the old report type was still used

Merge branch 'fix/add_puppeteer' into 'develop'
The requirements needed to include puppeteer and html-to-docs See merge request proj-wise2526-video2document/video2document!44
2026-06-15 18:01:52 +02:00 · 2025-12-15 16:06:18 +01:00 · 2025-12-15 15:46:42 +01:00 · 2025-12-15 15:43:03 +01:00 · 2025-12-15 15:03:36 +01:00 · 2025-12-15 14:41:28 +01:00
54 changed files with 17355 additions and 630 deletions
@@ -964,8 +964,22 @@ app.*.symbols
 !/dev/ci/**/Gemfile.lock
 # Storage files
-storage/
+storage/documents/*
 storage/transcriptionSummaries/*
 storage/transcripts/*
 storage/video/*
 # The inverse for the .gitkeep files, to make sure the folders are there but not the local files
 !storage/documents/.gitkeep
 !storage/transcriptionSummaries/.gitkeep
 !storage/transcripts/.gitkeep
 !storage/video/.gitkeep
 *.mp4
 *.webm
 *.mp3
 *.mov
 *.wav
 *.flac
 !testvideo.mp4
@@ -1,33 +1,27 @@
-workflow:
+image: node:latest
  rules:
    # Run the pipeline for merge requests or when committing to a branch
    - if: $CI_PIPELINE_SOURCE == "merge_request_event"
    - if: $CI_COMMIT_BRANCH
 image: python:3.14.0
 stages:
-  - setup
+  # - install
  - test
-setup_environment:
+# job-install:
-  stage: setup
+#   stage: install
-  script:
+#   script:
-    - pip install --upgrade pip
+#     - npm install
-    - pip install -r requirements.txt
+#   artifacts:
-    - echo "Dependencies installed successfully."
+#     untracked: false
 #     when: on_success
 #     access: all
 #     expire_in: "30 days"
 #     paths:
 #       - node_modules
  only:
    - main
    - feature/ci-pipeline-s1-09a-1  # You can add more branches if needed
-test_app:
+
 job-test:
  stage: test
  script:
-    - echo "Running V2D Framework basic test..."
+    - npm install
-    - python -m unittest discover || echo "No tests found."
+    - echo "ASSEMBLYAI_API_KEY=$apikey_assembly" > .env
-
+    - echo "GOOGLE_API_KEY=$apikey_gemini" >> .env
-  only:
+    - npm test
    - main
    - feature/ci-pipeline-s1-09a-1
@@ -9,43 +9,62 @@
 <body>
 <div class="mitte" id="mitte"> 
-  <div class="flagsBtns" id="flagsBtns">
+  <div class="labelDiv" id="labelDiv">
-    <button class="de_Btn" id="de_Btn" onclick="changeLanguage('de')"><img src="flags/germany-flag-png-large.jpg" width="25px" height="20px"/></button>
+    <label id="labelKI">Select ki:</label>
-    <button class="eng_Btn" id="eng_Btn" onclick="changeLanguage('en')"><img src="flags/united-kingdom-flag-png-large.jpg" width="25px" height="20px"/></button>
+    <label id="labelTranscription">Select transcription:</label>
-    <button class="in_Btn" id="in_Btn" onclick="changeLanguage('in')"><img src="flags/india-flag-png-large.png" width="25px" height="20px"/></button>
+    <label id="labelLanguage">Select language:</label>
    <img id="labelLanguageFlag" src="flags/united-kingdom-flag-png-large.jpg" width="20" height="10" >
  </div>
  <div class="dropdownMenus" id="dropdownMenus">
    <select name="ai_type" id="ai_type">
    </select>
    <select name="transkript_type" id="transkript_type">
    </select>
    <select name="output_type" id="output_type">
      <option value="flac">flac</option>
      <option value="mp3">mp3</option>
      <option value="wav">wav</option>
    </select>
    <select name="language_option" id="language_option">
    </select>
  </div>
  <h1 id="h1">Video to document</h1> 
  <div class="upload-container" id="uploadContainer">
    <p id="p1">Drag and drop video file</p>
    <video id="previewThumbnail" autoplay="false">
    </video>
    <div class="file-name" id="fileName">No video chosen</div>
    <div id="thumbnailContainer">
      <img id="thumbnailImage" style="display:none;">
    </div>
      <button class="custom-btn" id="manualUploadBtn">Search video</button>
  <input type="file" id="videoUpload" accept="video/*">
  </div>
 <div class="checkbox-group">
  <label id="checkbox_group" for="checkbox-group">Choose prefered document style:</label>
  <div class="checkbox-container">
-    <input type="checkbox" name ="docFormat" id="docFormat">
+    <input type="checkbox" name ="docFormat" id="docFormat" value="Meeting report">
    <label id="label_format" for="docFormat">Meeting report</label>
  </div>
  <div class="checkbox-container">
-    <input type="checkbox" name="docFormat" id="docFormatSummary">
+    <input type="checkbox" name="docFormat" id="docFormatSummary" value="Summary with timestamps">
    <label id="label_summary" for="docFormatSummary">Summary with timestamps</label>
  </div>
 </div>
-<button class="submit-btn" id="submitButton" onclick="checkBoxes()">Submit</button>
+<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
-<div class="progressbar">
+<div class="progressbar" id="progressbar">
  <div class="progress_fill"></div>
  <span class="progress_text">0%</span>
 </div>
 </div>
 <script src="languages.js"></script>
 <script src="script.js"></script>
 <script src="./renderer.js"></script>
 </body>
@@ -0,0 +1,48 @@
 var languageOptions = {
    "eng":{
        "flagPath": "flags/united-kingdom-flag-png-large.jpg",
        "labelKI": "Select ki:",
        "labelTranscription": "Select transcription:",
        "labelLanguage": "Select language:",
        "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":{
        "flagPath": "flags/germany-flag-png-large.jpg",
        "labelKI": "Waehle KI:",
        "labelTranscription": "Waehle Transkription:",
        "labelLanguage": "Waehle Sprache:",
        "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":{
        "flagPath": "flags/india-flag-png-large.png",
        "labelKI": "की का चयन करें:",
        "labelTranscription": "प्रतिलेखन चुनें:",
        "labelLanguage": "भाषा चुने:",
        "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"
    }
 };
@@ -1,18 +1,27 @@
 const { contextBridge, ipcRenderer, webUtils } = require('electron')
 try {
    contextBridge.exposeInMainWorld("explorer", {
        onFileDrop: (file) => webUtils.getPathForFile(file)
    })
-    contextBridge.exposeInMainWorld("extractor", {
+    contextBridge.exposeInMainWorld("submit", {
-        extract: (file) => ipcRenderer.send("extract", file)
+        submit: (meeting_specifications) => {ipcRenderer.send("file_submit", meeting_specifications)}
    })
    contextBridge.exposeInMainWorld("electronAPI", {
        getFilePath: (file) => {return webUtils.getPathForFile(file)}
    })
    contextBridge.exposeInMainWorld("onStartup", {
        getModuleNames: () => ipcRenderer.invoke('get-module-names')
    })
    ipcRenderer.on("progress", (event, resp) => {
        alert(`Finished step ${resp.curstep} of ${resp.totalsteps}`)
    })
    ipcRenderer.on("error", (event, err) => {alert(err)})
 } catch (error) {
    console.log("Error in preload.js");
 }
@@ -16,16 +16,72 @@ uploadContainer.addEventListener("drop", (e) => {
        e.preventDefault()
        const files = e.dataTransfer.files
        const filePath = window.explorer.onFileDrop(files[0])
-        var holdy = filePath + "";
+        const testEndings = [".mp4", ".mov", ".avi", ".mkv"];
-        if(holdy.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
+        var pathToLower = filePath.toLowerCase();
-            console.log(filePath)
+        if(testEndings.some(e => pathToLower.endsWith(e))){
-
+          document.getElementById("progressbar").style.visibility = "visible";
            const files1 = e.dataTransfer.files;
            handleFiles(files1);
        }else{
          alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
        }
    } catch (error) {
        console.log("Error in renderer.js with the listerner for the drop function");
    } 
 })
 window.addEventListener('load', async (e) => { 
  try {
      console.log("test");
      loadLanguageOptions(); 
      const value = await window.onStartup.getModuleNames();
      loadAiOptions(value.ai_modules);
      loadTranscriptionOptions(value.transcription_modules);
  } catch (error) {
  }
 });
 language_option.addEventListener('change', (e)=>{
    try {
        const select = document.getElementById('language_option');
        changeLanguage(select.value);
    } catch (error) {
    }
 });
 videoUpload.addEventListener("change", () => {
  try {
    activateSubmitBtn(videoUpload.files.length > 0);
  } 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");
    console.log(error);
  }
 });
 //listener for the file explorer search
 manualUploadBtn.addEventListener('click', () => {
  try {
    videoUpload.click();
  } catch (error) {
    console.log("Error in manualBtn EventListener click");
    console.log(error);
  }
 });
@@ -1,90 +1,100 @@
 //listener for the file explorer search
 manualUploadBtn.addEventListener('click', () => {
  try {
    videoUpload.click();
  } catch (error) {
    console.log("Error in manualBtn EventListener click");
  }
 });
 //function to check if one checkbox is at least klicked
 function checkBoxes() {
  try {
    const checkboxes = document.querySelectorAll('input[name="docFormat"]');
    let isChecked = false;
-
+    var checkedCounter = 0;
    checkboxes.forEach(function(checkbox){
      if(checkbox.checked){
        isChecked = true;
        checkedCounter++;
      }
    });
    if (isChecked) {
      //Code to submit the video
-      var pathTest = window.electronAPI.getFilePath(videoUpload.files[0]);
+      var selectedCheckboxes = {};
-      if(pathTest.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
+      checkboxes.forEach(function(checkbox){
-        window.extractor.extract({inputVideoPath: pathTest, outputType:"wav"})
+        if(checkbox.checked){
          selectedCheckboxes[checkbox.nextElementSibling.textContent] = "";
        } 
      });
      const testEndings = [".mp4", ".mov", ".avi", ".mkv"];
      var pathTest = window.electronAPI.getFilePath(videoUpload.files[0]);
      var pathToLower = pathTest.toLowerCase();
      if(testEndings.some(e => pathToLower.endsWith(e))){
        document.getElementById("progressbar").style.visibility = "visible";
        //assembly of the json for the main
        const selectedStyles = [checkedCounter];
        var iter = 0;
        checkboxes.forEach(function(checkbox){
        if(checkbox.checked){
          console.log(checkbox.value);
          selectedStyles[iter] = {iter: checkbox.value};
          iter++;
          } 
        });
        console.log(selectedCheckboxes);
        const outputType = document.getElementById("output_type");
        const transcriptionType = document.getElementById("transkript_type");
        const aiType = document.getElementById("ai_type");
        const sendingPackage = {
          "video": {
            "module":"extraction-video-to-audio",
            "inputVideoPath": pathTest,
            "outputType": outputType.value
          },
          "transcription": {
            "module": transcriptionType.value
          },
          "document": {
            "module":aiType.value,
            "styles": selectedStyles
          }
        };
        window.submit.submit(sendingPackage)
      }else{
        alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
      }
    } else {
      //language only english at the moment
      alert('Please select at least one document type.');
    }
  } catch (error) {
-    console.log(error)
+    console.log("Error in script.js checkBoxes function");
    console.log(error);
  }
 // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
 }
 //language changing feature
 function changeLanguage(language) {
    if (language === 'en') {
        document.getElementById('title').textContent = 'Video to document';
        document.getElementById('h1').textContent = 'Video to document';
        document.getElementById('p1').textContent = 'Drag and drop video file';
        document.getElementById('fileName').textContent = 'No video chosen';
        document.getElementById('manualUploadBtn').textContent = 'Search video';
        document.getElementById('checkbox_group').textContent = 'Choose prefered document style:';
        document.getElementById('label_format').textContent = 'Meeting report';
        document.getElementById('label_summary').textContent = 'Summary with timestamps';
        document.getElementById('submitButton').textContent = 'Submit';
    } else if (language === 'de') {
        document.getElementById('title').textContent = 'Video zu Dokument';
        document.getElementById('h1').textContent = 'Video zu Dokument';
        document.getElementById('p1').textContent = 'Video per Drag & Drop ablegen';
        document.getElementById('fileName').textContent = 'Kein Video ausgewaehlt';
