REST API & Auto Naming

Merge branch 'feature/implementing-everything' into 'develop'
working on implementing everything See merge request proj-wise2526-video2document/video2document!27
2026-06-15 18:01:52 +02:00 · 2025-11-26 21:55:19 +01:00 · 2025-11-24 17:25:37 +01:00 · 2025-11-24 17:24:08 +01:00 · 2025-11-24 17:01:49 +01:00 · 2025-11-24 16:51:48 +01:00
44 changed files with 14828 additions and 433 deletions
@@ -964,4 +964,8 @@ app.*.symbols
 !/dev/ci/**/Gemfile.lock

 #Storage files
-storage/
+storage/
+
+*.mp4
+*.wav
+*.flac
@@ -3,43 +3,69 @@
 <head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>Video Upload Drag and Drop + Button</title>
+  <title id="title">Video to document</title>
  <link rel="stylesheet" href="style.css">
 </head>
 <body>
 
 <div class="mitte" id="mitte"> 
-  <h1>Video to document</h1> 
-  <div class="upload-container" id="uploadContainer">
-    <p>Drag and drop video file</p>
-    <div class="file-name" id="fileName">No video chosen</div>
+  <div class="labelDiv" id="labelDiv">
+    <label id="labelKI">Select ki:</label>
+    <label id="labelTranscription">Select transcription:</label>
+    <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>

-  <button class="custom-btn" id="manualUploadBtn">Search video</button>
+  <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 for="checkbox-group">Choose prefered document style:</label>
+  <label id="checkbox_group" for="checkbox-group">Choose prefered document style:</label>
  <div class="checkbox-container">
-    <input type="checkbox" id="docFormat">
-    <label for "docFormat">Meeting report</label>
+    <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" id="docFormatCustom">
-    <label for "docFormatCustom">Summary with timestamps</label>
+    <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">Submit Video</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="script.js"></script>
-  <script src="./renderer.js"></script>
+<script src="languages.js"></script>
+<script src="script.js"></script>
+<script src="./renderer.js"></script>
 </body>
 </html>
@@ -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"
+    }
+    
+};
@@ -1,7 +1,27 @@
-
-
 const { contextBridge, ipcRenderer, webUtils } = require('electron')

-contextBridge.exposeInMainWorld("explorer", {
-    onFileDrop: (file) => webUtils.getPathForFile(file)
-})
+try {
+    contextBridge.exposeInMainWorld("explorer", {
+        onFileDrop: (file) => webUtils.getPathForFile(file)
+    })
+    contextBridge.exposeInMainWorld("submit", {
+        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");
+}
@@ -1,22 +1,87 @@

-const dropzone = document.getElementById("uploadContainer");
-
-dropzone.addEventListener("dragover", (e) =>{
-    e.stopPropagation();
-    e.preventDefault();
-});
-
-dropzone.addEventListener("drop", (e) => {
-    e.stopPropagation()
-    e.preventDefault()
-    const files = e.dataTransfer.files
-    const filePath = window.explorer.onFileDrop(files[0])
-    var holdy = filePath + "";
-    if(holdy.endsWith(".mp4")){
-        console.log(filePath)
-
-        const files1 = e.dataTransfer.files;
-        handleFiles(files1);
+uploadContainer.addEventListener("dragover", (e) =>{
+    try {
+        e.stopPropagation();
+        e.preventDefault();
+    } catch (error) {
+        console.log("Error in renderer.js dragover listener function")
    }
    
-})
+});
+
+//listener for when a file get dropped on the drag&drop field
+uploadContainer.addEventListener("drop", (e) => {
+    try {
+        e.stopPropagation()
+        e.preventDefault()
+        const files = e.dataTransfer.files
+        const filePath = window.explorer.onFileDrop(files[0])
+        const testEndings = [".mp4", ".mov", ".avi", ".mkv"];
+        var pathToLower = filePath.toLowerCase();
+        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);
+  }
+  
+});
@@ -1,37 +1,216 @@
-const uploadContainer = document.getElementById('uploadContainer');
-const fileInput = document.getElementById('videoUpload');
-const fileName = document.getElementById('fileName');
-const manualBtn = document.getElementById('manualUploadBtn');
-const videoPreview = document.getElementById('videoPreview');
+
+//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 selectedCheckboxes = {};
+      checkboxes.forEach(function(checkbox){
