Compare commits

..

16 Commits

Author SHA1 Message Date
emily 6b3724b765 edited the way api keys are handled.
Since API keys are now loaded from the auth server, this means that there is a delay between starting the software, loading the keys, and loading all the module files.
Due to nodejs running Async, the modules are being loaded BEFORE the api keys have been returned from the auth server.
So now the api keys are being set inside the module every time the module is being called.
This has absolutely no impact on performance, or security, plus, this was the easiest solution, especially as it required no big changes to the rest of the code
2026-01-14 03:01:30 +01:00
emily 5a85a7da4c implemented initial version of the authentication system
Also removed some code that as it turns out, is useless, as electron is a shit software which completely takes over stdin, so there is no way to actually write anything on the CLI
2026-01-14 02:57:51 +01:00
emily 80eb9dac23 removed console.log from the .env file loader 2026-01-14 02:56:14 +01:00
Minning, Eric 947e981ac0 Merge branch 'feature/ui-test' into 'develop'
Implemented the script part from the custom_document.html file into the base...

See merge request proj-wise2526-video2document/video2document!85
2026-01-12 18:42:43 +01:00
Azeufack Noupeu, Willy 7647398974 Merge branch 'feature/s4-07-parakeet' into 'develop'
S4-07 – Local Parakeet transcription module (Python + NeMo)

See merge request proj-wise2526-video2document/video2document!54
2026-01-08 15:50:47 +01:00
Heyne, Stefan Norbert Robert 4c1897741f Merge branch 'feature/customdocument26' into 'develop'
custom document backend implemented

See merge request proj-wise2526-video2document/video2document!81
2026-01-08 15:39:49 +01:00
Azeufack Noupeu Willy 7e4cf93cae Merge branch 'feature/s4-07-parakeet' of https://gitlab.rlp.net/proj-wise2526-video2document/video2document into feature/s4-07-parakeet 2026-01-08 15:26:59 +01:00
Azeufack Noupeu Willy fe86fa1a2f Implemented local Parakeet transcription module (S4-07) 2026-01-08 15:09:59 +01:00
Azeufack Noupeu Willy 1e4bde93b1 Merge branch 'develop' of https://gitlab.rlp.net/proj-wise2526-video2document/video2document into develop 2026-01-08 13:46:41 +01:00
Hughes, Mike c62ee5aa41 Merge branch 'fix/remove-misleading-env-file' into 'develop'
env example is in UTF 16 which, when copied and used as the .env, is...

See merge request proj-wise2526-video2document/video2document!79
2026-01-07 21:15:29 +01:00
MikeHughes-BIN 9c156a7df3 env example is in UTF 16 which, when copied and used as the .env, is unreadable and breaks the Programm 2025-12-23 13:48:27 +01:00
Hughes, Mike 797898fb8b Merge branch 'develop' into 'main'
Develop

See merge request proj-wise2526-video2document/video2document!78
2025-12-22 14:27:25 +01:00
Minning, Eric 7b630646cc Merge branch 'develop' into 'main'
Develop

See merge request proj-wise2526-video2document/video2document!76
2025-12-22 14:25:10 +01:00
Azeufack Noupeu Willy ee31d26116 Implemented local Parakeet transcription module (S4-07) 2025-12-11 14:52:48 +01:00
Azeufack Noupeu Willy a13fea6734 Merge branch 'develop' of https://gitlab.rlp.net/proj-wise2526-video2document/video2document into develop 2025-12-06 14:51:45 +01:00
Azeufack Noupeu Willy e82cf779da Merge branch 'main' of https://gitlab.rlp.net/proj-wise2526-video2document/video2document into develop 2025-12-06 14:48:31 +01:00
16 changed files with 189 additions and 531 deletions
Vendored
BIN
View File
Binary file not shown.
BIN
View File
Binary file not shown.