        document.getElementById('manualUploadBtn').textContent = 'Video suchen';
        document.getElementById('checkbox_group').textContent = 'Bevorzugte Dokumentvarianten:';
        document.getElementById('label_format').textContent = 'Meeting Bericht';
        document.getElementById('label_summary').textContent = 'Zusammenfassung mit Zeitstempeln';
        document.getElementById('submitButton').textContent = 'Absenden';
    } else if(language == "in") {
        document.getElementById('title').textContent = 'दस्तावेज़ के लिए वीडियो';
        document.getElementById('h1').textContent = 'दस्तावेज़ के लिए वीडियो';
        document.getElementById('p1').textContent = 'वीडियो फ़ाइल खींचें और छोड़ें';
        document.getElementById('fileName').textContent = 'कोई वीडियो नहीं चुना गया';
        document.getElementById('manualUploadBtn').textContent = 'वीडियो खोजें';
        document.getElementById('checkbox_group').textContent = 'पसंदीदा दस्तावेज़ शैली चुनें:';
        document.getElementById('label_format').textContent = 'बैठक रिपोर्ट';
        document.getElementById('label_summary').textContent = 'टाइमस्टैम्प के साथ सारांश';
        document.getElementById('submitButton').textContent = 'जमा करना';
    }
 }
 //listener for the file explorer search when something got selected
 videoUpload.addEventListener('change', () => {
  try {
-    handleFiles(videoUpload.files);
+    document.getElementById('labelLanguageFlag').src = languageOptions[language].flagPath;
    document.getElementById('labelKI').textContent = languageOptions[language].labelKI;
    document.getElementById('labelTranscription').textContent = languageOptions[language].labelTranscription;
    document.getElementById('labelLanguage').textContent = languageOptions[language].labelLanguage;
    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 in manualBtn EventListener change");
+    console.log("Error in script.js changeLanguage function");
    console.log(error);
  }
-});
+}
 //function to display the file path in the drop down box
 function handleFiles(files) {
@@ -92,12 +102,16 @@ function handleFiles(files) {
    if (files.length > 0) {
      const file = files[0];
      if (file.type.startsWith('video/')) {
        const filePath = window.explorer.onFileDrop(files[0])
        videoUpload.files = files;
        fileName.textContent = `Chosen video: ${file.name}`;
        generateThumbnail(filePath);
        activateSubmitBtn(true);
      }
    }
  } catch (error) {
    console.log("Error in script.js handleFiles function");
    console.log(error);
  }
 }
@@ -110,6 +124,93 @@ function updateProgressBar(bar, value){
    bar.querySelector(".progress_text").textContent = `${value}%`;
  } catch (error) {
    console.log("Error in scripts.js updateProgressBar function");
    console.log(error);
  }
 }
 //function to load ai options to the drop down list
 function loadAiOptions(options){
  try {
    var menu = document.getElementById('ai_type');
    var object_holdy;
    var choice ;
    object_holdy = options
    for(i = 0; i < options.length; i++){
      choice = document.createElement('option');
      choice.textContent = object_holdy[i].displayname;
      choice.value = object_holdy[i].name;
      menu.appendChild(choice);
    }
  } catch (error) {
    console.log("Error in script.js loadAiOptions function");
    console.log(error);
  }
 }
 //function to load transcription options to the drop down list
 function loadTranscriptionOptions(options){
  try {
    var menu = document.getElementById('transkript_type');
    var object_holdy;
    var choice ;
    object_holdy = options
    for(i = 0; i < options.length; i++){
      choice = document.createElement('option');
      choice.textContent = object_holdy[i].displayname;
      choice.value = object_holdy[i].name;
      menu.appendChild(choice);
    }
  } catch (error) {
    console.log("Error in script.js function loadTranscriptionOptions");
    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);
  }
 }
 function activateSubmitBtn(hasFile){
  try {
    submitButton.disabled = !hasFile;
  } catch (error) {
    console.log(error);
  }
 }
 function deaktivateProgressbar(){
  try {
    document.getElementById("progressbar").style.visibility = "hidden";
  } catch (error) {
    console.log(error);
  }
 }
 //Video thumbnail generation
 function generateThumbnail(path){
  const videoElement = document.getElementById("previewThumbnail");
  while (videoElement.firstChild) videoElement.removeChild(videoElement.firstChild);
  videoElement.src = path;
  videoElement.type = "video/mov";
  videoElement.load();
  videoElement.style.maxWidth = 40;
  videoElement.style.maxHeight = 40;
  videoElement.autoplay = false;
 }
@@ -5,7 +5,7 @@ body {
  justify-content: center;
  align-items: center;
  height: 100vh;
-  background-color: #555;
+  background-color: #f2f3f4;
  gap: 15px;
  margin: 0;
 }
@@ -17,9 +17,10 @@ body {
  border-radius: 12px;
  box-shadow: 0 4px 10px rgba(0,0,0,0.1);
  text-align: center;
-  width: 400px;
+  width: 350px;
  height: 200px;
  transition: border 0.3s, background-color 0.3s;
-  border: 2px dashed #ccc;
+  border: 2px dashed #7378c9;
 }
@@ -40,11 +41,35 @@ body {
  margin-top: 10px;
  font-size: 14px;
  color: #333;
  overflow: hidden;
  text-overflow: ellipsis;
  white-space: nowrap;
 }
 #thumbnailContainer {
  width: 100%;
  display: flex;
  justify-content: center;
  margin-bottom: 15px;
 }
 #thumbnailImage {
  width: 200px;
  height: auto;
  border-radius: 10px;
  box-shadow: 0px 4px 10px rgba(0,0,0,0.1);
  object-fit: cover;
 }
 #previewThumbnail {
  width: 150px;
  height: 100px;
  /*border: 1px dashed black;*/
 }
 .custom-btn {
  padding: 10px 20px;
  margin-top: 10px;
  background-color: #007BFF;
  color: white;
  border: none;
@@ -84,6 +109,8 @@ gap: 5px;
 .submit-btn {
  padding: 10px 20px;
  margin-top: 10px;
  margin-bottom: 10px;
  background-color: #007BFF;
  color: white;
  border: none;
@@ -92,17 +119,26 @@ gap: 5px;
  font-size: 14px;
 }
 .submit-btn:disabled {
  opacity: 0.5;
  cursor: not-allowed;
  pointer-events: none;
 }
 .mitte {
-  background-color: #f2f3f4;
+  background-color: #FDFCFA;
  display: flex;
  width: 700px;
  flex-direction: column;
  align-items: center;
  padding: 5% 50px;
  margin-top: 20px;
  gap: 10px;
-  border: 1px;
+  border: 0px;
  border-color: black;
  border-style: solid;
  border-radius: 6px;
  box-shadow: 0px 4px 10px rgba(0,0,0,0.1);
 }
 h1 {
@@ -116,6 +152,7 @@ h1 {
  background: rgb(42, 46, 78);
  border-radius: 5px;
  overflow: hidden;
  visibility: hidden;
 }
 .progress_fill{
@@ -133,15 +170,19 @@ h1 {
  color: white;
 }
-.flagsBtns {
+
 .dropdownMenus {
  display: flex;
  justify-content: flex-end;
  margin-top: 1px;
  gap: 150px;
  padding: 2px 10px 2px 10px;
 }
-.de_Btn, .eng_Btn, .in_Btn {
+#ai_type, #transkript_type, #language_option {
-  padding: 8px 16px;
+  padding: 3px;
-  color: white;
+}
-  border: none;
+
-  border-radius: 8px;
+.labelDiv {
-  cursor: pointer;
+  gap: 200px;
 }
@@ -35,6 +35,8 @@ console.log("-------------------------------------------------------------------
 // --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //
 const rl = readline.createInterface({
@@ -60,7 +62,7 @@ let mainWindow;
 function createWindow() {
    mainWindow = new electron.BrowserWindow({
        width: 800,
-    height: 600,
+        height: 800,
        webPreferences: {
            nodeIntegration: false,
            contextIsolation: true,
@@ -74,6 +76,180 @@ function createWindow() {
 electron.app.whenReady().then(createWindow);
-electron.ipcMain.on("extract", (event, args) => {
+// electron.ipcMain.on("extract", (event, args) => {
-    mapFunctions.get("extraction-video-to-audio").function(args)
+//     mapFunctions.get("extraction-video-to-audio").function(args)
 // })
 // setTimeout(() => {
 //     mainWindow.webContents.send("fuck", "worked uwu")
 // }, 5000);
 electron.ipcMain.handle('get-module-names', async () => {
    let module_array = {
        "ai_modules":[],
        "transcription_modules":[]
    }
    mapFunctions.forEach(e => {
        switch(e.type){
            case "llm":
                module_array.ai_modules.push({"name": e.name, "displayname": e.displayname})
                break;
            case "transcription":
                module_array.transcription_modules.push({"name": e.name, "displayname": e.displayname})
                break;
        }
    })
    // console.log(module_array);
    return module_array
 });
 // electron.ipcMain.on("get_modules", async (event, args) => {
 //     let module_array = {
 //         "ai_modules":[],
 //         "transcription_modules":[]
 //     }
 //     mapFunctions.forEach(e => {
 //         switch(e.type){
 //             case "llm":
 //                 module_array.ai_modules.push({"name": e.name, "displayname": e.displayname})
 //                 break;
 //             case "transcription":
 //                 module_array.transcription_modules.push({"name": e.name, "displayname": e.displayname})
 //                 break;
 //         }
 //     })
 //     console.log(module_array);
 //     mainWindow.webContents.send("modules", module_array)
 // })
 electron.ipcMain.on("file_submit", async (event, args) => {
    try {
        let curstep = 0
        let totalsteps = 3 + args.document.styles.length
        if(args.document.styles.length == 0)
            throw new Error("At least one Document Style needed");
        console.log(args);
        let audiopath = ""
        let transcriptpath = ""
        console.log("\n\n Running the Video to Audio Extractor");
        // This code handles the Video to Audio extraction module call
        await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: mapFunctions.get(args.transcription.module).audioformat}).then(resp => {
            console.log(resp);
            audiopath = resp
            curstep++
            mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
        }).catch(err => {
            mainWindow.webContents.send("error", err)
            return
        })
        console.log("\n\n Running the Audio to Transcription module");
        // TODO implement transcription module
        // This code handles the Audio to Text transcription module call
        await mapFunctions.get("module-handler").function(args.transcription.module, audiopath).then(resp => {
            console.log(resp);
            transcriptpath = resp
            curstep++
            mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
        }).catch(err => {
            mainWindow.webContents.send("error", err)
            return
        })
        console.log("\n\n Running the Transcription Summarizer module");
        // This code summarises the transcript, so that it can be used by an llm
        // await mapFunctions.get("summarize-transcription").function('A:\\programing\\@projects\\video2document\\storage\\transcripts\\IMG_2978.json').then(resp => {
        await mapFunctions.get("summarize-transcription2").function(transcriptpath).then(resp => {
            console.log(resp);
            transcriptpath = resp
            curstep++
            mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
        }).catch(err => {
            mainWindow.webContents.send("error", err)
            return
        })
        console.log("\n\n Running the LLM module");
        // TODO implement documentation module
        // This code handles the Text to Document processing module call
        for (let i = 0; i < args.document.styles.length; i++) {
            console.log(`\n\n Running the LLM for Document Style ${i+1}`);
            await mapFunctions.get("module-handler").function(args.document.module, {inputTranscriptPath: transcriptpath, documentTypePath: "./storage/documentType/standard_meeting_report.txt", language: "en"}).then(resp => {
                console.log(resp);
                transcriptpath = resp
                curstep++
                mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
            }).catch(err => {
                mainWindow.webContents.send("error", err)
                return
            })
        }
        // TODO actually implement this functionality
        // Module to get the first few lines for each speaker to send to the frontend
 //         await mapFunctions.get("speaker-getter-idfk").function(transcriptpath).then(resp => {
 //             console.log(resp);
 //             transcriptpath = resp
 //             curstep++
 //             mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
 // // {
 // // speakerA: {source: "Pfad zur Audio File"},
 // // speakerB:.....
