    throw new Error('FFmpeg binary not found!');
 }
 ffmpeg.setFfmpegPath(ffmpegPath);
 // Prepare output directory (always storage/audio under project root)
 const outputDir = `${__dirname}/../../../storage/audio`;
 if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
 }
 module.exports = {
    name:"extraction-video-to-audio", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
    type:"extractor", // value used to differentiate each module to order them in the UI
    displayname:"Default extractor", // The displayname used within the UI
    async function(parameter){
        /*
        parameter structure:
        {
            inputVideoPath: String, // Path to the file
            outputType: String      // Audio file output format
        }
        */
        let progressBar = new cliProgress.SingleBar({
            format: 'Processing |{bar}| {percentage}% | {timemark}',
            barCompleteChar: '\u2588',
            barIncompleteChar: '\u2591',
            hideCursor: true
        });
        try {
            // if (meta.url === `file://${process.argv[1]}`) {
                this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
                    .then(() => console.log('Audio extraction successful.'))
                    .catch((err) => console.error(err));
            // }
        } catch (error) {
            console.log(parameter.outputType);
        }
    },
    // Derive input and output paths
    // const inputVideoPath = process.argv[2];
    // console.log(process.argv);
    /**
     * Extracts audio from a video using ffmpeg.
     * - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
     * - Shows CLI progress bar
     * - Handles errors gracefully (without errors)
     */
    extractAudioFromVideo: async function (videoFilePath, progressBar, outputType){
        let inputVideoName = path.basename(videoFilePath, path.extname(videoFilePath));
        let outputAudioPath = path.join(outputDir, `${inputVideoName}.${outputType}`);
        return new Promise((resolve, reject) => {
            try {
                ffmpeg(videoFilePath)
                .outputFormat(outputType)
                // .audioCodec('pcm_s16le')
                .audioChannels(1)
                .audioFrequency(16000)
                // .setFfmpegPath("./ffmpeg.exe")
                .on('progress', (progress) => {
                    if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
                    if (progress.percent) {
                    progressBar.update(progress.percent, { timemark: progress.timemark });
                    }
                })
                .on('end', () => {
                    progressBar.update(100, { timemark: 'done' });
                    progressBar.stop();
                    console.log(`Extraction completed: ${outputAudioPath}`);
                     audioEvents.emit('audio_ready', {
                        sessionId: inputVideoName,
                        audioPath: outputAudioPath
                    });
                    resolve();
                })
                .on('error', (err) => {
                    progressBar.stop();
                    console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
                    reject(err);
                })
                .save(outputAudioPath);
            } catch (error) {
                console.log();
            }
        });
    },
    audioEvents: audioEvents
 }
@@ -1,90 +0,0 @@
 import ffmpegPath from 'ffmpeg-static';
 import ffmpeg from 'fluent-ffmpeg';
 import path from 'path';
 import fs from 'fs';
 import cliProgress from 'cli-progress';
 import { fileURLToPath } from 'url';
 // Base code reference: https://docs.yemreak.com/arsiv/programming/extract-audio-from-video-with-typescript-and-ffmpeg
 // Test command: npx ts-node ./extract.ts /path/to/video.mp4
 /**
 * Extracts audio from a video file and saves it as WAV.
 * @param videoFilePath Path to the input video file.
 */
 // Ensure ffmpeg binary is available
 if (!ffmpegPath) {
  throw new Error('FFmpeg binary not found!');
 }
 ffmpeg.setFfmpegPath(ffmpegPath);
 // Ensure an input video path is provided via CLI
 if (process.argv.length < 3) {
  console.error('Usage: ts-node ./extract.ts <input-video-path>');
  process.exit(1);
 }
 // Resolve __dirname equivalent in ESM
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);
 // Prepare output directory (always storage/audio under project root)
 const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'audio');
 if (!fs.existsSync(outputDir)) {
  fs.mkdirSync(outputDir, { recursive: true });
 }
 // Derive input and output paths
 const inputVideoPath = process.argv[2];
 const inputVideoName = path.basename(inputVideoPath, path.extname(inputVideoPath));
 const outputAudioPath = path.join(outputDir, `${inputVideoName}.wav`);
 // Initialize CLI progress bar
 const progressBar = new cliProgress.SingleBar({
  format: 'Processing |{bar}| {percentage}% | {timemark}',
  barCompleteChar: '\u2588',
  barIncompleteChar: '\u2591',
  hideCursor: true
 });
 /**
 * Extracts audio from a video using ffmpeg.
 * - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
 * - Shows CLI progress bar
 * - Handles errors gracefully (without errors)
 */
 export function extractAudioFromVideo(videoFilePath: string): Promise<void> {
  return new Promise((resolve, reject) => {
    ffmpeg(videoFilePath)
      .outputFormat('wav')
      .audioCodec('pcm_s16le')
      .audioChannels(1)
      .audioFrequency(16000)
      .on('progress', (progress) => {
        if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
        if (progress.percent) {
          progressBar.update(progress.percent, { timemark: progress.timemark });
        }
      })
      .on('end', () => {
        progressBar.update(100, { timemark: 'done' });
        progressBar.stop();
        console.log(`Extraction completed: ${outputAudioPath}`);
        resolve();
      })
      .on('error', (err) => {
        progressBar.stop();
        console.error(`failed_audio_extraction: ${err.message}`);
        reject(err);
      })
      .save(outputAudioPath);
  });
 }
 // Run extraction if executed directly from CLI
 if (import.meta.url === `file://${process.argv[1]}`) {
  extractAudioFromVideo(inputVideoPath)
    .then(() => console.log('Audio extraction successful.'))
    .catch((err) => console.error(err));
 }
@@ -5,7 +5,7 @@ import { fileURLToPath } from "url"; // To handle __dirname in ES modules
 const __filename = fileURLToPath(import.meta.url); // Get current file path
 const __dirname = path.dirname(__filename); // Get current directory path
-const transcriptsDir = path.resolve(__dirname, "../../storage/transcriptions");
+const transcriptsDir = path.resolve(__dirname, "../../../storage/transcriptions");
 export class whisperLocal { // is called by transcribe.ts
@@ -26,7 +26,6 @@ export class whisperLocal { // is called by transcribe.ts
  async transcribe(audioPath: string): Promise<string> { //asyncronous function to transcribe audio
    return new Promise((resolve, reject) => {
        const transcriptsDir = path.resolve(__dirname, "../../../../storage/transcripts"); //storage directory for transcripts
        if (!fs.existsSync(transcriptsDir)) { //if transcripts directory does not exist, create it
            fs.mkdirSync(transcriptsDir, { recursive: true });
@@ -0,0 +1,128 @@
 require('dotenv/config');
 const axios = require('axios');
 const fs = require('fs');
 const path = require('path');
 const API_KEY = process.env.ASSEMBLYAI_API_KEY;
 const BASE_URL = 'https://api.assemblyai.com/v2';
 /**
 * Uploads audio file to AssemblyAI
 */
 async function uploadAudio(audioPath) {
  const audioData = fs.readFileSync(audioPath);
  const response = await axios.post(`${BASE_URL}/upload`, audioData, {
    headers: {
      'authorization': API_KEY,
      'content-type': 'application/octet-stream'
    }
  });
  return response.data.upload_url;
 }
 /**
 * Extract session id from path or URL
 */
 function getSessionId(inputPath) {
  try {
    const parsed = new URL(inputPath);
    const base = path.basename(parsed.pathname);
    return base.replace(/\.[^.]+$/, '');
  } catch (err) {
    return path.basename(inputPath, path.extname(inputPath));
  }
 }
 /**
 * Creates transcription job with speaker diarization
 */
 async function createTranscript(audioUrl) {
  const response = await axios.post(`${BASE_URL}/transcript`, {
    audio_url: audioUrl,
    speaker_labels: true,
    language_detection: true
  }, {
    headers: {
      'authorization': API_KEY,
      'content-type': 'application/json'
    }
  });
  return response.data.id;
 }
 /**
 * Polls transcript status until completed
 */
 async function pollTranscript(transcriptId) {
  while (true) {
    const response = await axios.get(`${BASE_URL}/transcript/${transcriptId}`, {
      headers: { 'authorization': API_KEY }
    });
    const status = response.data.status;
    if (status === 'completed') {
