Compare commits

..

2 Commits

Author SHA1 Message Date
Azeufack Noupeu Willy 84ab93ce77 chore: update package-lock.json after axios installation 2025-11-24 19:53:33 +01:00
Azeufack Noupeu Willy 173ed90642 feat(S3-06): integrate orchestrator in main.js and complete assembly module 2025-11-24 19:36:50 +01:00
21 changed files with 481 additions and 1374 deletions
BIN
View File
Binary file not shown.
+8 -23
View File
@@ -9,20 +9,9 @@
<body>
<div class="mitte" id="mitte">
<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">
<div class="flagsBtns" id="flagsBtns">
<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="mp4">mp4</option>
</select>
<select name="language_option" id="language_option">
</select>
</div>
@@ -31,32 +20,28 @@
<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>
<button class="custom-btn" id="manualUploadBtn">Search video</button>
<input type="file" id="videoUpload" accept="video/*">
<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" value="Meeting report">
<input type="checkbox" name ="docFormat" id="docFormat">
<label id="label_format" for="docFormat">Meeting report</label>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary" value="Summary with timestamps">
<input type="checkbox" name="docFormat" id="docFormatSummary">
<label id="label_summary" for="docFormatSummary">Summary with timestamps</label>
</div>
</div>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()">Submit</button>
<div class="progressbar" id="progressbar">
<div class="progressbar">
<div class="progress_fill"></div>
<span class="progress_text">0%</span>
</div>
-12
View File
@@ -1,9 +1,5 @@
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",
@@ -15,10 +11,6 @@ var languageOptions = {
"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",
@@ -30,10 +22,6 @@ var languageOptions = {
"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",
+58 -1
View File
@@ -2,6 +2,9 @@ import { app, BrowserWindow, ipcMain, dialog } from 'electron';
import { exec } from 'child_process';
import path from 'path';
import { fileURLToPath } from 'url';
// Import audio events and transcription module
import { audioEvents } from '../../services/modules/extraction/ffmpegExtractor.js';
import { transcribe } from '../../services/modules/transcription-remote/assembly.js';
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
@@ -22,7 +25,61 @@ function createWindow() {
mainWindow.loadFile('main/index.html');
}
app.whenReady().then(createWindow);
// Setup pipeline orchestrator
function setupOrchestrator() {
console.log('🎯 [Pipeline] Orchestrator ready. Listening for audio_ready events...');
audioEvents.on('audio_ready', async (data) => {
const { audioPath, sessionId } = data;
console.log(`✅ [Pipeline] Audio ready: ${sessionId}`);
// AC6: Send status to UI - Audio bereit
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'audio_ready',
message: 'Audio bereit'
});
try {
// AC4: Status transcription_started
console.log(`🚀 [Pipeline] Starting transcription: ${sessionId}`);
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'transcription_started',
message: 'Transkription gestartet'
});
// AC2: Auto-start transcription (S2-02b)
await transcribe(audioPath, sessionId);
// AC6: Status transcription_completed
console.log(`✅ [Pipeline] Transcription completed: ${sessionId}`);
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'transcription_completed',
message: 'Transkription abgeschlossen'
});
} catch (error) {
// AC5: Error logging + failed_transcription_start
console.error(`❌ [Pipeline] Transcription failed: ${sessionId}`);
console.error(` Error:`, error.message);
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'failed_transcription_start',
message: 'Fehler beim Transkriptionsstart',
error: error.message
});
}
});
}
app.whenReady().then(() => {
createWindow();
setupOrchestrator();
});
// Kommunikation vom Renderer (Frontend)
ipcMain.handle('convert-video', async (event, filePath) => {
+3 -15
View File
@@ -4,24 +4,12 @@ try {
contextBridge.exposeInMainWorld("explorer", {
onFileDrop: (file) => webUtils.getPathForFile(file)
})
contextBridge.exposeInMainWorld("submit", {
submit: (meeting_specifications) => {ipcRenderer.send("file_submit", meeting_specifications)}
contextBridge.exposeInMainWorld("extractor", {
extract: (file) => ipcRenderer.send("extract", file)
})
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");
}
}
+10 -56
View File
@@ -16,72 +16,26 @@ uploadContainer.addEventListener("drop", (e) => {
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";
var holdy = filePath + "";
if(holdy.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