 // // }
            mainWindow.webContents.send("speakers", {speakerA:"pfad1", speakerB:"pfad2"})
 //         }).catch(err => {
 //             mainWindow.webContents.send("error", err)
 //             return
 //         })
    } catch (error) {
        console.log(error);
    }
 })
 let q =
 {
    video: {
        module: "String", // The name of the module, idk if we ever implement other extraction modules, the default one is extraction-video-to-audio
        inputVideoPath: "String", // See script.js on line 27 for an example of what this should look like
        outputType: "String" // The file format to be used for the audio output file, such as wav, mp3, flac and so on
    },
    transcription:{
        module: "String" // The module name of the transcription model you want to use
    },
    document:{
        module: "String", // The module name of the AI model you want to use to create the document
        styles: [ // An array of all the document styles/prompts you want to have the document be processed with
            {
                prompt: "String",
            }
        ]
    }
 }
 let q1 = {
    "ai_modules":    [
        {name:"abc", displayname:"ABC"},
        {name:"qeg", displayname:"aqghegahu"}
    ],
    "transcription_modules":    [
        {name:"abc", displayname:"ABC"},
        {name:"qeg", displayname:"aqghegahu"}
    ]
 }
@@ -1,10 +1,16 @@
 {
  "dependencies": {
-    "cli-progress": "^3.12.0",
+    "@google/genai": "^1.30.0",
    "@types/axios": "^0.9.36",
    "axios": "^1.13.2",
    "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",
    "html-to-docx": "^1.8.0",
    "mocha": "^11.7.5",
    "puppeteer": "^24.33.0"
  },
  "devDependencies": {
    "@types/cli-progress": "^3.11.6",
@@ -23,7 +29,7 @@
  },
  "scripts": {
    "start": "electron main.js",
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "test": "mocha ./test/unit/test.js"
  },
  "repository": {
    "type": "git",
@@ -1,3 +0,0 @@
 fastapi
 uvicorn
 pytest
@@ -6,13 +6,20 @@ platform        = process.platform
 mainDir         = __dirname
 fs              = require("fs")
 readline        = require("readline")
 puppeteer       = require("puppeteer")
 htmltodocx    = require("html-to-docx")
 config          = require("./config/config")
 ffmpegPath = require('ffmpeg-static');
 ffmpeg = require('fluent-ffmpeg');
 path = require('path');
-cliProgress = require('cli-progress');
+// cliProgress = require('cli-progress');
 // { app, BrowserWindow, ipcMain, dialog } = require('electron');
 electron = require('electron');
 axios = require("axios")
 console.log(require('dotenv').config({path: __dirname + '/.env'}));
@@ -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);
  }
 })();
@@ -0,0 +1,47 @@
 const fs = require('fs');
 const path = require('path');
 //node show-models.js, remember to set SAIA_API_KEY in your environment before running the script
 const SAIA_API_KEY = process.env.SAIA_API_KEY;
 const SAIA_MODELS_URL = "https://chat-ai.academiccloud.de/v1/models";
 // Script to list available models
 (async () => {
    if (!SAIA_API_KEY) {
        console.error("ERROR: SAIA_API_KEY environment variable is not set!");
        process.exit(1);
    }
    console.log("Fetching available models from SAIA...\n");
    try {
        const response = await fetch(SAIA_MODELS_URL, {
            method: "GET",
            headers: {
                "Authorization": `Bearer ${SAIA_API_KEY}`,
                "Accept": "application/json"
            }
        });
        if (!response.ok) {
            const text = await response.text();
            throw new Error(`SAIA API error (${response.status}): ${text}`);
        }
        const data = await response.json();
        console.log("Available models:");
        console.log(JSON.stringify(data, null, 2));
        if (data.data && Array.isArray(data.data)) {
            console.log("\n\nModel IDs:");
            data.data.forEach(model => {
                console.log(`- ${model.id}`);
            });
        }
    } catch (error) {
        console.error("Error fetching models:", error);
    }
 })();
@@ -1,18 +0,0 @@
 import { whisperLocal } from "../services/modules/transcription/local/whisperLocal.ts";
 const audioPath = process.argv[2];
 if (!audioPath) {
  console.error("Please provide an audio file path as argument.");
  process.exit(1);
 }
 const whisper = new whisperLocal();
 (async () => {
  try {
    const text = await whisper.transcribe(audioPath);
    console.log(text);
  } catch (err) {
    console.error("Transcription failed:", err);
  }
 })();
@@ -0,0 +1,194 @@
 const fs = require('fs');
 const path = require('path');
 const puppeteer = require('puppeteer');
 const htmlToDocx = require('html-to-docx');
 const { execSync } = require('child_process');
 const os = require('os');
 const outputDir = path.join(__dirname, "../../../storage/documents");
 if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
 }
 async function showSaveDialog(defaultName, format) {
    const platform = os.platform();
    if (platform === 'darwin') {
        // macOS
        const applescript = `
            set defaultName to "${defaultName}.${format}"
            set theFile to choose file name with prompt "Dokument speichern als:" default name defaultName
            POSIX path of theFile
        `;
        try {
            const result = execSync(`osascript -e '${applescript}'`, { encoding: 'utf8' });
            return result.trim();
        } catch (err) {
            if (err.status === 1) return null; // User canceled
            throw err;
        }
    } else if (platform === 'win32') {
        // Windows
        const powershell = `
            Add-Type -AssemblyName System.Windows.Forms
            $dialog = New-Object System.Windows.Forms.SaveFileDialog
            $dialog.FileName = "${defaultName}.${format}"
            $dialog.Filter = "${format.toUpperCase()} Dateien (*.${format})|*.${format}|Alle Dateien (*.*)|*.*"
            $dialog.Title = "Dokument speichern als"
            $result = $dialog.ShowDialog()
            if ($result -eq 'OK') { $dialog.FileName }
        `;
        try {
            const result = execSync(`powershell -Command "${powershell.replace(/\n/g, '; ')}"`, { 
                encoding: 'utf8' 
            });
            return result.trim() || null;
        } catch (err) {
            throw err;
        }
    } else {
        // Linux - zenity oder kdialog
        try {
            const result = execSync(
                `zenity --file-selection --save --confirm-overwrite --filename="${defaultName}.${format}"`, 
                { encoding: 'utf8' }
            );
            return result.trim();
        } catch (err) {
            try {
                const result = execSync(
                    `kdialog --getsavefilename . "${defaultName}.${format}"`, 
                    { encoding: 'utf8' }
                );
                return result.trim();
            } catch (err2) {
                // Fallback
                return path.join(os.homedir(), 'Downloads', `${defaultName}.${format}`);
            }
        }
    }
 }
 const module_exports = {
    name: "htmlDocumentConverter",
    type: "converter",
    displayname: "HTML Document Converter",
    description: "Converts LLM-generated HTML to PDF, DOCX, TXT, or HTML",
    /**
     * Main conversion function
     * @param {Object} options
     * @param {string} options.inputPath - Path to the HTML input
     * @param {string} options.format - 'pdf' | 'docx' | 'html' | 'txt'
     * @param {string} [options.outputName] - Optional output filename (without extension)
     * @param {boolean} [options.showDialog] - Show save dialog (default: false in module mode, true in CLI mode)
     */
    async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) {
        if (!fs.existsSync(inputPath)) {
            throw new Error(`Input file not found: ${inputPath}`);
        }
        const ext = path.extname(inputPath).toLowerCase();
        const baseName = outputName || path.basename(inputPath, ext);
        let outputFile;
        if (showDialog) {
            // Zeige nativen Dialog
            outputFile = await showSaveDialog(baseName, format);
            if (!outputFile) {
                console.log('Speichervorgang abgebrochen.');
                return null;
            }
        } else {
            // Nutze Standard-Ausgabeverzeichnis
            outputFile = path.join(outputDir, `${baseName}.${format.toLowerCase()}`);
        }
        let htmlContent = fs.readFileSync(inputPath, 'utf8');
        // Remove <think> tags if present
        htmlContent = htmlContent.replace(/<think>[\s\S]*?<\/think>/gi, '');
        switch (format.toLowerCase()) {
            case 'html':
                fs.writeFileSync(outputFile, htmlContent, 'utf8');
                break;
            case 'pdf':
                await this.htmlToPDF(htmlContent, outputFile);
                break;
            case 'docx':
                await this.htmlToDOCX(htmlContent, outputFile);
                break;
            case 'txt':
                fs.writeFileSync(outputFile, this.htmlToTXT(htmlContent), 'utf8');
                break;
            default:
                throw new Error(`Unsupported format: ${format}`);
        }
        console.log(`Erfolgreich gespeichert: ${outputFile}`);
        return outputFile;
    },
    // HTML → PDF
    async htmlToPDF(html, outputPath) {
        const browser = await puppeteer.launch({ 
            headless: true,
            args: ['--no-sandbox', '--disable-setuid-sandbox']
        });
        const page = await browser.newPage();
        await page.setContent(html, { waitUntil: 'networkidle0' });
        await page.pdf({ 
            path: outputPath, 
            format: 'A4', 
            printBackground: true,
            margin: { top: '20mm', right: '20mm', bottom: '20mm', left: '20mm' }
        });
        await browser.close();
    },
    // HTML → DOCX
    async htmlToDOCX(html, outputPath) {
        const buffer = await htmlToDocx(html);
        fs.writeFileSync(outputPath, buffer);
    },
    // HTML → TXT (rudimentär)
    htmlToTXT(html) {
        return html.replace(/<[^>]*>/g, '').replace(/\s+\n/g, '\n').trim();
    }
 };
 module.exports = module_exports;
 // CLI usage mit Dialog
 if (require.main === module) {
    (async () => {
        const args = process.argv.slice(2);
        if (args.length < 1) {
            console.log('Usage: node htmlDocumentConverter.js <input.html> [format]');
            console.log('Formats: pdf (default), docx, html, txt');
            console.log('');
            console.log('Ein nativer "Speichern unter" Dialog wird automatisch geöffnet.');
            process.exit(1);
        }
        const inputPath = args[0];
        const format = args[1] || 'pdf';
        try {
            await module_exports.convert({ 
                inputPath, 
                format, 
                showDialog: true  
            });
        } catch (err) {
            console.error('Konvertierung fehlgeschlagen:', err.message);
            process.exit(1);
        }
    })();
 }
@@ -1,8 +0,0 @@
 module.exports = {
    name:"chatgpt", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
    type:"document", // value used to differentiate each module to order them in the UI
    displayname:"ChatGPT", // The displayname used within the UI
    async function(parameter){
        // TODO add code to actually send the transcript to ChatGPT and get a response back
    }
 }
@@ -1,4 +1,3 @@
 // Ensure ffmpeg binary is available
 if (!ffmpegPath) {
    throw new Error('FFmpeg binary not found!');
@@ -25,18 +24,12 @@ module.exports = {
            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]}`) {
+            return new Promise((resolve, reject) => {
-                this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
+                this.extractAudioFromVideo(parameter.inputVideoPath, parameter.outputType)
-                    .then(() => console.log('Audio extraction successful.'))