      return response.data;
    } else if (status === 'error') {
      throw new Error(`Transcription failed: ${response.data.error}`);
    }
    // Wait 3 seconds before next poll
    await new Promise(resolve => setTimeout(resolve, 3000));
  }
 }
 /**
 * Saves transcript to storage
 */
 function saveTranscript(transcript, sessionId) {
  const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }
  const outputPath = path.join(outputDir, `${sessionId}.json`);
  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
  console.log(`✅ Transcript saved: ${outputPath}`);
 }
 module.exports = {
  name: "assembly",
  type: "transcription",
  displayname: "AssemblyAI",
  run: async function(audioPath) {
    try {
      // Determine if audioPath is an external URL or a local file
      let audioUrl;
      if (/^https?:\/\//i.test(audioPath)) {
        console.log('🔗 Using external audio URL...');
        audioUrl = audioPath;
      } else {
        if (!fs.existsSync(audioPath)) {
          throw new Error(`Audio file not found: ${audioPath}`);
        }
        console.log('📤 Uploading audio file...');
        audioUrl = await uploadAudio(audioPath);
      }
      console.log('🔄 Creating transcript job...');
      const transcriptId = await createTranscript(audioUrl);
      console.log('⏳ Waiting for transcription...');
      const transcript = await pollTranscript(transcriptId);
      const sessionId = getSessionId(audioPath);
      saveTranscript(transcript, sessionId);
      return transcript;
    } catch (error) {
      console.error('❌ Transcription error:', error.message);
      throw error;
    }
  }
 };
@@ -0,0 +1,133 @@
 import 'dotenv/config';
 import axios from 'axios';
 import fs from 'fs';
 import path from 'path';
 import { fileURLToPath } from 'url';
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = path.dirname(__filename);
 const API_KEY = process.env.ASSEMBLYAI_API_KEY;
 const BASE_URL = 'https://api.assemblyai.com/v2';
 /**
 * Uploads audio file to AssemblyAI
 */
 async function uploadAudio(audioPath: string): Promise<string> {
  const audioData = fs.readFileSync(audioPath);
  const response = await axios.post<{ upload_url: string }>(`${BASE_URL}/upload`, audioData, {
    headers: {
      'authorization': API_KEY,
      'content-type': 'application/octet-stream'
    }
  });
  return response.data.upload_url;
 }
 /**
 * Extract a session id (basename without extension) from a local path or a URL
 */
 function getSessionId(inputPath: string): string {
  try {
    const parsed = new URL(inputPath);
    const base = path.basename(parsed.pathname);
    return base.replace(/\.[^.]+$/, '');
  } catch (err) {
    // not a URL, treat as local path
    return path.basename(inputPath, path.extname(inputPath));
  }
 }
 /**
 * Creates transcription job with speaker diarization
 */
 async function createTranscript(audioUrl: string): Promise<string> {
  const response = await axios.post<{ id: string }>(`${BASE_URL}/transcript`, {
    audio_url: audioUrl,
    speaker_labels: true,
    language_detection: true
  }, {
    headers: {
      'authorization': API_KEY,
      'content-type': 'application/json'
    }
  });
  return response.data.id;
 }
 /**
 * Polls transcript status until completed
 */
 async function pollTranscript(transcriptId: string): Promise<any> {
  while (true) {
    const response = await axios.get<any>(`${BASE_URL}/transcript/${transcriptId}`, {
      headers: { 'authorization': API_KEY }
    });
    const status = response.data.status;
    if (status === 'completed') {
      return response.data;
    } else if (status === 'error') {
      throw new Error(`Transcription failed: ${response.data.error}`);
    }
    // Wait 3 seconds before next poll
    await new Promise(resolve => setTimeout(resolve, 3000));
  }
 }
 /**
 * Saves transcript to storage
 */