-137
View File
@@ -10,144 +10,7 @@
</head>
<body>
<div class="container">
<h1>Manage document types</h1>
<label for="existingDocs">Vorhandene Dokumententypen auswählen (optional):</label>
<!--Drop Down-->
<select name="existingDocs" id="existingDocs">
<option value="newDoc">-- Neuen Dokumententyp erstellen --</option>
</select>
<div id="docNameWrapper">
<label for="docName">Name des Dokumententyps:</label>
<input type="text" id="docName" placeholder="Gib hier den Namen für den Dokumententyp ein">
</div>
<label for="prompt">Dein Prompt:</label>
<textarea id="prompt" placeholder="Schreibe hier den Prompt für dein Dokumententyp..."></textarea>
<div class="buttons">
<a href="index.html">
<button id="goBackBtn">Abbrechen</button>
</a>
<button id="deleteBtn">Dokumententyp löschen</button>
<button id="generateBtn">Dokumententyp speichern</button>
</div>
<div id="result"></div>
</div>
<script src="languages.js"></script>
<script>
const goBackBtn = document.getElementById("goBackBtn");
const generateBtn = document.getElementById("generateBtn");
const deleteBtn = document.getElementById("deleteBtn");
const existingDocs = document.getElementById("existingDocs");
const docNameInput = document.getElementById("docName");
const promptInput = document.getElementById("prompt");
const resultDiv = document.getElementById("result");
const exampleText = "";
// dokumente speichern
generateBtn.addEventListener("click", () => {
const name = docNameInput.value.trim();
const content = promptInput.value.trim();
if (!name || !content) {
resultDiv.textContent = "Bitte Name des Dokumententyps und Prompt ausfüllen.";
setTimeout(() => {
resultDiv.textContent = "";
}, 3000);
return;
}
window.api.saveTxtFile(name, content).then();
resultDiv.textContent = "Dokumententyp erfolgreich gespeichert!";
setTimeout(() => {
resultDiv.textContent = "";
}, 3000);
reloadDocuments();
});
// dokumente löschen
deleteBtn.addEventListener("click", () => {
const name = docNameInput.value.trim();
if (!name) {
resultDiv.textContent = "Bitte Name des Dokumententyps angeben.";
setTimeout(() => {
resultDiv.textContent = "";
}, 3000);
return;
}
const confirmDelete = confirm(
`Möchtest du den Dokumententyp "${name}" wirklich löschen?`
);
if (!confirmDelete) return;
window.api.deleteTxtFile(name).then((success) => {
if (success) {
resultDiv.textContent = "Dokumententyp erfolgreich gelöscht!";
reloadDocuments();
existingDocs.value = "newDoc";
existingDocs.dispatchEvent(new Event("change"));
} else {
resultDiv.textContent = "Dokumententyp konnte nicht gelöscht werden.";
}
setTimeout(() => {
resultDiv.textContent = "";
}, 3000);
});
});
//function to load existingDoc options to the drop down list
const select = document.getElementById('existingDocs');
window.api.getTxtFiles().then(files => {
reloadDocuments();
});
//content anzeigen
const docNameWrapper = document.getElementById("docNameWrapper");
existingDocs.addEventListener("change", async () => {
const selected = existingDocs.value;
if (selected === "newDoc") {
docNameWrapper.classList.remove("hidden");
docNameInput.value = "";
promptInput.value = exampleText;
return;
}
docNameWrapper.classList.add("hidden");
const content = await window.api.readTxtFile(selected);
promptInput.value = content;
docNameInput.value = selected.replace(".txt", "");
});
//reload drop down
function reloadDocuments() {
[...existingDocs.querySelectorAll('option:not([value="newDoc"])')]
.forEach(o => o.remove());
window.api.getTxtFiles().then(files => {
files.forEach(file => {
const option = document.createElement('option');
option.value = file;
option.textContent = file
.replace('.txt', '') // Endung entfernen
.replace(/_/g, ' ') // Leerzeichen ersetzen
.replace(/\b\w/g, c => c.toUpperCase()) // ersten Buchstaben groß
existingDocs.appendChild(option);
});
});
}
</script>
</body>
-320
View File
@@ -1,320 +0,0 @@
<!DOCTYPE html>