console.log(filePath)
const files1 = e.dataTransfer.files;
handleFiles(files1);
}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) {
}
window.addEventListener('load', (e) => {
console.log("test");
loadLanguageOptions();
});
language_option.addEventListener('change', (e)=>{
try {
const select = document.getElementById('language_option');
changeLanguage(select.value);
} catch (error) {
}
const select = document.getElementById('language_option');
console.log(select.value);
changeLanguage(select.value);
});
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);
}
});
+30 -112
View File
@@ -1,82 +1,45 @@
//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 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"].');
if(pathTest.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
window.extractor.extract({inputVideoPath: pathTest, outputType:"wav"})
}
} 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);
console.log(error)
}
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
}
//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;
@@ -86,30 +49,34 @@ function changeLanguage(language) {
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);
}
}
//listener for the file explorer search when something got selected
videoUpload.addEventListener('change', () => {
try {
handleFiles(videoUpload.files);
} catch (error) {
console.log("Error in manualBtn EventListener change");
}
});
//function to display the file path in the drop down box
function handleFiles(files) {
try {
if (files.length > 0) {
const file = files[0];
if (file.type.startsWith('video/')) {
const filePath = window.explorer.onFileDrop(files[0])
videoUpload.files = files;
fileName.textContent = `Chosen video: ${file.name}`;
generateThumbnail(filePath);
activateSubmitBtn(true);
}
}
} catch (error) {
console.log("Error in script.js handleFiles function");
console.log(error);
}
}
@@ -122,7 +89,6 @@ function updateProgressBar(bar, value){
bar.querySelector(".progress_text").textContent = `${value}%`;
} catch (error) {
console.log("Error in scripts.js updateProgressBar function");
console.log(error);
}
}
@@ -131,13 +97,12 @@ function updateProgressBar(bar, value){
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;
var opty = options[i];
var namey = "option" + i;
var choice = document.createElement(namey);
choice.textContent = "t";
choice.value = i;
menu.appendChild(choice);
}
} catch (error) {
@@ -146,25 +111,6 @@ function loadAiOptions(options){
}
}
//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 {
@@ -183,32 +129,4 @@ function loadLanguageOptions(){
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;
}
}
+33 -74
View File
@@ -5,71 +5,46 @@ body {
justify-content: center;
align-items: center;
height: 100vh;
background-color: #f2f3f4;
background-color: #555;
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: 350px;
height: 200px;
width: 400px;
transition: border 0.3s, background-color 0.3s;
border: 2px dashed #7378c9;
border: 2px dashed #ccc;
}
.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;
@@ -77,27 +52,27 @@ 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;
@@ -106,11 +81,9 @@ gap: 5px;
gap: 10px;
align-items: flex-start;
}
.submit-btn {
padding: 10px 20px;
margin-top: 10px;
margin-bottom: 10px;
background-color: #007BFF;
color: white;
border: none;
@@ -118,33 +91,24 @@ gap: 5px;
cursor: pointer;
font-size: 14px;
}
.submit-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
pointer-events: none;
}
.mitte {
background-color: #FDFCFA;
background-color: #f2f3f4;
display: flex;
width: 700px;
flex-direction: column;
align-items: center;
padding: 5% 50px;
margin-top: 20px;
gap: 10px;
border: 0px;
border: 1px;
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;
@@ -152,16 +116,15 @@ h1 {
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%;
@@ -170,19 +133,15 @@ h1 {
color: white;
}
.dropdownMenus {
.flagsBtns {
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;
.de_Btn, .eng_Btn, .in_Btn {
padding: 8px 16px;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
}
+80 -150
View File
@@ -33,6 +33,73 @@ console.log(`${mapFunctions.size} Function modules loaded`);
console.log("--------------------------------------------------------------------------------");
// ======================== S3-06 : PIPELINE ORCHESTRATOR ========================
// Get audioEvents from ffmpegExtractor module
const ffmpegExtractor = mapFunctions.get("extraction-video-to-audio");
const audioEvents = ffmpegExtractor.audioEvents;
console.log('🎯 [S3-06] Pipeline Orchestrator ready. Listening for audio_ready events...');
audioEvents.on('audio_ready', async (data) => {