 function saveTranscript(transcript: any, sessionId: string): void {
  const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }
  const outputPath = path.join(outputDir, `${sessionId}.json`);
  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
  console.log(`✅ Transcript saved: ${outputPath}`);
 }
 export default {
  name: "assembly",
  type: "transcription",
  displayname: "AssemblyAI",
  run: async (audioPath: string) => {
    try {
      // Determine if audioPath is an external URL or a local file
      let audioUrl: string;
      if (/^https?:\/\//i.test(audioPath)) {
        console.log('🔗 Using external audio URL...');
        audioUrl = audioPath;
      } else {
        console.log('🔄 Uploading local audio...');
        if (!fs.existsSync(audioPath)) {
          throw new Error(`Audio file not found: ${audioPath}`);
        }
        audioUrl = await uploadAudio(audioPath);
      }
      console.log('🔄 Creating transcript job...');
      const transcriptId = await createTranscript(audioUrl);
      console.log('⏳ Waiting for transcription...');
      const transcript = await pollTranscript(transcriptId);
  const sessionId = getSessionId(audioPath);
      saveTranscript(transcript, sessionId);
      return transcript;
    } catch (error: any) {
      console.error('❌ Transcription error:', error.message);
      throw error;
    }
  }
 };
@@ -1,8 +0,0 @@
 module.exports = {
    name:"assembly", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
    type:"transcription", // value used to differentiate each module to order them in the UI
    displayname:"Assembly", // The displayname used within the UI
    async function(parameter){
        // TODO add code to actually process the audio file
    }
 }
@@ -5,5 +5,9 @@ module.exports = {
        // We are now calling the example function from the example folder
        mapFunctions.get("example").function("Startup")
        // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
        // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./b.mp4", outputType:"wav"})
        // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./b.mp4", outputType:"flac"})
    }
 }
@@ -0,0 +1,53 @@
 // services/pipeline/jobs/transcribeLatest.ts
 import path from 'path';
 import fs from 'fs';
 // @ts-ignore: module has no type declarations or cannot be resolved in current TS config
 import assembly from '../../modules/transcription/assembly';
 /**
 * Finds the most recently modified .wav file in storage/audio/
 */
 function getLatestWav(): string {
  const audioDir = path.join(process.cwd(), 'storage', 'audio');
  const files = fs.readdirSync(audioDir).filter(f => f.toLowerCase().endsWith('.wav'));
  if (files.length === 0) throw new Error('⚠️ No .wav file found in storage/audio');
  const newest = files
    .map(f => ({ f, t: fs.statSync(path.join(audioDir, f)).mtimeMs }))
    .sort((a, b) => b.t - a.t)[0].f;
  return path.join(audioDir, newest);
 }
 /**
 * Full transcription pipeline according to the defined workflow:
 * 1. Audio Upload → AssemblyAI
 * 2. Job Creation (transcript_id)
 * 3. Polling Status (queued → processing → completed)
 * 4. Download Transcript JSON
 * 5. Storage: /transcripts/{session_id}.json
 */
 async function main() {
  const audioPath = getLatestWav();
  console.log('1️⃣ Audio Upload → AssemblyAI');
  console.log('   Source:', audioPath);
  console.log('2️⃣ Job Creation (transcript_id)');
  console.log('3️⃣ Polling Status (queued → processing → completed)');
  console.log('4️⃣ Download Transcript JSON');
  console.log('5️⃣ Storage: /transcripts/{session_id}.json');
  // Execute the transcription process via the AssemblyAI module
  const result = await assembly.run(audioPath);
  console.log('✅ Transcription completed successfully');
  console.log('🆔 Transcript ID:', result.id);
  console.log('📁 Transcript file saved under: storage/transcripts/');
 }