+                    .then((resp) => resolve(resp))
-                    .catch((err) => console.error(err));
+                    .catch((err) => {reject(err)});
-            // }
+            })
        } catch (error) {
            console.log(parameter.outputType);
@@ -53,7 +46,7 @@ module.exports = {
     * - Shows CLI progress bar
     * - Handles errors gracefully (without errors)
     */
-    extractAudioFromVideo: async function (videoFilePath, progressBar, outputType){
+    extractAudioFromVideo: async function (videoFilePath, outputType){
        let inputVideoName = path.basename(videoFilePath, path.extname(videoFilePath));
        let outputAudioPath = path.join(outputDir, `${inputVideoName}.${outputType}`);
@@ -64,30 +57,18 @@ module.exports = {
                // .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' });
+                    resolve(outputAudioPath);
                    progressBar.stop();
                    console.log(`Extraction completed: ${outputAudioPath}`);
                    resolve();
                })
                .on('error', (err) => {
-                    progressBar.stop();
+                    // console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
                    console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
                    reject(err);
                })
                .save(outputAudioPath);
            } catch (error) {
-                console.log();
+                // console.log(error);
            }
        });
    }
 }
@@ -0,0 +1,154 @@
 // Prepare output directory (always storage/transcriptionSummaries under project root)
 const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
 if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
 }
 //Speaker, ALL-Sentences, Start, End
 module.exports = {
    name: "summarize-transcription", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
    type: "summarizer", // value used to differentiate each module to order them in the UI
    displayname: "Summarizer",  // The displayname used within the UI
    async function(args) {
        return new Promise(async (resolve, reject) => {
            let inputJson = args.json;
            //JSON Path
            if (args.jsonPath) {
                try {
                    const raw = fs.readFileSync(args.jsonPath, "utf-8");
                    inputJson = JSON.parse(raw);
                } catch (e) {
                    // console.error("Failed to load JSON from file:", e);
                    reject(e)
                    return
                }
            }
            // JSON parsen
            if (typeof args === "string") {
                try {
                    await new Promise((res, rej) => {
                        fs.readFile(args, 'utf8', function (err, data) {
                            if (err){
                                rej(err)
                                return
                            }
                            inputJson = JSON.parse(data);
                            res()
                        });
                    })
                } catch (e) {
                    // console.log("Invalid JSON in summarize-transcription");
                    // console.log(e)
                    reject(e)
                    return
                }
            }
            const words = inputJson.words;
            if (!Array.isArray(words)) {
                    reject("No words Array found")
                    return
            }
            const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
            const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
            const result = [];
            let currentSentence = "";
            let currentSpeaker = null;
            let startTime = null;
            let endTime = null;
            for (const w of words) {
                if (!currentSpeaker) currentSpeaker = w.speaker;
                if (startTime === null) startTime = w.start;
                endTime = w.end;
                //speaker changing
                if (currentSpeaker !== w.speaker && currentSentence) { 
                    const lastEntry = result[result.length - 1];
                    if (lastEntry && lastEntry.speaker === currentSpeaker) {
                        lastEntry.sentence += " " + currentSentence;
                        lastEntry.end = endTime;
                    } else {
                        result.push({
                            speaker: currentSpeaker,
                            sentence: currentSentence,
                            start: startTime,
                            end: endTime
                        });
                    }
                    currentSentence = "";
                    startTime = w.start;
                }
                currentSpeaker = w.speaker;
                currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
                const lastWord = w.text.trim();
                const lastChar = lastWord.slice(-1);
                const isAbbreviation = ABBREVIATIONS.has(lastWord);
                //sentence ending
                if (ENDINGS.includes(lastChar) && !isAbbreviation) {
                    const lastEntry = result[result.length - 1];
                    if (lastEntry && lastEntry.speaker === currentSpeaker) {
                        lastEntry.sentence += " " + currentSentence;
                        lastEntry.end = endTime;
                    } else {
                        result.push({
                            speaker: currentSpeaker,
                            sentence: currentSentence,
                            start: startTime,
                            end: endTime
                        });
                    }
                    currentSentence = "";
                    startTime = null;
                    endTime = null;
                    currentSpeaker = null;
                }
            }
            // safe last sentence 
            if (currentSentence) {
                const lastEntry = result[result.length - 1];
                if (lastEntry && lastEntry.speaker === currentSpeaker) {
                    lastEntry.sentence += " " + currentSentence;
                    lastEntry.end = endTime;
                } else {
                    result.push({
                        speaker: currentSpeaker,
                        sentence: currentSentence,
                        start: startTime,
                        end: endTime
                    });
                }
            }
            // Output as Text
            const output = result.map(r => 
                `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
            );
            // Output on cosole
            //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
            try {
                const jsonPath = path.join(outputDir, "transcription_result.json");
                fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
                const txtPath = path.join(outputDir, "transcription_result.txt");
                fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
                // console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
                resolve(jsonPath);
            } catch (err) {
                // console.error("Error saving Summary:", err);
                reject(err);
            }
        })
    }
 }
@@ -0,0 +1,149 @@
 // Prepare output directory (always storage/transcriptionSummaries under project root)
 const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
 if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
 }
 function getSessionId(inputPath) {
  try {
    const parsed = new URL(inputPath);
    const base = path.basename(parsed.pathname);
    return base.replace(/\.[^.]+$/, '');
  } catch {
    return path.basename(inputPath, path.extname(inputPath));
  }
 }
 //Speaker, Sentence, Start, End
 module.exports = {
    name: "summarize-transcription2", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
    type: "summarizer", // value used to differentiate each module to order them in the UI
    displayname: "Summarizer",  // The displayname used within the UI
    async function(args) {
        return new Promise(async (resolve, reject) => {
            let inputJson = args.json;
            //JSON Path
            if (args.jsonPath) {
                try {
                    const raw = fs.readFileSync(args.jsonPath, "utf-8");
                    inputJson = JSON.parse(raw);
                } catch (e) {
                    console.error("Failed to load JSON from file:", e);
                    reject("Could not read JSON from file path.")
                    return
                }
            }
            // JSON parsen
            if (typeof args === "string") {
                try {
                    await new Promise((res, rej) => {
                        fs.readFile(args, 'utf8', function (err, data) {
                            if (err){
                                rej(err)
                                return
                            }
                            inputJson = JSON.parse(data);
                            res()
                        });
                    })
                } catch (e) {
                    // console.log("Invalid JSON in summarize-transcription");
                    // console.log(e)
                    reject(e)
                    return
                }
            }
            const words = inputJson.words;
            if (!Array.isArray(words)) {
                reject("No words Array found")
                return;
            }
            const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
            const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
            const result = [];
            let currentSentence = "";
            let currentSpeaker = null;
            let startTime = null;
            let endTime = null;
            for (const w of words) {
                if (!currentSpeaker) currentSpeaker = w.speaker;
                if (startTime === null) startTime = w.start;
                endTime = w.end;
                //speaker changing
                if (currentSpeaker !== w.speaker && currentSentence) {
                    result.push({
                        speaker: currentSpeaker,
                        sentence: currentSentence,
                        start: startTime,
                        end: endTime
                    });
                    currentSentence = "";
                    startTime = w.start;
                }
                currentSpeaker = w.speaker;
                currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
                const lastWord = w.text.trim();
                const lastChar = lastWord.slice(-1);
                const isAbbreviation = ABBREVIATIONS.has(lastWord);
                //sentence ending
                if (ENDINGS.includes(lastChar) && !isAbbreviation) {
                    result.push({
                        speaker: currentSpeaker,
                        sentence: currentSentence,
                        start: startTime,
                        end: endTime
                    });
                    currentSentence = "";
                    startTime = null;
                    endTime = null;
                    currentSpeaker = null;
                }
            }
            // safe last sentence 
            if (currentSentence) {
                result.push({
                    speaker: currentSpeaker,
                    sentence: currentSentence,
                    start: startTime,
                    end: endTime
                });
            }
            // Output as Text
            const output = result.map(r => 
                `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
            );
            // Output on cosole
            //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
            try {
                let filename = getSessionId(args);
                const jsonPath = path.join(outputDir, `${filename}-${new Date().getTime()}.json`);
                fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
                const txtPath = path.join(outputDir, `${filename}-${new Date().getTime()}.txt`);
                fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
                // console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
                resolve(jsonPath);
            } catch (err) {
                // console.error("Error saving Summary:", err);
                reject(err);
            }
        })
    }
 }
@@ -0,0 +1,131 @@
 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 SAIA API key is set in environment variables: export SAIA_API_KEY="your_api_key_here"
 const SAIA_API_KEY = process.env.SAIA_API_KEY; // Ensure SAIA API key is set in environment variables
 const SAIA_URL = "https://chat-ai.academiccloud.de/v1/chat/completions"; //URL for the REST call, used model and action
 const module_exports = {
    name: "llm-saia_openai_gpt",
    type: "llm",
    displayname: "GPT 120B",
    description: "Generates documents using OpenAI GPT OSS 120B via SAIA platform",
    async function(parameter) {
        try {
            console.log("SAIA OpenAI GPT module invoked with parameters:", parameter);
            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 SAIA OpenAI GPT module:", error);
        }
    },
    createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
        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(SAIA_URL, {
                method: "POST",
                headers: {
                    "Authorization": `Bearer ${SAIA_API_KEY}`,
                    "Accept": "application/json",
                    "Content-Type": "application/json"
                },
                body: JSON.stringify({
                    model: "openai-gpt-oss-120b",
                    messages: [
                        { role: "system", content: "You are a helpful assistant that generates HTML documents from transcripts. Output only valid HTML content without any preamble, explanations, or markdown formatting." },
                        { role: "user", content: promptText }
                    ],
                    temperature: 0
                })
            });
            if (!response.ok) { //ok is true when a response was successful
                const text = await response.text();
                throw new Error(`SAIA API error (${response.status}): ${text}`);
            }
            const data = await response.json();
            // Get generated text from response or default to empty string (if null)
            // SAIA uses OpenAI-compatible structure: data.choices[x].message.content
            const output = data.choices?.[0]?.message?.content || "";
            let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file 
            console.log(inputTranscriptName);
            const outPath = path.join(outputDir, `${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);
        } catch (error) {
            console.error("Error generating SAIA content:", 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-openai-gpt.js <transcriptPath> <documentTypePath> [language]");
            console.error("Example: node llm-openai-gpt.js ./transcript.json ./docType.txt de");
            process.exit(1);
        }
        const [transcriptPath, documentTypePath, language] = args;
        // Check if API key is set
        if (!SAIA_API_KEY) {
            console.error("ERROR: SAIA_API_KEY environment variable is not set!");
            console.error("Please set it with: export SAIA_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!");
    })();
 }
@@ -0,0 +1,134 @@
 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"
 const GEMINI_API_KEY = process.env.GOOGLE_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) {
        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}.md`); // 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!");
    })();
 }
@@ -0,0 +1,130 @@
 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 SAIA API key is set in environment variables: export SAIA_API_KEY="your_api_key_here"
 const SAIA_API_KEY = process.env.SAIA_API_KEY;
 const SAIA_URL = "https://chat-ai.academiccloud.de/v1/chat/completions"; // URL for the REST call, used model and action
 const module_exports = {
    name: "qwen3-235b-a22b",
    type: "llm",
    displayname: "QWEN 3 235B",
    description: "Generates documents using QWEN 3 235B via SAIA platform",
    async function(parameter) {
        try {
            console.log("SAIA QWEN 3 235B module invoked with parameters:", parameter);
            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 SAIA QWEN 3 235B module:", error);
        }
    },
    createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
        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(SAIA_URL, {
                method: "POST",
                headers: {
                    "Authorization": `Bearer ${SAIA_API_KEY}`,
                    "Accept": "application/json",
                    "Content-Type": "application/json"
                },