+        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"].');
+      }


-
-
-
-manualBtn.addEventListener('click', () => {
-  fileInput.click();
-});
-
-
-fileInput.addEventListener('change', () => {
-  handleFiles(fileInput.files);
-});
-
-
-
-
-function handleFiles(files) {
-  if (files.length > 0) {
-    const file = files[0];
-    if (file.type.startsWith('video/')) {
-      fileInput.files = files;
-      fileName.textContent = `Chosen video: ${file.name}`;
+    } else {
+      //language only english at the moment
+      alert('Please select at least one document type.');
    }
-}
+  } catch (error) {
+    console.log("Error in script.js checkBoxes function");
+    console.log(error);
+  }
+  
 }

-function updateProgressBar(bar, value){
-  value = Math.round(value);
-  bar.querySelector(".progress_fill").style.width = `${value}%`;
-  bar.querySelector(".progress_text").textContent = `${value}%`;
-}
+//language changing feature
+function changeLanguage(language) {
+  try {
+    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 script.js changeLanguage function");
+    console.log(error);
+  }
+        
+}
+
+//function to display the file path in the drop down box
+function handleFiles(files) {
+  try {
+    if (files.length > 0) {
+      const file = files[0];
+      if (file.type.startsWith('video/')) {
+        const filePath = window.explorer.onFileDrop(files[0])
+        videoUpload.files = files;
+        fileName.textContent = `Chosen video: ${file.name}`;
+        generateThumbnail(filePath);
+        activateSubmitBtn(true);
+      }
+    }
+  } catch (error) {
+    console.log("Error in script.js handleFiles function");
+    console.log(error);
+  }
+
+}
+
+//function to regulate the progress on the progressbar
+function updateProgressBar(bar, value) {
+  try {
+    value = Math.round(value);
+    bar.querySelector(".progress_fill").style.width = `${value}%`;
+    bar.querySelector(".progress_text").textContent = `${value}%`;
+  } catch (error) {
+    console.log("Error in scripts.js updateProgressBar function");
+    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;
+}
@@ -5,46 +5,71 @@ body {
  justify-content: center;
  align-items: center;
  height: 100vh;
-  background-color: #444;
+  background-color: #f2f3f4;
  gap: 15px;
  margin: 0;
 }
-
-
+ 
+ 
 .upload-container {
  background: white;
  padding: 40px;
  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;
 }
-
-
+ 
+ 
 .upload-container.dragover {
  border-color: #007BFF;
  background-color: #eaf0ff;
 }
-
-
+ 
+ 
 .upload-container p {
  margin: 0 0 15px 0;
  font-size: 16px;
  color: #555;
 }
-
-
+ 
+ 
 .file-name {
  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;
@@ -52,37 +77,40 @@ body {
  cursor: pointer;
  font-size: 14px;
 }
-
-
+ 
+ 
 .custom-btn:hover {
  background-color: #0056b3;
 }
-
+ 
 .submit-btn:hover {
  background-color: #0056b3;
 }
-
+ 
 input[type="file"] {
  display: none;
 }
-
+ 
 .checkbox-container{
 margin-top: 8px;
 display: flex;
 align-items: center;
 gap: 5px;
 }
-
+ 
 .checkbox-group {
  margin-top: 15px;
+  margin-bottom: 15px;
  display: flex;
  flex-direction: column;
  gap: 10px;
  align-items: flex-start;
 }
-
+ 
 .submit-btn {
  padding: 10px 20px;
+  margin-top: 10px;
+  margin-bottom: 10px;
  background-color: #007BFF;
  color: white;
  border: none;
@@ -90,43 +118,71 @@ gap: 5px;
  cursor: pointer;
  font-size: 14px;
 }
-
+ 
+.submit-btn:disabled {
+  opacity: 0.5;
+  cursor: not-allowed;
+  pointer-events: none;
+}
+ 
 .mitte {
-  background-color: #eaf0ff;
+  background-color: #FDFCFA;
  display: flex;
+  width: 700px;
  flex-direction: column;
  align-items: center;
  padding: 5% 50px;
  margin-top: 20px;
  gap: 10px;
-  border: 2px;
+  border: 0px;
  border-color: black;
  border-style: solid;
+  border-radius: 6px;
+  box-shadow: 0px 4px 10px rgba(0,0,0,0.1);
 }
-
+ 
 h1 {
  align-content: center;
 }
-
+ 
 .progressbar{
  position: relative;
  width: 210px;
  height: 30px;
-  background: darkslategray;
+  background: rgb(42, 46, 78);
  border-radius: 5px;
  overflow: hidden;
+  visibility: hidden;
 }
-
+ 
 .progress_fill{
  width: 0%;
  height: 100%;
  background: green;
  transition: all 0.2s;
 }
-
+ 
 .progress_text{
  position: absolute;
  top: 50%;
  right: 5px;
  transform: translateY(-50%);