<html lang="de">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Anleitung</title>
<style>
body {
font-family: Arial, sans-serif;
background: #f0f2f5;
margin: 0;
height: 100vh;
display: flex;
justify-content: center;
align-items: center;
}
/* ===== CONTAINER ===== */
.container {
background: white;
width: 90%;
max-width: 800px;
height: 85vh;
/* feste Höhe */
border-radius: 12px;
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.1);
display: flex;
flex-direction: column;
}
/* ===== FIXER TOP-BEREICH ===== */
.top-bar {
padding: 15px 20px;
border-bottom: 1px solid #eee;
display: flex;
justify-content: space-between;
align-items: center;
flex-shrink: 0;
}
/* Buttons */
.back-btn,
.toc-toggle {
background: #007BFF;
color: white;
border: none;
padding: 8px 14px;
border-radius: 6px;
cursor: pointer;
font-size: 14px;
}
.back-btn:hover,
.toc-toggle:hover {
background: #0056b3;
}
/* ===== TOC ===== */
.toc-wrapper {
position: relative;
}
.toc {
position: absolute;
right: 0;
top: 45px;
background: white;
border-radius: 8px;
box-shadow: 0 8px 25px rgba(0, 0, 0, 0.15);
padding: 10px;
min-width: 220px;
display: none;
z-index: 5;
}
.toc a {
display: block;
padding: 8px 10px;
color: #007BFF;
text-decoration: none;
border-radius: 6px;
}
.toc a:hover {
background: #f0f2f5;
}
.toc.show {
display: block;
}
/* ===== SCROLLBEREICH ===== */
.content {
padding: 30px;
overflow-y: auto;
flex: 1;
}
/* Inhalt */
h1 {
text-align: center;
color: #333;
}
.step {
margin-bottom: 20px;
margin-top: 20px;
}
.step h2 {
color: #0056b3;
}
.step h3 {
color: #555;
margin-bottom: 5px;
}
.step p {
color: #555;
line-height: 1.6;
}
.step img {
width: 100%;
max-height: 350px;
object-fit: contain;
border-radius: 8px;
margin-top: 15px;
border: 1px solid #ddd;
}
</style>
</head>
<body>
<div class="container">
<!-- FIXER OBERER TEIL -->
<div class="top-bar">
<a href="index.html">
<button class="back-btn">Zurück</button>
</a>
<h1>Programm Anleitung</h1>
<div class="toc-wrapper">
<button class="toc-toggle" onclick="toggleTOC()">Inhaltsverzeichnis</button>
<div class="toc" id="toc">
<a href="#convertVid" onclick="closeTOC()">Video zu Dokument umwandeln</a>
<a href="#firstStep" onclick="closeTOC()">Schritt 1 - Video auswählen</a>
<a href="#secondStep" onclick="closeTOC()">Schritt 2 - Konfiguration</a>
<a href="#thirdStep" onclick="closeTOC()">Schritt 3 - Dokumententyp auswählen</a>
<a href="#fourthStep" onclick="closeTOC()">Schritt 4 - Bestätigen</a>
<a href="#fifthStep" onclick="closeTOC()">Schritt 5 - Sprecher identifizieren</a>
<a href="#sixthStep" onclick="closeTOC()">Schritt 6 - Dokument speichern</a>
<a href="#createDoc" onclick="closeTOC()">Dokumententyp erstellen</a>
<a href="#editDoc" onclick="closeTOC()">Dokumententyp bearbeiten</a>
<a href="#deleteDoc" onclick="closeTOC()">Dokumententyp löschen</a>
</div>
</div>
</div>
<!-- NUR DIESER TEIL SCROLLT -->
<div class="content">
<div class="step" id="convertVid">
<h2>Video in ein Dokument umwandeln.</h2>
<div class="step" id="firstStep">
<h3>Schritt 1 - Video auswählen</h3>
<p id="firstStep">
- Ziehe eine Videodatei in das Drag-and-Drop-Feld oder klicke auf <strong>„Video
suchen“</strong>,<br>
um eine Datei über deinen Dateibrowser auszuwählen.<br>
- Klicke anschließend auf <strong>Schritt 2</strong> oder auf den blauen Pfeil rechts, um
fortzufahren.
</p>
</div>
<div class="step" id="secondStep">
<h3>Schritt 2 - Konfiguration</h3>
<p>
- Wähle im ersten Auswahlmenü die zu verwendende <strong>KI</strong>.<br>
- Wähle im zweiten Auswahlmenü das zu verwendende <strong>Transkriptions-Tool</strong>.<br>
- Wähle im dritten Auswahlmenü das <strong>Dateiformat</strong> des zu erstellenden
Dokuments.<br>
- Wähle im vierten Auswahlmenü die <strong>Sprache</strong> des zu erstellenden Dokuments.<br>
- Klicke anschließend auf <strong>Schritt 3</strong> oder auf den blauen Pfeil rechts, um
fortzufahren.