                body: JSON.stringify({
                    model: "qwen3-235b-a22b",  
                    messages: [
                        { role: "system", content: "You are a helpful assistant that generates HTML documents from transcripts. Output only valid HTML content without any preamble, explanations, or markdown formatting." },
                        { role: "user", content: promptText }
                    ],
                    temperature: 0
                })
            });
            if (!response.ok) { // ok is true when a response was successful
                const text = await response.text();
                throw new Error(`SAIA API error (${response.status}): ${text}`);
            }
            const data = await response.json();
            // Get generated text from response or default to empty string (if null)
            // SAIA uses OpenAI-compatible structure: data.choices[x].message.content
            const output = data.choices?.[0]?.message?.content || "";
            let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file
            console.log(inputTranscriptName);
            const outPath = path.join(outputDir, `${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);
        } catch (error) {
            console.error("Error generating SAIA content:", 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 qwen3.js <transcriptPath> <documentTypePath> [language]");
            console.error("Example: node qwen3.js ./transcript.json ./docType.txt de");
            process.exit(1);
        }
        const [transcriptPath, documentTypePath, language] = args;
        // Check if API key is set
        if (!SAIA_API_KEY) {
            console.error("ERROR: SAIA_API_KEY environment variable is not set!");
            console.error("Please set it with: export SAIA_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: ${language || 'en (default)'}`);
        await module_exports.createDocumentFromTranscript(
            transcriptPath,
            documentTypePath,
            language || 'en'
        );
        console.log("Done!");
    })();
 }
@@ -5,7 +5,7 @@ import { fileURLToPath } from "url"; // To handle __dirname in ES modules
 const __filename = fileURLToPath(import.meta.url); // Get current file path
 const __dirname = path.dirname(__filename); // Get current directory path
-const transcriptsDir = path.resolve(__dirname, "../../storage/transcriptions");
+const transcriptsDir = path.resolve(__dirname, "../../../storage/transcriptions");
 export class whisperLocal { // is called by transcribe.ts
@@ -26,7 +26,6 @@ export class whisperLocal { // is called by transcribe.ts
  async transcribe(audioPath: string): Promise<string> { //asyncronous function to transcribe audio
    return new Promise((resolve, reject) => {
        const transcriptsDir = path.resolve(__dirname, "../../../../storage/transcripts"); //storage directory for transcripts
        if (!fs.existsSync(transcriptsDir)) { //if transcripts directory does not exist, create it
            fs.mkdirSync(transcriptsDir, { recursive: true });
@@ -0,0 +1,125 @@
 const API_KEY = process.env.ASSEMBLYAI_API_KEY;
 const BASE_URL = 'https://api.assemblyai.com/v2';
 //---------------------------------------------------Upload audio---------------------------------------------------
 async function uploadAudio(audioPath) {
  const audioData = fs.readFileSync(audioPath);
  const response = await axios.post(`${BASE_URL}/upload`, audioData, {
    headers: {
      authorization: API_KEY,
      'content-type': 'application/octet-stream'
    }
  });
  return response.data.upload_url;
 }
 ////---------------------------------------------------Extract session id---------------------------------------------------
 function getSessionId(inputPath) {
  try {
    const parsed = new URL(inputPath);
    const base = path.basename(parsed.pathname);
    return base.replace(/\.[^.]+$/, '');
  } catch {
    return path.basename(inputPath, path.extname(inputPath));
  }
 }
 //---------------------------------------------------Create transcript---------------------------------------------------
 async function createTranscript(audioUrl) {
  const response = await axios.post(
    `${BASE_URL}/transcript`,
    {
      audio_url: audioUrl,
      speaker_labels: true,
      language_detection: true
    },
    {
      headers: {
        authorization: API_KEY,
        'content-type': 'application/json'
      }
    }
  );
  return response.data.id;
 }
 //---------------------------------------------------Poll transcript---------------------------------------------------
 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;
    if (status === 'error') throw new Error(`Transcription failed: ${response.data.error}`);
    await new Promise(res => setTimeout(res, 3000));
  }
 }
 //---------------------------------------------------Save transcript---------------------------------------------------
 function saveTranscript(transcript, sessionId) {
  const outputDir = path.join(__dirname, '../../../storage/transcripts');
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }
  const outputPath = path.join(outputDir, `${sessionId}.json`);
  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
  // console.log(`Transcript saved: ${outputPath}`);
  return outputPath;
 }
 //---------------------------------------------------Modul---------------------------------------------------
 module.exports = {
  name: 'assembly',
  type: 'transcription',
  displayname: 'AssemblyAI',
  audioformat: "mp3",
  async function(audioFileName) {
    return new Promise(async (resolve, reject) => {
      try {
        // audioFileName ist nur "datei.mp3"
        const audioPath = audioFileName;
        let audioUrl;
        if (/^https?:\/\//i.test(audioFileName)) {
          audioUrl = audioFileName;
        } else {
          if (!fs.existsSync(audioPath)) {
            throw new Error(`Audio file not found: ${audioPath}`);
          }
          audioUrl = await uploadAudio(audioPath);
        }
        const transcriptId = await createTranscript(audioUrl);
        const transcript = await pollTranscript(transcriptId);
        const sessionId = getSessionId(audioFileName);
        resolve(saveTranscript(transcript, sessionId));
      } catch (error) {
        // console.error('Transcription error:', error.message);
        reject(error);
        return
      }
    })
  }
 };
@@ -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
    }
 }
@@ -1,319 +0,0 @@
 {
  "name": "transcription",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "dependencies": {
        "axios": "^1.13.2"
      },
      "devDependencies": {
        "@types/axios": "^0.9.36",
        "@types/node": "^24.10.0"
      }
    },
    "node_modules/@types/axios": {
      "version": "0.9.36",
      "resolved": "https://registry.npmjs.org/@types/axios/-/axios-0.9.36.tgz",
      "integrity": "sha512-NLOpedx9o+rxo/X5ChbdiX6mS1atE4WHmEEIcR9NLenRVa5HoVjAvjafwU3FPTqnZEstpoqCaW7fagqSoTDNeg==",
      "dev": true,
      "license": "MIT"
    },
    "node_modules/@types/node": {
      "version": "24.10.0",
      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.10.0.tgz",
      "integrity": "sha512-qzQZRBqkFsYyaSWXuEHc2WR9c0a0CXwiE5FWUvn7ZM+vdy1uZLfCunD38UzhuB7YN/J11ndbDBcTmOdxJo9Q7A==",
      "dev": true,
      "license": "MIT",
      "dependencies": {
        "undici-types": "~7.16.0"
      }
    },
    "node_modules/asynckit": {
      "version": "0.4.0",
      "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==",
      "license": "MIT"
    },
    "node_modules/axios": {
      "version": "1.13.2",
      "resolved": "https://registry.npmjs.org/axios/-/axios-1.13.2.tgz",
      "integrity": "sha512-VPk9ebNqPcy5lRGuSlKx752IlDatOjT9paPlm8A7yOuW2Fbvp4X3JznJtT4f0GzGLLiWE9W8onz51SqLYwzGaA==",
      "license": "MIT",
      "dependencies": {
        "follow-redirects": "^1.15.6",
        "form-data": "^4.0.4",
        "proxy-from-env": "^1.1.0"
      }
    },
    "node_modules/call-bind-apply-helpers": {
      "version": "1.0.2",
      "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
      "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
      "license": "MIT",
      "dependencies": {
        "es-errors": "^1.3.0",
        "function-bind": "^1.1.2"
      },
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/combined-stream": {
      "version": "1.0.8",
      "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
      "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
      "license": "MIT",
      "dependencies": {
        "delayed-stream": "~1.0.0"
      },
      "engines": {
        "node": ">= 0.8"
      }
    },
    "node_modules/delayed-stream": {
      "version": "1.0.0",
      "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
      "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
      "license": "MIT",
      "engines": {
        "node": ">=0.4.0"
      }
    },
    "node_modules/dunder-proto": {
      "version": "1.0.1",
      "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
      "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
      "license": "MIT",
      "dependencies": {
        "call-bind-apply-helpers": "^1.0.1",
        "es-errors": "^1.3.0",
        "gopd": "^1.2.0"
      },
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/es-define-property": {
      "version": "1.0.1",
      "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
      "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
      "license": "MIT",
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/es-errors": {
      "version": "1.3.0",
      "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
      "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
      "license": "MIT",
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/es-object-atoms": {
      "version": "1.1.1",
      "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
      "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
      "license": "MIT",
      "dependencies": {
        "es-errors": "^1.3.0"
      },
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/es-set-tostringtag": {
      "version": "2.1.0",
      "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
      "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
      "license": "MIT",
      "dependencies": {
        "es-errors": "^1.3.0",
        "get-intrinsic": "^1.2.6",
        "has-tostringtag": "^1.0.2",
        "hasown": "^2.0.2"
      },
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/follow-redirects": {
      "version": "1.15.11",
      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.11.tgz",
      "integrity": "sha512-deG2P0JfjrTxl50XGCDyfI97ZGVCxIpfKYmfyrQ54n5FO/0gfIES8C/Psl6kWVDolizcaaxZJnTS0QSMxvnsBQ==",
      "funding": [
        {
          "type": "individual",
          "url": "https://github.com/sponsors/RubenVerborgh"
        }
      ],
      "license": "MIT",
      "engines": {
        "node": ">=4.0"
      },
      "peerDependenciesMeta": {
        "debug": {
          "optional": true
        }
      }
    },
    "node_modules/form-data": {
      "version": "4.0.4",
      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
      "license": "MIT",
      "dependencies": {
        "asynckit": "^0.4.0",
        "combined-stream": "^1.0.8",
        "es-set-tostringtag": "^2.1.0",
        "hasown": "^2.0.2",
        "mime-types": "^2.1.12"
      },
      "engines": {
        "node": ">= 6"
      }
    },
    "node_modules/function-bind": {
      "version": "1.1.2",
      "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
      "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
      "license": "MIT",
      "funding": {
        "url": "https://github.com/sponsors/ljharb"
      }
    },
    "node_modules/get-intrinsic": {
      "version": "1.3.0",
      "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
      "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
      "license": "MIT",
      "dependencies": {
        "call-bind-apply-helpers": "^1.0.2",
        "es-define-property": "^1.0.1",
        "es-errors": "^1.3.0",
        "es-object-atoms": "^1.1.1",
        "function-bind": "^1.1.2",
        "get-proto": "^1.0.1",
        "gopd": "^1.2.0",
        "has-symbols": "^1.1.0",
        "hasown": "^2.0.2",
        "math-intrinsics": "^1.1.0"
      },
      "engines": {
        "node": ">= 0.4"
      },
      "funding": {
        "url": "https://github.com/sponsors/ljharb"
      }
    },
    "node_modules/get-proto": {
      "version": "1.0.1",
      "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
      "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
      "license": "MIT",
      "dependencies": {
        "dunder-proto": "^1.0.1",
        "es-object-atoms": "^1.0.0"
      },
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/gopd": {
      "version": "1.2.0",
      "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
      "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
      "license": "MIT",
      "engines": {
        "node": ">= 0.4"
      },
      "funding": {
        "url": "https://github.com/sponsors/ljharb"
      }
    },
    "node_modules/has-symbols": {
      "version": "1.1.0",
      "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
      "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
      "license": "MIT",
      "engines": {
        "node": ">= 0.4"
      },
      "funding": {
        "url": "https://github.com/sponsors/ljharb"
      }
    },
    "node_modules/has-tostringtag": {
      "version": "1.0.2",
      "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
      "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
      "license": "MIT",
      "dependencies": {
        "has-symbols": "^1.0.3"
      },
      "engines": {
        "node": ">= 0.4"
      },
      "funding": {
        "url": "https://github.com/sponsors/ljharb"
      }
    },
    "node_modules/hasown": {
      "version": "2.0.2",
      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
      "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
      "license": "MIT",
      "dependencies": {
        "function-bind": "^1.1.2"
      },
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/math-intrinsics": {
      "version": "1.1.0",
      "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
      "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
      "license": "MIT",
      "engines": {
        "node": ">= 0.4"
      }
    },
    "node_modules/mime-db": {
      "version": "1.52.0",
      "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
      "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
      "license": "MIT",
      "engines": {
        "node": ">= 0.6"
      }
    },
    "node_modules/mime-types": {
      "version": "2.1.35",
      "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
      "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
      "license": "MIT",
      "dependencies": {
        "mime-db": "1.52.0"
      },
      "engines": {
        "node": ">= 0.6"
      }
    },
    "node_modules/proxy-from-env": {
      "version": "1.1.0",
      "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
      "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==",
      "license": "MIT"
    },
    "node_modules/undici-types": {
      "version": "7.16.0",
      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.16.0.tgz",
      "integrity": "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw==",
      "dev": true,
      "license": "MIT"
    }
  }
 }
@@ -1,9 +0,0 @@
 {
  "dependencies": {
    "axios": "^1.13.2"
  },
  "devDependencies": {
    "@types/axios": "^0.9.36",
    "@types/node": "^24.10.0"
  }
 }
@@ -1,3 +1,4 @@
 module.exports = {
    name:"Startup_function",
    async function(){
@@ -6,8 +7,18 @@ module.exports = {
        // We are now calling the example function from the example folder
        mapFunctions.get("example").function("Startup")
    //    let transcript = await mapFunctions.get("assembly").function('../../storage/audio/IMG_2978.wav');
    //    let summary = await mapFunctions.get("summarize-transcription").function({jsonPath:'/Users/santa/Proj25/video2document/storage/transcripts/IMG_2978.json'});
        // 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"})
        // mapFunctions.get("ipc-handler").function("extraction-video-to-audio", {inputVideoPath:"./a.mp4", outputType:"flac"})
    }
 }
@@ -0,0 +1,16 @@
 module.exports = {
    name:"module-handler", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
    async function(module,parameter){
        return new Promise(async (resolve, reject) => {
            if(mapFunctions.get(module) == undefined){
                reject("requested modules not found")
                return
            }
            mapFunctions.get(module).function(parameter).then((result) => {
                resolve(result)
            }).catch((err) => {
                reject(err)
            });
        })
    }
 }
@@ -1,6 +1,7 @@
 // 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';
 /**
@@ -0,0 +1,217 @@
 Generate a structured meeting report in HTML using STRUCTURE and STYLE.