+  color: white;
+}
+
+
+.dropdownMenus {
+  display: flex;
+  justify-content: flex-end;
+  margin-top: 1px;
+  gap: 150px;
+  padding: 2px 10px 2px 10px;
+}
+
+#ai_type, #transkript_type, #language_option {
+  padding: 3px;
+}
+
+.labelDiv {
+  gap: 200px;
 }
@@ -35,6 +35,8 @@ console.log("-------------------------------------------------------------------



+
+
 // --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //

 const rl = readline.createInterface({
@@ -55,4 +57,179 @@ rl.on("line", data =>{

 // ----------------------------------------------------------- ELECTRON ----------------------------------------------------------- //

-// TODO - Add Electron support to the project
+let mainWindow;
+
+function createWindow() {
+    mainWindow = new electron.BrowserWindow({
+        width: 800,
+        height: 800,
+        webPreferences: {
+            nodeIntegration: false,
+            contextIsolation: true,
+            preload: `${mainDir}/electron/main/preload.js`
+        }
+    });
+
+    mainWindow.loadFile('./electron/main/index.html');
+}
+
+electron.app.whenReady().then(createWindow);
+
+
+// electron.ipcMain.on("extract", (event, args) => {
+//     mapFunctions.get("extraction-video-to-audio").function(args)
+// })
+
+// 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: args.video.outputType}).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++) {
+            await mapFunctions.get("module-handler").function(args.document.module, {prompt: args.document.styles[i].prompt, transcript: 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
+            })
+        }
+
+
+    } 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"}
+    ]
+}
@@ -1,8 +1,11 @@
 {
-  "type": "module",
  "dependencies": {
-    "@google/genai": "^1.29.0",
+    "@google/genai": "^1.30.0",
+    "@types/axios": "^0.9.36",
+    "axios": "^1.13.2",
    "cli-progress": "^3.12.0",
+    "dotenv": "^17.2.3",
+    "electron": "^39.1.1",
    "express": "^5.1.0",
    "ffmpeg-static": "^5.2.0",
    "fluent-ffmpeg": "^2.1.3"
@@ -23,6 +26,7 @@
    "test": "tests"
  },
  "scripts": {
+    "start": "electron main.js",
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "repository": {
@@ -8,3 +8,16 @@ fs              = require("fs")
 readline        = require("readline")
 config          = require("./config/config")

+ffmpegPath = require('ffmpeg-static');
+ffmpeg = require('fluent-ffmpeg');
+path = require('path');
+cliProgress = require('cli-progress');
+
+// { app, BrowserWindow, ipcMain, dialog } = require('electron');
+
+electron = require('electron');
+genai    = require("@google/genai");
+
+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: ${videoPath}`);
-
-    await extractAudioFromVideo(videoPath); // Call the extraction function (ffmpegExtractor.ts in services/modules/extraction)
-
-    console.log("Audio extraction completed successfully.");
-  } catch (err) {
-    console.error("Audio extraction failed:", err);
-    process.exit(1);
-  }
-})();
@@ -1,18 +0,0 @@
-import { whisperLocal } from "../services/modules/transcription/local/whisperLocal.ts";
-
-const audioPath = process.argv[2];
-if (!audioPath) {
-  console.error("Please provide an audio file path as argument.");
-  process.exit(1);
-}
-
-const whisper = new whisperLocal();
-
-(async () => {
-  try {
-    const text = await whisper.transcribe(audioPath);
-    console.log(text);
-  } catch (err) {
-    console.error("Transcription failed:", err);
-  }
-})();
@@ -1,31 +0,0 @@
-import { GoogleGenAI } from "@google/genai";
-import fs from "fs";
-
-// Mike Hughes 10/11/25 - Code inspired from 
-// https://www.geeksforgeeks.org/javascript/javascript-program-to-read-text-file/ for reading text files in JS
-// and from https://ai.google.dev/gemini-api/docs/quickstart?hl=de for using Gemini API
-// Before using, make sure to export the Google Gemini API key as an environment variable:
-//  export GOOGLE_API_KEY="your_api_key_here"
-//  Keys can be obtained from https://aistudio.google.com/app/api-keys
-//  Also make sure to install the package via sudo npm install @google/genai
-
-const ai = new GoogleGenAI({});
-let transcript = "";
-
-async function main() {
-    try {
-        const transcript = await fs.promises.readFile('../../../../storage/transcripts/Kurzgesagt.txt', 'utf-8');
-