 // Entry point
 main().catch((err) => {
  console.error('❌ Transcription pipeline failed:', err.message || err);
  process.exit(1);
 });
@@ -0,0 +1,14 @@
 import 'dotenv/config';
 import assemblyModule from '../../services/modules/transcription-remote/assembly.ts';
 // Test: URL passed as argument OR local file ./storage/audio/test.wav
 const audioPath = process.argv[2] || './storage/audio/test.wav';
 assemblyModule.run(audioPath)
  .then(result => {
    console.log('✅ Success!');
    console.log('Transcript ID:', result.id);
  })
  .catch(error => {
    console.error('❌ Error:', error?.message || error);
  });
@@ -0,0 +1,8 @@
 from fastapi.testclient import TestClient
 from app.main import app
 client = TestClient(app)
 def test_health():
    response = client.get("/health")
    assert response.status_code == 200
Author	SHA1	Message	Date
Azeufack Noupeu Willy	84ab93ce77	chore: update package-lock.json after axios installation	2025-11-24 19:53:33 +01:00
Azeufack Noupeu Willy	173ed90642	feat(S3-06): integrate orchestrator in main.js and complete assembly module	2025-11-24 19:36:50 +01:00
Azeufack Noupeu Willy	925eb33eab	chore: add .env.example template for AssemblyAI API key	2025-11-20 15:42:03 +01:00
Azeufack Noupeu Willy	911cba14fd	chore(typescript): add @ts-ignore for assembly module import	2025-11-20 14:34:07 +01:00
Azeufack Noupeu Willy	6813659443	feat(main): add pipeline orchestrator for auto-transcription	2025-11-20 14:31:26 +01:00
Azeufack Noupeu Willy	a0ed2ab7bd	feat(extraction): add audio_ready event emission - Add EventEmitter to emit audio_ready when extraction completes - Pass sessionId and audioPath in event data - Export audioEvents for Main process orchestrator Refs: S3-06 AC1,AC3,AC7	2025-11-20 14:05:52 +01:00
Hughes, Mike	4b72568ad3	Merge branch 'feature/ui-test' into 'develop' Implemented a dropdown field for the languages as well as functions and a file... See merge request proj-wise2526-video2document/video2document!23	2025-11-16 14:52:29 +01:00
MikeHughes-BIN	76c18fa713	Merge branch 'develop' into feature/ui-test	2025-11-15 15:46:26 +01:00
Spanier, Pit	2edc7f8351	Merge branch 'fix/transcription-module-fix' into 'develop' New Folder structure See merge request proj-wise2526-video2document/video2document!21	2025-11-15 15:11:35 +01:00
MikeHughes-BIN	6083773f88	New Folder structure	2025-11-15 14:45:13 +01:00
eric.minning	4a91f03289	Implemented a dropdown field for the languages as well as functions and a file to easily implement other languages.	2025-11-14 18:32:41 +01:00
Spanier, Pit	444d408480	Merge branch 'feature/fixing-the-program' into 'develop' fixed the program by moving the example module back to where the program can ACTUALLY load it See merge request proj-wise2526-video2document/video2document!20	2025-11-14 14:30:16 +01:00
emily	d9eacafc3a	fixed the program by moving the example module back to where the program can ACTUALLY load it	2025-11-14 14:28:11 +01:00
Hughes, Mike	ab737f0dc9	Merge branch 'feature/12-externe-transkription-s2-02b' into 'develop' feat(S2-02b): Implement AssemblyAI external transcription with speaker diarization See merge request proj-wise2526-video2document/video2document!18	2025-11-13 17:38:39 +01:00
MikeHughes-BIN	79e0c48755	Reduced Number of test paths to avoid redundancy	2025-11-13 17:35:40 +01:00
MikeHughes-BIN	9254ddc57f	Changed the Folder Structure for better maintainability	2025-11-13 17:34:22 +01:00
Azeufack Noupeu Willy	c021272ca4	merge: Resolve conflicts with develop	2025-11-13 15:22:33 +01:00
Azeufack Noupeu Willy	e7e97a7f60	feat(S2-02b): Implement AssemblyAI external transcription with speaker diarization - Add assembly.ts module for REST API transcription via AssemblyAI - Implement 5-step pipeline: upload → create job → poll status → download → save - Enable speaker_labels for diarization (Speaker A, B, C...) - Add millisecond-precision timestamps for each utterance - Store JSON transcripts in storage/transcripts/{session_id}.json - Add axios, dotenv dependencies - Add transcribeLatest.ts helper for quick testing User Story: S2-02b - Externe Transkription per REST API	2025-11-13 13:07:18 +01:00