const { audioPath, sessionId } = data;
console.log(`✅ [Pipeline] Audio ready: ${sessionId}`);
console.log(`📁 Audio path: ${audioPath}`);
// Send status to UI
if (mainWindow) {
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'audio_ready',
message: 'Audio bereit'
});
}
try {
console.log(`🚀 [Pipeline] Starting transcription: ${sessionId}`);
if (mainWindow) {
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'transcription_started',
message: 'Transkription gestartet'
});
}
// Get transcription module
const assemblyModule = mapFunctions.get("assembly");
if (assemblyModule && assemblyModule.run) {
await assemblyModule.run(audioPath);
} else {
console.warn('⚠️ Assembly module not found or missing run function');
}
console.log(`✅ [Pipeline] Transcription completed: ${sessionId}`);
if (mainWindow) {
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'transcription_completed',
message: 'Transkription abgeschlossen'
});
}
} catch (error) {
console.error(`❌ [Pipeline] Transcription failed: ${sessionId}`);
console.error(` Error:`, error.message);
if (mainWindow) {
mainWindow.webContents.send('pipeline-status', {
sessionId,
status: 'failed_transcription_start',
message: 'Fehler beim Transkriptionsstart',
error: error.message
});
}
}
});
// ===============================================================================
// --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //
@@ -58,159 +125,22 @@ rl.on("line", data =>{
let mainWindow;
function createWindow() {
mainWindow = new electron.BrowserWindow({
width: 800,
height: 800,
webPreferences: {
nodeIntegration: false,
contextIsolation: true,
preload: `${mainDir}/electron/main/preload.js`
}
});
mainWindow = new electron.BrowserWindow({
width: 800,
height: 600,
webPreferences: {
nodeIntegration: false,
contextIsolation: true,
preload: `${mainDir}/electron/main/preload.js`
}
});
mainWindow.loadFile('./electron/main/index.html');
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 = 2 + 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 = ""
// 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
})
// 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
// })
// 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"}
]
}
electron.ipcMain.on("extract", (event, args) => {
mapFunctions.get("extraction-video-to-audio").function(args)
})
+115 -674
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -1,7 +1,7 @@
{
"dependencies": {
"@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",
-1
View File
@@ -16,4 +16,3 @@ cliProgress = require('cli-progress');
// { app, BrowserWindow, ipcMain, dialog } = require('electron');
electron = require('electron');
genai = require("@google/genai");
@@ -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:"llm", // value used to differentiate each module to order them in the UI
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
+15 -5
View File
@@ -1,3 +1,6 @@
const EventEmitter = require('events');
const audioEvents = new EventEmitter();
// Ensure ffmpeg binary is available
if (!ffmpegPath) {
throw new Error('FFmpeg binary not found!');
@@ -31,11 +34,11 @@ module.exports = {
hideCursor: true
});
try {
return new Promise((resolve, reject) => {
// if (meta.url === `file://${process.argv[1]}`) {
this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
.then((resp) => resolve(resp))
.then(() => console.log('Audio extraction successful.'))
.catch((err) => console.error(err));
})
// }
} catch (error) {
console.log(parameter.outputType);
@@ -74,7 +77,13 @@ module.exports = {
progressBar.update(100, { timemark: 'done' });
progressBar.stop();
console.log(`Extraction completed: ${outputAudioPath}`);
resolve(outputAudioPath);
audioEvents.emit('audio_ready', {
sessionId: inputVideoName,
audioPath: outputAudioPath
});
resolve();
})
.on('error', (err) => {
progressBar.stop();
@@ -87,5 +96,6 @@ module.exports = {
console.log();
}
});
}
},
audioEvents: audioEvents
}
-55
View File
@@ -1,55 +0,0 @@
const outputDir = path.join(__dirname, "../../../storage/documents"); // path for output directory
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
}
const ai = new genai.GoogleGenAI({
apiKey: process.env.GOOGLE_API_KEY // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
});
module.exports = {
name: "llm-gemini",
type: "llm",
displayname: "Gemini LLM",
description: "Generates documents using Google Gemini LLM",
async function(parameter) {
try {
console.log("Gemini LLM module invoked with parameters:", parameter);
await this.createDocumentFromTranscript( //Call the function to create document with transcript, document type and language