-        const response = await ai.models.generateContent({
-            model: "gemini-2.5-flash",
-            contents: `Create a short documentation about the content of the following transcript:\n\n${transcript}`,
-        });
-
-        console.log(response.text);
-        fs.writeFileSync("../../../../storage/documents/Kurzgesagt_documentation.md", response.text, "utf8");
-    } catch (error) {
-    console.error('Error generating content:', error);
-    }
-}
-
-main();
@@ -0,0 +1,91 @@
+// Ensure ffmpeg binary is available
+if (!ffmpegPath) {
+    throw new Error('FFmpeg binary not found!');
+}
+ffmpeg.setFfmpegPath(ffmpegPath);
+
+// Prepare output directory (always storage/audio under project root)
+const outputDir = `${__dirname}/../../../storage/audio`;
+if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true });
+}
+
+
+
+module.exports = {
+    name:"extraction-video-to-audio", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
+    type:"extractor", // value used to differentiate each module to order them in the UI
+    displayname:"Default extractor", // The displayname used within the UI
+    async function(parameter){
+        /*
+        parameter structure:
+        {
+            inputVideoPath: String, // Path to the file
+            outputType: String      // Audio file output format
+        }
+        */
+        let progressBar = new cliProgress.SingleBar({
+            format: 'Processing |{bar}| {percentage}% | {timemark}',
+            barCompleteChar: '\u2588',
+            barIncompleteChar: '\u2591',
+            hideCursor: true
+        });
+        try {
+            return new Promise((resolve, reject) => {
+                this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
+                    .then((resp) => resolve(resp))
+                    .catch((err) => console.error(err));
+            })
+        } catch (error) {
+            console.log(parameter.outputType);
+            
+        }
+
+    },
+    // Derive input and output paths
+    // const inputVideoPath = process.argv[2];
+    // console.log(process.argv);
+
+    /**
+     * Extracts audio from a video using ffmpeg.
+     * - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
+     * - Shows CLI progress bar
+     * - Handles errors gracefully (without errors)
+     */
+    extractAudioFromVideo: async function (videoFilePath, progressBar, outputType){
+        let inputVideoName = path.basename(videoFilePath, path.extname(videoFilePath));
+        let outputAudioPath = path.join(outputDir, `${inputVideoName}.${outputType}`);
+
+        return new Promise((resolve, reject) => {
+            try {
+                ffmpeg(videoFilePath)
+                .outputFormat(outputType)
+                // .audioCodec('pcm_s16le')
+                .audioChannels(1)
+                .audioFrequency(16000)
+                // .setFfmpegPath("./ffmpeg.exe")
+                .on('progress', (progress) => {
+                    if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
+                    if (progress.percent) {
+                    progressBar.update(progress.percent, { timemark: progress.timemark });
+                    }
+                })
+                .on('end', () => {
+                    progressBar.update(100, { timemark: 'done' });
+                    progressBar.stop();
+                    console.log(`Extraction completed: ${outputAudioPath}`);
+                    resolve(outputAudioPath);
+                })
+                .on('error', (err) => {
+                    progressBar.stop();
+                    console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
+                    reject(err);
+                })
+                .save(outputAudioPath);
+
+            } catch (error) {
+                console.log();
+            }
+        });
+    }
+}
@@ -1,90 +0,0 @@
-import ffmpegPath from 'ffmpeg-static';
-import ffmpeg from 'fluent-ffmpeg';
-import path from 'path';
-import fs from 'fs';
-import cliProgress from 'cli-progress';
-import { fileURLToPath } from 'url';
-
-// Base code reference: https://docs.yemreak.com/arsiv/programming/extract-audio-from-video-with-typescript-and-ffmpeg
-// Test command: npx ts-node ./extract.ts /path/to/video.mp4
-
-/**
- * Extracts audio from a video file and saves it as WAV.