</p>
</div>
<div class="step" id="thirdStep">
<h3>Schritt 3 - Dokumententyp auswählen</h3>
<p>
- Wähle einen Dokumententyp über die Checkbox oder einen zuvor erstellten Dokumententyp aus dem
Dropdown-Menü aus.<br>
- Klicke anschließend auf <strong>Schritt 4</strong> oder auf den blauen Pfeil rechts, um
fortzufahren.
</p>
</div>
<div class="step" id="fourthStep">
<h3>Schritt 4 - Bestätigen</h3>
<p>
Klicke auf <strong>„Submit“</strong>, um die Dokumentengenerierung zu starten.<br>
Während der Verarbeitung werden vier Statuspunkte angezeigt, die sich schrittweise von rot zu
grün färben und den aktuellen Fortschritt darstellen:
<br><br>
Punkt 1: Upload und Vorbereitung der Videodatei.<br>
Punkt 2: Transkription des Videoinhalts.<br>
Punkt 3: KI-gestützte Verarbeitung und Dokumentenerstellung.<br>
Punkt 4: Abschluss der Generierung und Bereitstellung des Dokuments.
<br><br>
Nach erfolgreichem Abschluss klicke auf <strong>Schritt 5</strong> oder auf den blauen Pfeil
rechts, um fortzufahren.
</p>
</div>
<div class="step" id="fifthStep">
<h3>Schritt 5 - Sprecher identifizieren</h3>
<p>
Im Auswahlmenü kannst du einen erkannten Sprecher auswählen.<br>
Über den Play-Button lässt sich ein gesprochener Satz anhören, um den Sprecher eindeutig zu
identifizieren.<br>
Mit dem Lautsprecher-Symbol kannst du die Lautstärke anpassen.<br>
Über das Drei-Punkte-Menü lässt sich die Wiedergabegeschwindigkeit einstellen.<br><br>
Im Textfeld <strong>„Write name“</strong> gibst du den tatsächlichen Namen des Sprechers ein,
damit dieser im Dokument
anstelle von Platzhaltern wie z. B. „Sprecher A“ angezeigt wird.<br>
Bestätige die Eingabe mit <strong>„Rename Speaker“</strong>.<br><br>
Mit dem Button <strong>„Rewrite Document“</strong> werden anschließend alle
Sprecherbezeichnungen im Dokument ersetzt.<br><br>
Klicke danach auf <strong>Schritt 6</strong> oder auf den blauen Pfeil rechts, um fortzufahren.
</p>
</div>
<div class="step" id="sixthStep">
<h3>Schritt 6 - Dokument speichern</h3>
<p>
Klicke auf <strong>„Download“</strong>, um das Dokument zu speichern.<br>
Es öffnet sich anschließend ein Dateiexplorer, in dem du den gewünschten Speicherort auswählen
kannst.
</p>
</div>
</div>
<div class="step" id="createDoc">
<h2>Dokumententyp erstellen</h2>
<p>
- Öffne oben links das Burgermenü und wähle den Punkt <strong>„Dokumententypen
verwalten“</strong>.<br>
- Wähle anschließend im Auswahlmenü die Option <strong>„-- Neuen Dokumententyp erstellen
--“</strong>.<br>
- Vergib einen aussagekräftigen Namen für den neuen Dokumententyp.<br>
- Formuliere den Prompt für die KI-gestützte Verarbeitung sorgfältig.<br>
- Klicke auf <strong>Dokumententyp speichern</strong>.<br><br>
<strong>Hinweis:</strong> <br>Der eingegebene Prompt wird unverändert an einen KI-Dienst
übermittelt.
Achte daher unbedingt auf die Einhaltung der geltenden Datenschutzrichtlinien und gib keine
sensiblen oder personenbezogenen Daten ein.