 Output ONLY the final .md document — no meta comments, no explanations.
 Follow exactly the STRUCTURE defined below.
 Follow exactly the STYLE rules.
 Use timestamps in HH:MM:SS format.
 If information is missing, use: Unclear:<reason>.
 ==================== STRUCTURE & RULES ====================
 {
  "FORMAT": "HTML",
  "STRUCTURE": {
    "titlepage": [
      "title",
      "date",
      "start",
      "end",
      "duration",
      "location",
      "host",
      "participants"
    ],
    "toc": "[section](#anchor) — HH:MM:SS",
    "section": {
      "h2": "<topic> — HH:MM:SS",
      "summary": "exactly 1 concise sentence",
      "key_points": "maximum 5 bullet points; quotes optional",
      "decisions": "list items formatted as: decision text | owner | due date",
      "actions": "HTML table: id | task | owner | due | status"
    },
    "exec_summary": "exactly 3 short sentences",
    "consolidated": [
      "decisions",
      "actions"
    ],
    "appendix": "optional"
  },
  "STYLE": {
    "tone": "neutral, concise, professional",
    "ts_format": "HH:MM:SS",
    "no_meta": true
  },
  "PROCESS": {
    "timestamps": "use transcript timestamps if present; otherwise estimate minimal",
    "speakers": "use names if available; else Speaker X",
    "long_transcripts": "split → summarize → merge",
    "unclear": "Unclear:<reason>"
  },
  "PROMPT_SNIPPET": "Generate meeting report in HTML using STRUCTURE and STYLE. Output only the report."
 }
 ============================================================
 Insert all generated content into the following HTML TEMPLATE:
 # {{title}}
 **Date:** {{date}}  
 **Start:** {{start}}  
 **End:** {{end}}  
 **Duration:** {{duration}}  
 **Location:** {{location}}  
 **Host:** {{host}}  
 **Participants:** {{participants}}
 ---
 ## Table of Contents
 {{toc}}
 ---
 Generate a structured meeting report in HTML using STRUCTURE and STYLE.
 Output ONLY the final .md document — no meta comments, no explanations.
 Follow exactly the STRUCTURE defined below.
 Follow exactly the STYLE rules.
 Use timestamps in HH:MM:SS format.
 If information is missing, use: UNKLAR:<reason>.
 ==================== STRUCTURE & RULES ====================
 {
  "FORMAT": "HTML",
  "STRUCTURE": {
    "titlepage": [
      "title",
      "date",
      "start",
      "end",
      "duration",
      "location",
      "host",
      "participants"
    ],
    "toc": "[section](#anchor) — HH:MM:SS",
    "section": {
      "h2": "<topic> — HH:MM:SS",
      "summary": "exactly 1 concise sentence",
      "key_points": "maximum 5 bullet points; quotes optional",
      "decisions": "list items formatted as: decision text | owner | due date",
      "actions": "HTML table: id | task | owner | due | status"
    },
    "exec_summary": "exactly 3 short sentences",
    "consolidated": [
      "decisions",
      "actions"
    ],
    "appendix": "optional"
  },
  "STYLE": {
    "tone": "neutral, concise, professional",
    "ts_format": "HH:MM:SS",
    "no_meta": true
  },
  "PROCESS": {
    "timestamps": "use transcript timestamps if present; otherwise estimate minimal",
    "speakers": "use names if available; else Speaker X",
    "long_transcripts": "split → summarize → merge",
    "unclear": "UNKLAR:<reason>"
  },
  "PROMPT_SNIPPET": "Generate meeting report in HTML using STRUCTURE and STYLE. Output only the report."
 }
 ============================================================
 Insert all generated content into the following HTML TEMPLATE:
 # {{title}}
 **Date:** {{date}}  
 **Start:** {{start}}  
 **End:** {{end}}  
 **Duration:** {{duration}}  
 **Location:** {{location}}  
 **Host:** {{host}}  
 **Participants:** {{participants}}
 ---
 ## Table of Contents
 {{toc}}
 ---
 ## Executive Summary
 {{exec_summary}}
 ---
 ## Sections
 {{sections}}
 ---
 ## Consolidated Decisions
 {{consolidated_decisions}}
 ---
 ## Consolidated Actions
 {{consolidated_actions}}
 ---
 ## Appendix
 {{appendix}}
 ============================================================
 Final Requirement:
 Output ONLY the completed HTML meeting report.
 ## Executive Summary
 {{exec_summary}}
 ---
 ## Sections
 {{sections}}
 ---
 ## Consolidated Decisions
 {{consolidated_decisions}}
 ---
 ## Consolidated Actions
 {{consolidated_actions}}
 ---
 ## Appendix
 {{appendix}}
 ============================================================
 Final Requirement:
 Output ONLY the completed HTML meeting report.
@@ -1,5 +1,5 @@
 import 'dotenv/config';
-import assemblyModule from './assembly.ts';
+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';
@@ -0,0 +1,18 @@
 require('dotenv').config();
 const path = require('path');
 const assemblyModule = require('../../services/modules/transcription-remote/assembly.js');
 // Audio-Datei oder URL aus Kommandozeile, Standard: test.wav
 const audioPath = process.argv[2] || './storage/audio/IMG_2978.wav';
 (async () => {
  try {
    const transcript = await assemblyModule.run(audioPath);
    console.log('Transcription succesful');
    console.log('Transcript ID:', transcript?.id);
    console.log('Speaker labels:', transcript?.utterances?.length || 0);
  } catch (error) {
    console.error('Error in Transcription:', error?.message || error);
  }
 })();
@@ -0,0 +1,39 @@
 **Goal:** Generate a structured meeting report (Markdown). **Output ONLY:** final .md. No meta.
 ```json
 {
  "FORMAT": "markdown",
  "STRUCTURE": {
    "titlepage": ["title","date","start","end","duration","location","host","participants"],
    "toc": "[section](#anchor) — HH:MM:SS",
    "section": {
      "h2": "<topic> — HH:MM:SS",
      "summary": "1 sentence",
      "key_points": "<=5 bullets, quotes optional",
      "decisions": "list: text | owner | due",
      "actions": "table: id | task | owner | due | status"
    },
    "exec_summary": "3 short sentences",
    "consolidated": ["decisions", "actions"],
    "appendix": "optional"
  },
  "STYLE": {
    "tone": "neutral, concise",
    "ts_format": "HH:MM:SS",
    "no_meta": true
  },
  "PROCESS": {
    "timestamps": "use if present; else estimate minimal",
    "speakers": "use labels; else Speaker X",
    "long_transcripts": "chunk → summarize → merge",
    "unclear": "UNKLAR:<reason>"
  },
  "JSON_OUTPUT_OPTIONAL": true,
  "PROMPT_SNIPPET": "Generate meeting report in markdown using STRUCTURE and STYLE. Output only the report."