- * @param videoFilePath Path to the input video file.
- */
-
-// Ensure ffmpeg binary is available
-if (!ffmpegPath) {
-  throw new Error('FFmpeg binary not found!');
-}
-ffmpeg.setFfmpegPath(ffmpegPath);
-
-// Ensure an input video path is provided via CLI
-if (process.argv.length < 3) {
-  console.error('Usage: ts-node ./extract.ts <input-video-path>');
-  process.exit(1);
-}
-
-// Resolve __dirname equivalent in ESM
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-
-// Prepare output directory (always storage/audio under project root)
-const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'audio');
-if (!fs.existsSync(outputDir)) {
-  fs.mkdirSync(outputDir, { recursive: true });
-}
-
-// Derive input and output paths
-const inputVideoPath = process.argv[2];
-const inputVideoName = path.basename(inputVideoPath, path.extname(inputVideoPath));
-const outputAudioPath = path.join(outputDir, `${inputVideoName}.wav`);
-
-// Initialize CLI progress bar
-const progressBar = new cliProgress.SingleBar({
-  format: 'Processing |{bar}| {percentage}% | {timemark}',
-  barCompleteChar: '\u2588',
-  barIncompleteChar: '\u2591',
-  hideCursor: true
-});
-
-/**
- * Extracts audio from a video using ffmpeg.
- * - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
- * - Shows CLI progress bar
- * - Handles errors gracefully (without errors)
- */
-export function extractAudioFromVideo(videoFilePath: string): Promise<void> {
-  return new Promise((resolve, reject) => {
-    ffmpeg(videoFilePath)
-      .outputFormat('wav')
-      .audioCodec('pcm_s16le')
-      .audioChannels(1)
-      .audioFrequency(16000)
-      .on('progress', (progress) => {
-        if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
-        if (progress.percent) {
-          progressBar.update(progress.percent, { timemark: progress.timemark });
-        }
-      })
-      .on('end', () => {
-        progressBar.update(100, { timemark: 'done' });
-        progressBar.stop();
-        console.log(`Extraction completed: ${outputAudioPath}`);
-        resolve();
-      })
-      .on('error', (err) => {
-        progressBar.stop();
-        console.error(`failed_audio_extraction: ${err.message}`);
-        reject(err);
-      })
-      .save(outputAudioPath);
-  });
-}
-
-// Run extraction if executed directly from CLI
-if (import.meta.url === `file://${process.argv[1]}`) {
-  extractAudioFromVideo(inputVideoPath)
-    .then(() => console.log('Audio extraction successful.'))