Spanier, Pit	80392874bb	Merge branch 'feature/combination-of-all-the-things' into 'develop' Fixed an error in checkBoxes function and uploadContainer "drop" listener... See merge request proj-wise2526-video2document/video2document!15	2025-11-12 20:56:11 +01:00
emily	94f390f28b	Implemented audio extractor into IPC call, sooooooo, frontend and backend are now officially linked successfully	2025-11-12 20:28:55 +01:00
emily	73f6fa7524	fixed the code so that it now returns the actual path of the file	2025-11-12 20:24:45 +01:00
eric.minning	1a681eb2b8	Improved error log and implemented a variable and function for file path storage	2025-11-12 20:14:56 +01:00
emily	87e3368a9a	fixed code	2025-11-12 20:04:48 +01:00
emily	6d9c94c685	removed some debug console outputs	2025-11-12 20:03:09 +01:00
emily	fbd5368223	Implemented functionality to have the UI be able to communicate with the backend	2025-11-12 20:00:25 +01:00
emily	449255dda1	Merge commit 'c8cbd4e92a034fa108d06337a3e63d24e529432f' into feature/combination-of-all-the-things	2025-11-12 19:55:50 +01:00
eric.minning	c8cbd4e92a	Fixed an error in checkBoxes function and uploadContainer "drop" listener regarding file path testing	2025-11-12 18:52:28 +01:00
eric.minning	0f54edb0aa	Removed the variables at the start of the script.js file	2025-11-12 18:44:27 +01:00
eric.minning	54f1f6c135	Added the check if a path is selected and the call to the transcript functio.	2025-11-12 18:16:27 +01:00
Verena Schulz	a32e7e5744	Checkboxes check (with alert)	2025-11-12 17:39:02 +01:00
Verena Schulz	d9e96316c0	Language selection implemented and UI reworked	2025-11-11 18:31:01 +01:00
eric.minning	da3a8c7d8c	Added try/catch handling and some comments	2025-11-11 16:02:07 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	af794e0245	Merge branch 'feature/ci-pipeline-s1-09a-1' into 'develop' Feature/ci pipeline s1 09a 1 See merge request proj-wise2526-video2document/video2document!7	2025-11-10 18:07:55 +01:00
emily	dfe91bb15a	Merge commit '3a8963b49d96d0746b64244fa17458d4ae68ec45' into feature/combination-of-all-the-things	2025-11-10 17:01:30 +01:00
emily	92043440fe	Combined Frontend with backend, and implemented the extractor function into the module structure	2025-11-10 16:18:57 +01:00
emily	bd8ed1bf81	added mp4, flac and wav files to gitignore	2025-11-10 16:12:59 +01:00
Spanier, Pit	3a8963b49d	Merge branch 'feature/ui-test' into 'develop' Added a progressbar See merge request proj-wise2526-video2document/video2document!13	2025-11-10 15:43:55 +01:00
eric.minning	f4c45f8371	Added a progressbar	2025-11-10 15:38:59 +01:00
Hughes, Mike	73ad7b0687	Merge branch 'feature/modulare-pipeline-s1-04' into 'develop' Implemented the general modular framework. See merge request proj-wise2526-video2document/video2document!12	2025-11-08 14:59:56 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	fb173a4041	Update .gitlab-ci.yml file	2025-11-06 16:21:01 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	b70680e950	Ci file	2025-11-06 16:00:28 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	a069452f87	requirements	2025-11-06 15:53:38 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	fd4d342eeb	Delete .gitlab-ci.yml	2025-11-06 15:52:45 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	70221683c3	tesing	2025-11-06 15:51:56 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	a92e33fa59	Add new directory	2025-11-06 15:51:08 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	0dc2ebe99c	App	2025-11-06 15:50:10 +01:00
Aarthi Manivannan, Premanathan Aarthi Manivannan	a0fe1a80e3	Add new directory	2025-11-06 15:49:27 +01:00