parameter.inputTranscriptPath, // Path to input transcript file
parameter.documentTypePath, // Path to document type file which is chosen in the front end by the user
parameter.language // Language for the document which is chosen in the front end by the user
);
} catch (error) {
console.error("Error in Gemini LLM module:", error);
}
},
createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
try {
const transcript = await fs.promises.readFile(transcriptPath, "utf-8");
const documentType = await fs.promises.readFile(documentTypePath, "utf-8");
const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`;
const response = await ai.models.generateContent({
model: "gemini-2.5-flash", // Specify the Gemini model to use
contents: promptText // Input prompt for content generation
});
const output = response.text || ""; // Get generated text from response or default to empty string (if null)
const outPath = path.join(outputDir, "test.md"); // Output file path & name TO BE DONE to make dynamic out of 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);
}
}
};
@@ -1,8 +1,128 @@
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
require('dotenv/config');
const axios = require('axios');
const fs = require('fs');
const path = require('path');
const API_KEY = process.env.ASSEMBLYAI_API_KEY;
const BASE_URL = 'https://api.assemblyai.com/v2';
/**
* Uploads audio file to AssemblyAI
*/
async function uploadAudio(audioPath) {
const audioData = fs.readFileSync(audioPath);
const response = await axios.post(`${BASE_URL}/upload`, audioData, {
headers: {
'authorization': API_KEY,
'content-type': 'application/octet-stream'
}
}
});
return response.data.upload_url;
}
/**
* Extract session id from path or URL
*/
function getSessionId(inputPath) {
try {
const parsed = new URL(inputPath);
const base = path.basename(parsed.pathname);
return base.replace(/\.[^.]+$/, '');
} catch (err) {
return path.basename(inputPath, path.extname(inputPath));
}
}
/**
* Creates transcription job with speaker diarization
*/
async function createTranscript(audioUrl) {
const response = await axios.post(`${BASE_URL}/transcript`, {
audio_url: audioUrl,
speaker_labels: true,
language_detection: true
}, {
headers: {
'authorization': API_KEY,
'content-type': 'application/json'
}
});
return response.data.id;
}
/**
* Polls transcript status until completed
*/
async function pollTranscript(transcriptId) {
while (true) {
const response = await axios.get(`${BASE_URL}/transcript/${transcriptId}`, {
headers: { 'authorization': API_KEY }
});
const status = response.data.status;
if (status === 'completed') {
return response.data;
} else if (status === 'error') {
throw new Error(`Transcription failed: ${response.data.error}`);
}
// Wait 3 seconds before next poll
await new Promise(resolve => setTimeout(resolve, 3000));
}
}
/**
* Saves transcript to storage
*/
function saveTranscript(transcript, sessionId) {
const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
const outputPath = path.join(outputDir, `${sessionId}.json`);
fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
console.log(`✅ Transcript saved: ${outputPath}`);
}
module.exports = {
name: "assembly",
type: "transcription",
displayname: "AssemblyAI",
run: async function(audioPath) {
try {
// Determine if audioPath is an external URL or a local file
let audioUrl;
if (/^https?:\/\//i.test(audioPath)) {
console.log('🔗 Using external audio URL...');
audioUrl = audioPath;
} else {
if (!fs.existsSync(audioPath)) {
throw new Error(`Audio file not found: ${audioPath}`);
}
console.log('📤 Uploading audio file...');
audioUrl = await uploadAudio(audioPath);
}
console.log('🔄 Creating transcript job...');
const transcriptId = await createTranscript(audioUrl);
console.log('⏳ Waiting for transcription...');
const transcript = await pollTranscript(transcriptId);
const sessionId = getSessionId(audioPath);
saveTranscript(transcript, sessionId);
return transcript;
} catch (error) {
console.error('❌ Transcription error:', error.message);
throw error;
}
}
};
-3
View File
@@ -9,8 +9,5 @@ module.exports = {
// 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"})
}
}
@@ -1,16 +0,0 @@
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)
});
})
}
}
-39
View File
@@ -1,39 +0,0 @@
**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."
}
-7
View File
@@ -1,7 +0,0 @@
const gemini = require("../../../services/modules/llm-gemini/gemini.js");
gemini.function({
inputTranscriptPath: "./transcript.json",
documentTypePath: "./documentType.json",
language: "de"
});
-122
View File
@@ -1,122 +0,0 @@
[
{
"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
}
]