-    .catch((err) => console.error(err));
-}
@@ -0,0 +1,148 @@
+
+// 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);
+                    return { error: "Could not read JSON from file path." };
+                }
+            }
+            // JSON parsen
+            if (typeof args === "string") {
+                try {
+                    await new Promise((res) => {
+                        fs.readFile(args, 'utf8', function (err, data) {
+                            if (err) throw err;
+                            inputJson = JSON.parse(data);
+                            res()
+                        });
+                    })
+                } catch (e) {
+                    console.log("Invalid JSON in summarize-transcription");
+                    console.log(e)
+                    return { error: "Invalid JSON" };
+                }
+            }
+
+            const words = inputJson.words;
+            if (!Array.isArray(words)) {
+                return { error: "No words Array found" };
+            }
+
+            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- ${txtPath}`);
+
+                resolve(jsonPath);
+            } catch (err) {
+                console.error("Error saving Summary:", err);
+                reject(err);
+            }
+        })
+    }
+}
@@ -0,0 +1,143 @@
+
+// Prepare output directory (always storage/transcriptionSummaries under project root)
+const outputDir = `${__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);
+                    return { error: "Could not read JSON from file path." };
+                }
+            }
+            // JSON parsen
+                if (typeof args === "string") {
+                    try {
+                        await new Promise((res) => {
+                            fs.readFile(args, 'utf8', function (err, data) {
+                                if (err) throw err;
+                                inputJson = JSON.parse(data);
+                                res()
+                            });
+                        })
+                    } catch (e) {
+                        console.log("Invalid JSON in summarize-transcription");
+                        console.log(e)
+                        return { error: "Invalid JSON" };
+                    }
+                }
+
+            const words = inputJson.words;
+            if (!Array.isArray(words)) {
+                return { error: "No words Array found" };
+            }
+
+            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);
+            }
+        })
+    }
+}
@@ -1,6 +1,6 @@
 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
+    type:"llm", // 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
@@ -0,0 +1,76 @@
+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
+
+module.exports = {
+    name: "llm-gemini",
+    type: "llm",
+    displayname: "Gemini LLM",
+    description: "Generates documents using Google Gemini LLM",
+
+    async function(parameter) {
+        try {
+            console.log("Gemini LLM 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 Gemini LLM 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(`${GEMINI_URL}?key=${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);
+
+        } catch (error) {
+            console.error("Error generating Gemini content:", error);
+        }
+    }
+};
@@ -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 +1,123 @@
+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',
+
+  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: ${audioPath}`);
+          }
+          audioUrl = await uploadAudio(audioPath);
+        }
+
+        const transcriptId = await createTranscript(audioUrl);
+        const transcript = await pollTranscript(transcriptId);
+
+        const sessionId = getSessionId(audioFileName);
+        
+        resolve(saveTranscript(transcript, sessionId));
+
+      } catch (error) {
+        console.error('Transcription error:', error.message);
+        reject(error);
+      }
+    })
+  }
+};
@@ -0,0 +1,133 @@
+import 'dotenv/config';
+import axios from 'axios';
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const API_KEY = process.env.ASSEMBLYAI_API_KEY;
+const BASE_URL = 'https://api.assemblyai.com/v2';
+
+/**
+ * Uploads audio file to AssemblyAI
+ */
+async function uploadAudio(audioPath: string): Promise<string> {
+  const audioData = fs.readFileSync(audioPath);
+  
+  const response = await axios.post<{ upload_url: string }>(`${BASE_URL}/upload`, audioData, {
+    headers: {
+      'authorization': API_KEY,