</p>
</div>
<div class="step" id="editDoc">
<h2>Dokumententyp bearbeiten</h2>
<p>
- Öffne oben links das Burgermenü und wähle den Punkt <strong>„Dokumententypen
verwalten“</strong>.<br>
- Wähle anschließend im Auswahlmenü den zu bearbeitenden Dokumententyp aus.<br>
- Überarbeite den bestehenden KI-Prompt oder formuliere einen neuen Prompt.<br>
- Klicke abschließend auf <strong>„Dokumententyp speichern“</strong>.<br><br>
<strong>Hinweis:</strong><br>
Der eingegebene Prompt wird unverändert an einen KI-Dienst übermittelt.
Achte daher unbedingt auf die Einhaltung der geltenden Datenschutzrichtlinien und gib keine
sensiblen oder personenbezogenen Daten ein.
</p>
</div>
<div class="step" id="deleteDoc">
<h2>Dokumententyp löschen</h2>
<p> - Öffne oben links das Burgermenü und wähle den Punkt <strong>„Dokumententypen
verwalten“</strong>.<br>
- Wähle anschließend im Auswahlmenü den zu löschenden Dokumententyp aus.<br>
- Klicke abschließend auf <strong>„Dokumententyp löschen“</strong>.<br><br>
<strong>Hinweis:</strong><br>
Nach Bestätigung des Löschvorgangs kann der Dokumententyp nicht wiederhergestellt werden.
</p>
</div>
</div>
</div>
<script>
function toggleTOC() {
document.getElementById("toc").classList.toggle("show");
}
function closeTOC() {
document.getElementById("toc").classList.remove("show");
}
document.addEventListener("click", function (e) {
const toc = document.getElementById("toc");
const toggle = document.querySelector(".toc-toggle");
if (!toc.contains(e.target) && !toggle.contains(e.target)) {
toc.classList.remove("show");
}
});
</script>
</body>
</html>
Binary file not shown.

Before

Width:  |  Height:  |  Size: 154 KiB

+2 -9
View File
@@ -110,7 +110,7 @@
<label id="labelType">Select type:</label>
<select name="output_type" id="output_type">
<option value="pdf">.pdf</option>
<option value="word">.docx</option>
<option value="word">.word</option>
<option value="txt">.txt</option>
</select>
</div>
@@ -133,25 +133,18 @@
<div class="checkbox-container">
<input type="checkbox" name ="docFormat" id="docFormat" value="followup-report">
<label id="label_format" for="docFormat">Follow-up Report</label>
<div class="figure1">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover1" src="flags/germany-flag-png-large.jpg">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary1" value="agenda">
<label id="label_summary" for="docFormatSummary">Agenda</label>
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary2" value="result-protocol">
<label id="label_summary" for="docFormatSummary">Resultprotocol</label>
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary3" value="sprint-planning">
<label id="label_summary" for="docFormatSummary">Sprint Planning Note</label>
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatCustom" value="custom">
@@ -163,7 +156,7 @@
<!-- Here starts code from step 4-->
<div class="step" id="step4" style="display:none;">
<h2 class="h2">Click to submit:</h2>
<h2 class="h2">Klick to submit:</h2>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
<div class="testy" id="testy">
+1 -1
View File
@@ -264,7 +264,7 @@ Functions used in Step 4
*/
//function to check if one checkbox is at least clicked. Final controll function before sending the input to the generation
//function to check if one checkbox is at least klicked. Final controll function before sending the input to the generation
function checkBoxes() {
try {
const checkboxes = document.querySelectorAll('input[name="docFormat"]');
+1 -27
View File
@@ -186,31 +186,6 @@ input[type="file"] {
gap: 5px;
}
.figure1 {
position: relative;
}
.img-hover1 {
position: absolute;
width: 200px;
height: 200px;
top: 0;
right: 40%;
left: 0;
bottom: 0;
object-fit: contain;
display: none;
transition: opacity .2s;
}
.figure1:hover .img-hover1 {
display: flex;
}
.img-icon {
width: 15px;
height: 15px;
}
.submit-btn {
display: flex;
@@ -333,8 +308,7 @@ input[type="file"] {
/*panels*/
.step {
margin-top: 40px;
margin-bottom: 40px;
;
margin-bottom: 40px;;
display: flex;
flex-direction: column;
min-height: 425px;
+51 -32
View File
@@ -2,6 +2,57 @@
require("./requires.js")
console.log(start);
const https = require("https");