 }
@@ -0,0 +1,7 @@
 const gemini = require("../../../services/modules/llm-gemini/gemini.js");
 gemini.function({
    inputTranscriptPath: "./transcript.json",
    documentTypePath: "./documentType.json",
    language: "de"
 });
@@ -0,0 +1,122 @@
 [
  {
    "speaker": "A",
    "sentence": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter DeCarlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Good morning, Professor.",
    "start": 240,
    "end": 26560
  },
  {
    "speaker": "B",
    "sentence": "Good morning.",
    "start": 28060,
    "end": 28620
  },
  {
    "speaker": "A",
    "sentence": "So what is it about the conditions right now that have caused this round of wildfires to affect so many people so far away?",
    "start": 29100,
    "end": 37100
  },
  {
    "speaker": "B",
    "sentence": "Well, there's a couple of things. The season has been pretty dry already, and then the fact that we're getting hit in the US is because there's a couple weather systems that are essentially channeling the smoke from those Canadian wildfires through Pennsylvania into the mid Atlantic and the Northeast and kind of just dropping the smoke there.",
    "start": 39100,
    "end": 55820
  },
  {
    "speaker": "A",
    "sentence": "So what is it in this haze that makes it harmful? And I'm assuming it is harmful.",
    "start": 56590,
    "end": 60670
  },
  {
    "speaker": "B",
    "sentence": "It is, it is. The levels outside right now in Baltimore are considered unhealthy. And most of that is due to what's called particulate matter, which are tiny particles, microscopic, smaller than the width of your hair, that can get into your lungs and impact your respiratory system, your cardiovascular system, and even your neurological, your brain.",
    "start": 62350,
    "end": 82590
  },
  {
    "speaker": "A",
    "sentence": "What makes this particularly harmful? Is it the volume of particulate? Is it something in particular? What is it exactly? Can you just drill down on that a little bit more?",
    "start": 83630,
    "end": 92190
  },
  {
    "speaker": "B",
    "sentence": "Yeah. So the concentration of particulate matter, I was looking at some of the monitors that we have was reaching levels of what are, in science speak, 150 micrograms per meter cubed, which is more than 10 times what the annual average should be in about four times higher than what you're supposed to have on a 24 hour average. And so the concentrations of these particles in the air are just much, much, much higher than we typically see. And exposure to those high levels can lead to a host of health problems.",
    "start": 93550,
    "end": 123350
  },
  {
    "speaker": "A",
    "sentence": "And who is most vulnerable? I noticed that in New York City, for example, they're canceling outdoor activities. And so here it is in the early days of summer and they have to keep all the kids inside. So who tends to be vulnerable in a situation like this?",
    "start": 123430,
    "end": 135990
  },
  {
    "speaker": "B",
    "sentence": "It's the youngest. So children, obviously, whose bodies are still developing, the elderly who are, you know, their bodies are more in decline and they're more susceptible to the health impacts of breathing, the poor air quality. And then people who have pre existing health conditions, people with respiratory conditions or heart conditions, can be triggered by high levels of air pollution.",
    "start": 137610,
    "end": 156650
  },
  {
    "speaker": "A",
    "sentence": "Could this get worse?",
    "start": 157450,
    "end": 158650
  },
  {
    "speaker": "B",
    "sentence": "That's a good question. I mean, I think if in some areas it's much worse than others and it just depends on kind of where the smoke is concentrated. I think New York has some of the higher concentrations right now, but that's going to change as that air moves away from the New York area. But over the course of the next few days, we will see different areas being hit at different times with the highest concentrations.",
    "start": 162170,
    "end": 183420
  },
  {
    "speaker": "A",
    "sentence": "I was going to ask you about.",
    "start": 183740,
    "end": 184660
  },
  {
    "speaker": "B",
    "sentence": "More fires start burning. I don't expect the concentrations to go up too much higher.",
    "start": 184660,
    "end": 189020
  },
  {
    "speaker": "A",
    "sentence": "I was going to ask you how and you started to answer this, but how much longer could this last? Forgive me if I'm asking you to speculate, but what do you think?",
    "start": 189100,
    "end": 196220
  },
  {
    "speaker": "B",
    "sentence": "Well, I think the fires are going to burn for a little bit longer. But the key for us in the US Is the weather system changing. Right now it's the weather systems that are pulling that air into our Mid Atlantic and Northeast region. As those weather systems change and shift, we'll see that smoke going elsewhere and not impact us in this region as much. I think that's going to be the defining factor. I think the next couple days we're going to see a shift in that weather pattern and start to push the smoke away from where we are.",
    "start": 198280,
    "end": 227480
  },
  {
    "speaker": "A",
    "sentence": "And finally, with the impacts of climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences or circumstances?",
    "start": 227930,
    "end": 239850
  },
  {
    "speaker": "B",
    "sentence": "I mean, that is one of the predictions for climate change. Looking into the future, the fire season is starting earlier and lasting longer and we're seeing more frequent fires. So yeah, this is probably something that we'll be seeing more, more frequently. This tends to be much more of an issue in the western U.S. so the eastern U.S. getting hit right now is a little bit new. But yeah, I think with climate change moving forward, this is something that is going to happen more frequently.",
    "start": 241370,
    "end": 267570
  },
  {
    "speaker": "A",
    "sentence": "That's Peter DeCarlo, associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Professor DeCarlo, thanks so much for joining us and sharing this expertise with us.",
    "start": 267970,
    "end": 278210
  },
  {
    "speaker": "B",
    "sentence": "Thank you for having me.",
    "start": 279410,
    "end": 280530
  }
 ]
@@ -0,0 +1,12 @@
 const fs = require('fs');
 const transSummarizer = require("../../services/modules/jsonTools/transcriptionSummarizer.js");
 // JSON-Datei laden
 const inputJson = JSON.parse(fs.readFileSync("./testFile.json", "utf8"));
 // Übergabe an den Summarizer
 transSummarizer.function({
    json: inputJson
 });
@@ -1,8 +0,0 @@
 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
@@ -0,0 +1,170 @@
 // DO NOT TOUCH THIS
 require("../../requires.js")
 mapFunctions = new Map()
 // Loading the Function Map
 var path = `${mainDir}/services/modules`
 var folders = fs.readdirSync(path).filter(function (file) {
    return fs.statSync(path+'/'+file).isDirectory();
 });
 folders.forEach(element => {
    var commandFiles = fs.readdirSync(`${path}/${element}`).filter(file => file.endsWith('.js') && !file.startsWith("index"));
    for (const file of commandFiles) {
        delete require.cache[require.resolve(`${path}/${element}/${file}`)];
        const command = require(`${path}/${element}/${file}`);
        mapFunctions.set(command.name, command);
    }
 });
 // You can touch beyond this point
 let audiopath
 let transcriptPath
 let summarizePath
 let llmpath
 describe("Unit Tests", function() {
    describe('Audio Extraction', function () {
        this.slow(1000)
        this.timeout(3000)
        it('Extract .mp4 to .mp3', function (done) {
            mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: __dirname.replaceAll("\\","/")+"/testvideo.mp4", outputType: "mp3"}).then(resp => {
                audiopath = resp
                // console.log(resp);
                done()
            }).catch(err => {
                throw err;
            })
        })
        it('Extract .mp4 to .flac', function (done) {
            mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: __dirname.replaceAll("\\","/")+"/testvideo.mp4", outputType: "flac"}).then(resp => {
                // console.log(resp);
                done()
            }).catch(err => {
                throw err;
            })
        })
        it('Extracting to a nonexistant format', function (done) {
            mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: __dirname.replaceAll("\\","/")+"/testvideo.mp4", outputType: "qqq"}).then(resp => {
                // console.log(resp);
                done("Didnt crash")
            }).catch(err => {
                done()
            })
        })
        it('Extracting from nonexistant file', function (done) {
            mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: "a", outputType: "mp3"}).then(resp => {
                // console.log(resp);
                done("Didnt crash")
            }).catch(err => {
                done()
            })
        })
        it('Extracting from nonexistant file to nonexistant format', function (done) {
            mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: "a", outputType: "qqq"}).then(resp => {
                // console.log(resp);
                done("Didnt crash")
            }).catch(err => {
                done()
            })
        })
    });
    describe("Audio Transcription", function() {
        this.slow(20000)
        this.timeout(120000)
        it('Assembly', function (done) {
            mapFunctions.get("assembly").function(audiopath).then(resp => {
                // console.log(resp);
                transcriptPath = resp
                done()
            }).catch(err => {
                throw err
            })
        })
        it('Assembly Wrong file', function (done) {
            mapFunctions.get("assembly").function("a").then(resp => {
                // console.log(resp);
                // transcriptPath = resp
                done("Didnt crash")
            }).catch(err => {
                // console.log(err);
                done()
            })
        })
        // TODO add more Transcription Tool tests here
    })
    describe("Transcript Summarizer", function() {
        this.slow(100)
        this.timeout(1000)
        it("Summarizer 1", function (done){
            mapFunctions.get("summarize-transcription").function(transcriptPath).then(resp => {
                done()
            }).catch(err => {
                throw err
            })
        })
        it("Summarizer 1 Wrong File", function (done){
            mapFunctions.get("summarize-transcription").function("a").then(resp => {
                done("Didnt crash")
            }).catch(err => {
                done()
            })
        })
        it("Summarizer 2 (Main)", function (done){
            mapFunctions.get("summarize-transcription2").function(transcriptPath).then(resp => {
                summarizePath = resp
                done()
            }).catch(err => {
                throw err
            })
        })
        it("Summarizer 2 (Main) Wrong File", function (done){
            mapFunctions.get("summarize-transcription2").function("a").then(resp => {
                done("Didnt crash")
            }).catch(err => {
                done()
            })
        })
    })
    describe("Large Language Model", function() {
        this.slow(30000)
        this.timeout(120000)
        // it("ChatGPT", function (done){
        //     mapFunctions.get("chatgpt").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/meetingReport.json", language: "en"}).then(resp => {
        //         done()
        //     }).catch(err => {
        //         throw err
        //     })
        // })
        it("Gemini", function (done){
            mapFunctions.get("llm-gemini").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/meetingReport.json", language: "en"}).then(resp => {
                llmpath = resp
                done()
            }).catch(err => {
                throw err
            })
        })
    })
    after(function() {
        console.log(`\n\n\n${audiopath} \n${transcriptPath} \n${summarizePath} \n${llmpath}`);
    })
 })
Author	SHA1	Message	Date
MikeHughes-BIN	948ddb4310	the old report type was still used	2025-12-15 16:06:18 +01:00
Hughes, Mike	889d455fbe	Merge branch 'fix/add_puppeteer' into 'develop' The requirements needed to include puppeteer and html-to-docs See merge request proj-wise2526-video2document/video2document!44	2025-12-15 15:46:42 +01:00