+      'content-type': 'application/octet-stream'
+    }
+  });
+  
+  return response.data.upload_url;
+}
+
+/**
+ * Extract a session id (basename without extension) from a local path or a URL
+ */
+function getSessionId(inputPath: string): string {
+  try {
+    const parsed = new URL(inputPath);
+    const base = path.basename(parsed.pathname);
+    return base.replace(/\.[^.]+$/, '');
+  } catch (err) {
+    // not a URL, treat as local path
+    return path.basename(inputPath, path.extname(inputPath));
+  }
+}
+
+/**
+ * Creates transcription job with speaker diarization
+ */
+async function createTranscript(audioUrl: string): Promise<string> {
+  const response = await axios.post<{ id: string }>(`${BASE_URL}/transcript`, {
+    audio_url: audioUrl,
+    speaker_labels: true,
+    language_detection: true
+  }, {
+    headers: {
+      'authorization': API_KEY,
+      'content-type': 'application/json'
+    }
+  });
+  
+  return response.data.id;
+}
+
+/**
+ * Polls transcript status until completed
+ */
+async function pollTranscript(transcriptId: string): Promise<any> {
+  while (true) {
+    const response = await axios.get<any>(`${BASE_URL}/transcript/${transcriptId}`, {
+      headers: { 'authorization': API_KEY }
+    });
+    
+    const status = response.data.status;
+    
+    if (status === 'completed') {
+      return response.data;
+    } else if (status === 'error') {
+      throw new Error(`Transcription failed: ${response.data.error}`);
+    }
+    
+    // Wait 3 seconds before next poll
+    await new Promise(resolve => setTimeout(resolve, 3000));
+  }
+}
+
+/**
+ * Saves transcript to storage
+ */
+function saveTranscript(transcript: any, sessionId: string): void {
+  const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');
+  
+  if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true });
+  }
+  
+  const outputPath = path.join(outputDir, `${sessionId}.json`);
+  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
+  
+  console.log(`✅ Transcript saved: ${outputPath}`);
+}
+
+export default {
+  name: "assembly",
+  type: "transcription",
+  displayname: "AssemblyAI",
+  run: async (audioPath: string) => {
+    try {
+      // Determine if audioPath is an external URL or a local file
+      let audioUrl: string;
+      if (/^https?:\/\//i.test(audioPath)) {
+        console.log('🔗 Using external audio URL...');
+        audioUrl = audioPath;
+      } else {
+        console.log('🔄 Uploading local audio...');
+        if (!fs.existsSync(audioPath)) {
+          throw new Error(`Audio file not found: ${audioPath}`);
+        }
+        audioUrl = await uploadAudio(audioPath);
+      }
+      
+      console.log('🔄 Creating transcript job...');
+      const transcriptId = await createTranscript(audioUrl);
+      
+      console.log('⏳ Waiting for transcription...');
+      const transcript = await pollTranscript(transcriptId);
+      
+  const sessionId = getSessionId(audioPath);
+      saveTranscript(transcript, sessionId);
+      
+      return transcript;
+    } catch (error: any) {
+      console.error('❌ Transcription error:', error.message);
+      throw error;
+    }
+  }
+};
@@ -1,8 +0,0 @@
-module.exports = {
-    name:"assembly", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
-    type:"transcription", // value used to differentiate each module to order them in the UI
-    displayname:"Assembly", // The displayname used within the UI
-    async function(parameter){
-        // TODO add code to actually process the audio file
-    }
-}
@@ -5,5 +5,19 @@ 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)
+            });
+        })
+    }
+}
@@ -0,0 +1,53 @@
+// services/pipeline/jobs/transcribeLatest.ts
+import path from 'path';
+import fs from 'fs';
+// @ts-ignore: module has no type declarations or cannot be resolved in current TS config
+import assembly from '../../modules/transcription/assembly';
+
+/**
+ * Finds the most recently modified .wav file in storage/audio/
+ */
+function getLatestWav(): string {
+  const audioDir = path.join(process.cwd(), 'storage', 'audio');
+  const files = fs.readdirSync(audioDir).filter(f => f.toLowerCase().endsWith('.wav'));
+  if (files.length === 0) throw new Error('⚠️ No .wav file found in storage/audio');
+
+  const newest = files
+    .map(f => ({ f, t: fs.statSync(path.join(audioDir, f)).mtimeMs }))
+    .sort((a, b) => b.t - a.t)[0].f;
+
+  return path.join(audioDir, newest);
+}
+
+/**
+ * Full transcription pipeline according to the defined workflow:
+ * 1. Audio Upload → AssemblyAI
+ * 2. Job Creation (transcript_id)
+ * 3. Polling Status (queued → processing → completed)