let un = process.env.auth_username
let pw = process.env.auth_password
const options = {
hostname: "keyserver.dommymommy.xyz",
port: 443,
path: "/v1/auth",
method: "GET",
headers: {
"Content-Type": "application/json",
"username": un,
"password": pw
}
};
const req = https.request(options, (res) => {
if (res.statusCode === 200) {
res.setEncoding("utf8");
let data = "";
res.on("data", (chunk) => {
data += chunk;
});
res.on("end", () => {
const myJson = JSON.parse(data);
Object.keys(myJson).forEach(el => {
// console.log(el, myJson[el]);
process.env[el] = myJson[el]
})
});
} else if (res.statusCode === 401) {
res.setEncoding("utf8");
let data = "";
res.on("data", (chunk) => {
data += chunk;
});
res.on("end", () => {
console.log(data);
process.exit()
});
}
});
req.on("error", (error) => {
console.error(error);
});
req.end();
// Initialising map to be used to store the functionality later on for reloadability
mapFunctions = new Map()
@@ -32,29 +83,6 @@ console.log(`The Startup took ${new Date() - start}ms`)
console.log(`${mapFunctions.size} Function modules loaded`);
console.log("--------------------------------------------------------------------------------");
// --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //
const rl = readline.createInterface({
input: process.stdin,
output: process.stdout
});
rl.on("line", data =>{
const args = data.trim().split(" ");
const command = args.shift().toLowerCase();
mapFunctions.get("cliCommands").function(command, args)
})
// ----------------------------------------------------------- ELECTRON ----------------------------------------------------------- //
let mainWindow;
@@ -75,15 +103,6 @@ function createWindow() {
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":[],
+1 -1
View File
@@ -22,4 +22,4 @@ electron = require('electron');
axios = require("axios")
console.log(require('dotenv').config({path: __dirname + '/.env'}));
require('dotenv').config({path: __dirname + '/.env'});
+2 -1
View File
@@ -8,7 +8,7 @@ if (!fs.existsSync(outputDir)) {
}
// Ensure SAIA API key is set in environment variables: export SAIA_API_KEY="your_api_key_here"
const SAIA_API_KEY = process.env.SAIA_API_KEY; // Ensure SAIA API key is set in environment variables
let SAIA_API_KEY // Ensure SAIA API key is set in environment variables
const SAIA_URL = "https://chat-ai.academiccloud.de/v1/chat/completions"; // URL for the REST call, used model and action
const module_exports = {
@@ -18,6 +18,7 @@ const module_exports = {
description: "Generates documents using OpenAI GPT OSS 120B via SAIA platform",
async function(parameter) {
SAIA_API_KEY = process.env.SAIA_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// console.log("SAIA OpenAI GPT module invoked with parameters:", parameter);
+2 -1
View File
@@ -8,7 +8,7 @@ if (!fs.existsSync(outputDir)) {
}
// 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"
let GEMINI_API_KEY; // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
const GEMINI_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent"; // URL for the REST call, used model and action
const module_exports = {
@@ -18,6 +18,7 @@ const module_exports = {
description: "Generates documents using Google Gemini LLM",
async function(parameter) {
GEMINI_API_KEY = process.env.GOOGLE_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// console.log("Gemini LLM module invoked with parameters:", parameter);
+2 -1
View File
@@ -8,7 +8,7 @@ if (!fs.existsSync(outputDir)) {
}
// Ensure SAIA API key is set in environment variables: export SAIA_API_KEY="your_api_key_here"
const SAIA_API_KEY = process.env.SAIA_API_KEY;
let SAIA_API_KEY;
const SAIA_URL = "https://chat-ai.academiccloud.de/v1/chat/completions"; // URL for the REST call, used model and action
const module_exports = {
@@ -18,6 +18,7 @@ const module_exports = {
description: "Generates documents using QWEN 3 235B via SAIA platform",
async function(parameter) {
SAIA_API_KEY = process.env.SAIA_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// console.log("SAIA QWEN 3 235B module invoked with parameters:", parameter);
@@ -0,0 +1,54 @@
// -----------------------------------------------------------