MikeHughes-BIN	58741f0057	The requirements needed to include puppeteer and html-to-docs	2025-12-15 15:43:03 +01:00
Hughes, Mike	a8c284edd2	Merge branch 'feature/30-backend-export-funktion-des-dokuments-in-verschiedene-datei-formate-s4-05' into 'develop' Feature/30 backend export funktion des dokuments in verschiedene datei formate s4 05 See merge request proj-wise2526-video2document/video2document!43	2025-12-15 15:03:36 +01:00
MikeHughes-BIN	3a5808d97c	Merge branch 'develop' into feature/30-backend-export-funktion-des-dokuments-in-verschiedene-datei-formate-s4-05	2025-12-15 14:41:28 +01:00
Hughes, Mike	4083d5a5cb	Merge branch 'feature/35-backend-llm-chat-gpt-integration-s4-10' into 'develop' Feature/35 backend llm chat gpt integration s4 10 See merge request proj-wise2526-video2document/video2document!42	2025-12-15 14:33:31 +01:00
MikeHughes-BIN	d655925031	merge conflict resolve	2025-12-15 14:30:14 +01:00
MikeHughes-BIN	405a32098c	Remove success and error icons from console log messages for consistency	2025-12-15 14:15:40 +01:00
Hughes, Mike	1683502aa1	Merge branch 'develop' into 'feature/35-backend-llm-chat-gpt-integration-s4-10' # Conflicts: # services/modules/llm-gemini/gemini.js	2025-12-15 14:07:32 +01:00
MikeHughes-BIN	789ecd3a31	Update document processing to use prompts from styles and add structured meeting report template	2025-12-15 14:01:51 +01:00
MikeHughes-BIN	e72d03efbe	Added Pre's Document in the correct Folder	2025-12-15 13:55:40 +01:00
MikeHughes-BIN	ec57411992	Refactor document generation to output HTML format and update system instructions for clarity	2025-12-15 13:53:14 +01:00
MikeHughes-BIN	271fe78b7b	Changed the module to use puppeteer and html-to-docx	2025-12-14 18:14:16 +01:00
MikeHughes-BIN	1e38cc79f4	Extended the Role description	2025-12-14 16:53:35 +01:00
MikeHughes-BIN	746fec05d4	Changed model from llama to quen3 because llama was timing out due to token limit	2025-12-14 16:28:48 +01:00
Spanier, Pit	d647f53790	Merge branch 'feature/implementation-of-ci-s4-09' into 'develop' fixed the pipeline See merge request proj-wise2526-video2document/video2document!38	2025-12-14 16:13:28 +01:00
emily	791dbab739	edited the timeouts for the transcription and LLM tests	2025-12-13 23:04:31 +01:00
emily	c497fa9532	fixed a mistake i made in the pipeline	2025-12-13 23:02:29 +01:00
emily	3ce632bf8d	Optimised the pipeline Replaced the test video with a lower size version in an attempt at keeping this shitty gitlab.rlp provided action running from crashing constantly	2025-12-13 18:46:02 +01:00
Hughes, Mike	5ea8ec6a1a	Merge branch 'feature/implementation-of-ci-s4-09' into 'develop' implemented first CI pipeline version with a test test that only checks if 1... See merge request proj-wise2526-video2document/video2document!34	2025-12-13 14:13:06 +01:00
MikeHughes-BIN	7cd334645f	Added a module that safes the file in a requested format.	2025-12-11 14:22:04 +01:00
Spanier, Pit	15e2e35bda	Merge branch 'feature/35-backend-llm-chat-gpt-integration-s4-10' into 'develop' Feature/35 backend llm chat gpt integration s4 10 See merge request proj-wise2526-video2document/video2document!35	2025-12-11 13:30:14 +01:00
MikeHughes-BIN	53508b175a	changed Display name	2025-12-11 13:27:00 +01:00
MikeHughes-BIN	3dd8485140	audit	2025-12-11 13:23:22 +01:00
MikeHughes-BIN	68c1f0ed9f	removed google from requires	2025-12-11 13:20:54 +01:00
MikeHughes-BIN	2b597add6c	fixed a unicode bug	2025-12-11 13:03:04 +01:00
MikeHughes-BIN	3af038d195	Multiple AI models implemented - chatgpt, llama	2025-12-11 12:41:11 +01:00
MikeHughes-BIN	b546c96238	Refactor code structure for improved readability and maintainability	2025-12-11 12:08:07 +01:00
emily	6512b50d83	removal of an unneeded file	2025-12-10 22:46:25 +01:00
emily	faee605f12	Initial version of the working CI pipeline Added mocha based unit tests for each module Did a bit of cleanup in the modules to remove debug console.log calls Removed the Progress bar in the extractor and the library requirement Promisified the gemini module to make sure it returns the path as a promise instead of just on the cli Fixed gitignore so that it now only ignores the content int the storage directories, and not the whole directories Added neetingReport.json for the LLMs to use	2025-12-09 22:07:43 +01:00
emily	037d29e656	added gitkeep to the storage folders, and edited the gitignore to be more precise for our use case	2025-12-09 20:53:16 +01:00
emily	8c201db539	implemented first CI pipeline version with a test test that only checks if 1 is 1, needs implementation of actual tests	2025-12-09 17:56:59 +01:00
Spanier, Pit	882b49a489	Merge branch 'feature/audio-format-on-transcription-tool-selection-s4-08' into 'develop' removed the need to send the transcription module defined audio output format... See merge request proj-wise2526-video2document/video2document!33	2025-12-09 14:31:25 +01:00
Spanier, Pit	25d11d74a3	Merge branch 'fix/main-path-to-document-for-ai' into 'develop' Currently we only have the standard meeting document and the config right now... See merge request proj-wise2526-video2document/video2document!32	2025-12-09 14:12:14 +01:00
MikeHughes-BIN	0d3535128d	Currently we only have the standard meeting document and the config right now prevents the programm from running. Can be adapted later	2025-12-06 16:43:32 +01:00
emily	e661aefbe8	added json to send to frontend for the speaker naming functionality	2025-12-05 17:09:45 +01:00
emily	ed94928953	removed the need to send the transcription module defined audio output format to the frontend, and handle it on the backend instead	2025-12-05 16:45:39 +01:00
emily	8adf470f18	removed a debug console output	2025-12-05 15:58:45 +01:00
emily	f858f2edbb	added functionality for transcription tool to tell the frontend what audio format to use	2025-12-05 15:58:17 +01:00
MikeHughes-BIN	425e24853e	Similar to the Gemini LLM we now have a ChatGPT REST call. The API Key is still missing	2025-12-04 10:58:50 +01:00
Spanier, Pit	05c04aaef2	Merge branch 'feature/gemini-ai' into 'develop' REST API & Auto Naming See merge request proj-wise2526-video2document/video2document!31	2025-11-26 21:57:51 +01:00
MikeHughes-BIN	84cc94aa34	REST API & Auto Naming	2025-11-26 21:55:19 +01:00
Spanier, Pit	16f319f89f	Merge branch 'feature/implementing-everything' into 'develop' working on implementing everything See merge request proj-wise2526-video2document/video2document!27	2025-11-24 17:25:37 +01:00
santa	9ab98825a2	made it so that the transcript summary file name is not hardcoded anymore	2025-11-24 17:24:08 +01:00
emily	9a0a349813	Switched to transcription summarizer2 due to a better output format	2025-11-24 17:01:49 +01:00
emily	9dfc05e987	Fixed Transcription Summarizer, and now the whole pipeline works (except for LLM, because we need the keys for that)	2025-11-24 16:51:48 +01:00
santa	a5a60635fc	worked on fixing the code	2025-11-24 16:40:12 +01:00
emily	af13907fdc	added console outputs for debugging	2025-11-24 16:14:26 +01:00
emily	812bca8cfb	working on implementing everything Currently getting stuck on the assembly module as assembly ai for some fucking reason blocks me from making any requests This includes making a new user account	2025-11-24 15:35:32 +01:00
emily	34d644d7d7	Merge commit '2f5efee9c7f81cadc22f033f9ba20bb5cbc2d66e' into develop	2025-11-24 14:41:10 +01:00
Spanier, Pit	e73a2a8203	Merge branch 'feature/modular-ipc-system-implementation' into 'develop' Implemented first version of the json object that should be send back to the... See merge request proj-wise2526-video2document/video2document!26	2025-11-24 14:31:32 +01:00
santa	2f5efee9c7	Summarizer und weiters angepasst	2025-11-24 14:27:49 +01:00
santa	465fe8bd41	Summarizer angepasst	2025-11-24 14:25:29 +01:00
emily	78e5cf0503	Merge commit '718664523cb982791ec596e62b6536baca692e80' into feature/modular-ipc-system-implementation	2025-11-24 14:20:34 +01:00
eric.minning	718664523c	Fix, so the transcript module names get loaded in the right drop down menu	2025-11-24 14:19:57 +01:00
emily	eb42a1f377	fixed small error	2025-11-24 14:16:10 +01:00
emily	0e7b42cb4a	Merge commit '90825436520562cc7638f885b70286f765d9f20a' into feature/modular-ipc-system-implementation	2025-11-24 14:15:23 +01:00
emily	31ddddab6a	replaced get modules ipc event handler with a two way handler	2025-11-24 14:14:16 +01:00
eric.minning	9082543652	version 2 of trying to get the module names	2025-11-24 14:13:09 +01:00
emily	b9657e1c95	fixed another typo in the file submission object	2025-11-24 13:10:07 +01:00
emily	baeb9efd2b	fixed file submit code and incorrect property naming in file submission object	2025-11-24 13:04:41 +01:00
emily	8c4d213ed0	Merge commit '6531f5f51c125b9cef761b457ab09f494c77a7e7' into feature/modular-ipc-system-implementation	2025-11-24 12:56:21 +01:00
emily	474e587ff2	Added functionality to group modules for frontend	2025-11-24 12:53:05 +01:00
eric.minning	6531f5f51c	Implemented the interaction between the gui and main so that the ai/transcript names get loaded inside the dropdowns	2025-11-24 12:52:49 +01:00
emily	05449ad8f2	removed an empty line	2025-11-24 12:24:33 +01:00
emily	8046fe53d1	Merge commit 'b4f2ed561dbf2ae87d7816e8aa5b708ed70fb596' into feature/modular-ipc-system-implementation	2025-11-24 12:20:06 +01:00
emily	c2f22b3525	merged Mikes code for the google gemini module included the requires libraries in the package.json implemented the library into requires.js cleaned up ffmpeg from the events	2025-11-24 12:12:46 +01:00
emily	6257ad05a8	Merge commit '4ade9575f33fd353522a07abe2f60e2d1be6feb4' into feature/modular-ipc-system-implementation	2025-11-24 12:08:35 +01:00
emily	bf7438b753	cleaned up ffmpegextractor.js	2025-11-24 12:07:54 +01:00
emily	868945fb92	Merge commit '925eb33eab45c084e9386ada66d9cb14b966e312' into feature/modular-ipc-system-implementation	2025-11-24 12:06:58 +01:00
Hughes, Mike	0f689e2846	Merge branch 'feature/26-llm-schnittstelle-implementieren-s3-07' into 'develop' Feature/26 llm schnittstelle implementieren s3 07 See merge request proj-wise2526-video2document/video2document!24	2025-11-22 14:38:07 +01:00
Verena Schulz	b4f2ed561d	Grey background removed, bigger middle part	2025-11-22 13:48:01 +01:00
MikeHughes-BIN	4ade9575f3	Changes to the test	2025-11-20 16:30:47 +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
santa	b87bfd444d	Test erstellt	2025-11-20 13:27:15 +01:00
santa	97b571b7f9	Einbindung des Summarizer	2025-11-20 11:51:34 +01:00
santa	455147a41b	Summarizer Tool erstellt zur zusammenfassung der vom TranskriptionTool kommenden json	2025-11-20 10:15:11 +01:00
MikeHughes-BIN	a178ccf30f	Added comments to my code to make it more understandable	2025-11-18 19:53:19 +01:00
MikeHughes-BIN	75a454ad60	Moved test files into integration folder as they use multiple different components	2025-11-18 19:38:33 +01:00
MikeHughes-BIN	a1d804f463	Test created and changes to gemini.js file	2025-11-18 19:16:51 +01:00
eric.minning	fde4d584ab	If you change the language, the corresponding flag will now show above the language selection	2025-11-18 16:25:10 +01:00
eric.minning	abd72c9b54	Implemented first version of the json object that should be send back to the main. as well as fixed some bugs	2025-11-18 12:59:08 +01:00
MikeHughes-BIN	8e7e0b5043	Implement Gemini LLM module for document generation (first non tested prototype)	2025-11-17 21:16:50 +01:00
emily	4dc53b9d5f	implemented first version of the modular IPC system	2025-11-17 18:00:04 +01:00
eric.minning	5f14d633e3	Added labels and expanded the language function	2025-11-17 17:34:27 +01:00
Verena Schulz	7b01c4f022	Video icon improvement, changed dropdown alignment	2025-11-17 16:00:53 +01:00
eric.minning	4f57ec25bf	Changed the handleFiles function so it also contains the call for the generateThumbnail function	2025-11-17 15:18:18 +01:00
eric.minning	f8fb71e146	Added Verenas function to have a preview image of the selected video file	2025-11-17 15:02:22 +01:00
eric.minning	ada231cd28	Implemented a deaktivateProgressbar function	2025-11-17 13:15:37 +01:00
eric.minning	1e3d830ae2	Fixed a merg mistake and added try/catch lines	2025-11-17 11:27:17 +01:00
Verena Schulz	ab0e737f33	Submit button disabled without video, bigger middle part and dropzone, button in dropzone	2025-11-16 15:06:47 +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
santa	9441699561	if Pruefung fuer Datei Endung gefixt	2025-11-16 14:46:19 +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
eric.minning	1a681eb2b8	Improved error log and implemented a variable and function for file path storage	2025-11-12 20:14:56 +01:00