+ * 4. Download Transcript JSON
+ * 5. Storage: /transcripts/{session_id}.json
+ */
+async function main() {
+  const audioPath = getLatestWav();
+
+  console.log('1️⃣ Audio Upload → AssemblyAI');
+  console.log('   Source:', audioPath);
+
+  console.log('2️⃣ Job Creation (transcript_id)');
+  console.log('3️⃣ Polling Status (queued → processing → completed)');
+  console.log('4️⃣ Download Transcript JSON');
+  console.log('5️⃣ Storage: /transcripts/{session_id}.json');
+
+  // Execute the transcription process via the AssemblyAI module
+  const result = await assembly.run(audioPath);
+
+  console.log('✅ Transcription completed successfully');
+  console.log('🆔 Transcript ID:', result.id);
+  console.log('📁 Transcript file saved under: storage/transcripts/');
+}
+
+// Entry point
+main().catch((err) => {
+  console.error('❌ Transcription pipeline failed:', err.message || err);
+  process.exit(1);
+});
@@ -0,0 +1,14 @@
+import 'dotenv/config';
+import assemblyModule from '../../services/modules/transcription-remote/assembly.ts';
+
+// Test: URL passed as argument OR local file ./storage/audio/test.wav
+const audioPath = process.argv[2] || './storage/audio/test.wav';
+
+assemblyModule.run(audioPath)
+  .then(result => {
+    console.log('✅ Success!');
+    console.log('Transcript ID:', result.id);
+  })
+  .catch(error => {
+    console.error('❌ Error:', error?.message || error);
+  });
@@ -0,0 +1,18 @@
+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
+});
+
+
Author	SHA1	Message	Date
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
MikeHughes-BIN	79e0c48755	Reduced Number of test paths to avoid redundancy	2025-11-13 17:35:40 +01:00
MikeHughes-BIN	9254ddc57f	Changed the Folder Structure for better maintainability	2025-11-13 17:34:22 +01:00
Azeufack Noupeu Willy	c021272ca4	merge: Resolve conflicts with develop	2025-11-13 15:22:33 +01:00
Azeufack Noupeu Willy	e7e97a7f60	feat(S2-02b): Implement AssemblyAI external transcription with speaker diarization - Add assembly.ts module for REST API transcription via AssemblyAI - Implement 5-step pipeline: upload → create job → poll status → download → save - Enable speaker_labels for diarization (Speaker A, B, C...) - Add millisecond-precision timestamps for each utterance - Store JSON transcripts in storage/transcripts/{session_id}.json - Add axios, dotenv dependencies - Add transcribeLatest.ts helper for quick testing User Story: S2-02b - Externe Transkription per REST API	2025-11-13 13:07:18 +01:00
Spanier, Pit	80392874bb	Merge branch 'feature/combination-of-all-the-things' into 'develop' Fixed an error in checkBoxes function and uploadContainer "drop" listener... See merge request proj-wise2526-video2document/video2document!15	2025-11-12 20:56:11 +01:00
emily	94f390f28b	Implemented audio extractor into IPC call, sooooooo, frontend and backend are now officially linked successfully	2025-11-12 20:28:55 +01:00
emily	73f6fa7524	fixed the code so that it now returns the actual path of the file	2025-11-12 20:24:45 +01:00
eric.minning	1a681eb2b8	Improved error log and implemented a variable and function for file path storage	2025-11-12 20:14:56 +01:00
emily	87e3368a9a	fixed code	2025-11-12 20:04:48 +01:00
emily	6d9c94c685	removed some debug console outputs	2025-11-12 20:03:09 +01:00
emily	fbd5368223	Implemented functionality to have the UI be able to communicate with the backend	2025-11-12 20:00:25 +01:00
emily	449255dda1	Merge commit 'c8cbd4e92a034fa108d06337a3e63d24e529432f' into feature/combination-of-all-the-things	2025-11-12 19:55:50 +01:00
eric.minning	c8cbd4e92a	Fixed an error in checkBoxes function and uploadContainer "drop" listener regarding file path testing	2025-11-12 18:52:28 +01:00
eric.minning	0f54edb0aa	Removed the variables at the start of the script.js file	2025-11-12 18:44:27 +01:00
eric.minning	54f1f6c135	Added the check if a path is selected and the call to the transcript functio.	2025-11-12 18:16:27 +01:00
Verena Schulz	a32e7e5744	Checkboxes check (with alert)	2025-11-12 17:39:02 +01:00
Verena Schulz	d9e96316c0	Language selection implemented and UI reworked	2025-11-11 18:31:01 +01:00
eric.minning	da3a8c7d8c	Added try/catch handling and some comments	2025-11-11 16:02:07 +01:00
emily	dfe91bb15a	Merge commit '3a8963b49d96d0746b64244fa17458d4ae68ec45' into feature/combination-of-all-the-things	2025-11-10 17:01:30 +01:00
emily	92043440fe	Combined Frontend with backend, and implemented the extractor function into the module structure	2025-11-10 16:18:57 +01:00
emily	bd8ed1bf81	added mp4, flac and wav files to gitignore	2025-11-10 16:12:59 +01:00