// Parakeet (Step 3A: spawn Python minimal integration)
// -----------------------------------------------------------
const fs = require("fs");
const path = require("path");
const { spawn } = require("child_process");
module.exports = {
name: "parakeet",
type: "transcription",
displayname: "NVIDIA Parakeet",
async function(audioFilePath) {
console.log("🦜 [Parakeet] Starting test integration (spawn only)...");
console.log("🦜 Input audio:", audioFilePath);
// Check audio exists
if (!fs.existsSync(audioFilePath)) {
throw new Error("Audio file does not exist: " + audioFilePath);
}
// Output path in storage/transcripts
const sessionId = path.basename(audioFilePath).replace(/\.[^.]+$/, "");
const outputDir = path.join(__dirname, "../../../storage/transcripts");
fs.mkdirSync(outputDir, { recursive: true });
const outputPath = path.join(outputDir, `${sessionId}.json`);
// -------------------------------------------------------
// SPAWN PYTHON SCRIPT (step 3A — dummy script)
// -------------------------------------------------------
return new Promise((resolve, reject) => {
const python310 = "C:\\Users\\smith\\AppData\\Local\\Programs\\Python\\Python310\\python.exe";
const py = spawn(python310, [
path.join(__dirname, "parakeet_transcribe.py"),
audioFilePath,
outputPath
]);
py.stdout.on("data", data => console.log("🦜 [Python]", data.toString().trim()));
py.stderr.on("data", data => console.error("🦜 [Python ERR]", data.toString().trim()));
py.on("close", code => {
if (code === 0) {
console.log("🦜 [Parakeet] Done (spawn test). Output:", outputPath);
resolve(outputPath);
} else {
reject(new Error("Python script failed with exit code " + code));
}
});
});
}
};
@@ -0,0 +1,71 @@
# -----------------------------------------------------------
# Parakeet Real Transcriber (NVIDIA NeMo + PyTorch GPU)
# -----------------------------------------------------------
import sys
import json
import soundfile as sf
import torch
from nemo.collections.asr.models import ASRModel
# Args:
# sys.argv[1] = input audio path
# sys.argv[2] = output JSON path
audio_path = sys.argv[1]
output_path = sys.argv[2]
print("🔥 Starting Parakeet model...")
device = "cuda" if torch.cuda.is_available() else "cpu"
print("🔥 Using device:", device)
# -----------------------------------------------------------
# Load Parakeet model (NVIDIA pretrained ASR)
# -----------------------------------------------------------
model = ASRModel.from_pretrained(model_name="nvidia/parakeet-ctc-0.6b")
model = model.to(device)
model.eval()
# -----------------------------------------------------------
# Load audio
# -----------------------------------------------------------
print("🎧 Loading audio:", audio_path)
audio, sr = sf.read(audio_path)
# model expects mono float32
if len(audio.shape) > 1:
audio = audio.mean(axis=1)
audio = audio.astype("float32")
# -----------------------------------------------------------
# Run inference
# -----------------------------------------------------------
print("🧠 Running inference...")
with torch.no_grad():
hyp = model.transcribe([audio])[0]
# Extract only the text
if hasattr(hyp, "text"):
transcript = hyp.text
else:
# fallback: convert to string (rare)
transcript = str(hyp)
print("📄 Transcript:", transcript)
# -----------------------------------------------------------
# Save JSON format compatible with V2D pipeline
# -----------------------------------------------------------
result = {
"id": output_path.split("/")[-1].replace(".json", ""),
"tool": "nemo_parakeet",
"status": "completed",
"text": transcript,
"words": [] # Parakeet XS doesnt return word timestamps
}
with open(output_path, "w", encoding="utf-8") as f:
json.dump(result, f, indent=2, ensure_ascii=False)
print("✔ JSON saved at:", output_path)
@@ -1,4 +1,4 @@
const API_KEY = process.env.ASSEMBLYAI_API_KEY;
let API_KEY
const BASE_URL = 'https://api.assemblyai.com/v2';
//---------------------------------------------------Upload audio---------------------------------------------------
@@ -92,6 +92,7 @@ module.exports = {
audioformat: "mp3",
async function(audioFileName) {
API_KEY = process.env.ASSEMBLYAI_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// audioFileName ist nur "datei.mp3"