Compare commits

..

2 Commits

54 changed files with 476 additions and 20099 deletions
Vendored
BIN
View File
Binary file not shown.
+2 -16
View File
@@ -963,23 +963,9 @@ app.*.symbols
!/packages/flutter_tools/test/data/dart_dependencies_test/**/.packages
!/dev/ci/**/Gemfile.lock
# Storage files
storage/documents/*
storage/transcriptionSummaries/*
storage/transcripts/*
storage/video/*
# The inverse for the .gitkeep files, to make sure the folders are there but not the local files
!storage/documents/.gitkeep
!storage/transcriptionSummaries/.gitkeep
!storage/transcripts/.gitkeep
!storage/video/.gitkeep
#Storage files
storage/
*.mp4
*.webm
*.mp3
*.mov
*.wav
*.flac
!testvideo.mp4
+25 -20
View File
@@ -1,28 +1,33 @@
image: node:latest
workflow:
rules:
# Run the pipeline for merge requests or when committing to a branch
- if: $CI_PIPELINE_SOURCE == "merge_request_event"
- if: $CI_COMMIT_BRANCH
image: python:3.14.0
stages:
# - install
- setup
- test
# job-install:
# stage: install
# script:
# - npm install
# artifacts:
# untracked: false
# when: on_success
# access: all
# expire_in: "30 days"
# paths:
# - node_modules
setup_environment:
stage: setup
script:
- pip install --upgrade pip
- pip install -r requirements.txt
- echo "Dependencies installed successfully."
only:
- main
- feature/ci-pipeline-s1-09a-1 # You can add more branches if needed
job-test:
test_app:
stage: test
script:
- npm install
- echo "ASSEMBLYAI_API_KEY=$apikey_assembly" > .env
- echo "GOOGLE_API_KEY=$apikey_gemini" >> .env
- echo "SAIA_API_KEY=$apikey_saia" >> .env
- npm test
- echo "Running V2D Framework basic test..."
- python -m unittest discover || echo "No tests found."
only:
- main
- feature/ci-pipeline-s1-09a-1
+81 -366
View File
@@ -1,378 +1,93 @@
# Video2Document
## Getting started
To make it easy for you to get started with GitLab, here's a list of recommended next steps.
Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
## Add your files
- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
- [ ] [Add files using the command line](https://docs.gitlab.com/topics/git/add_files/#add-files-to-a-git-repository) or push an existing Git repository with the following command:
```
cd existing_repo
git remote add origin https://gitlab.rlp.net/proj-wise2526-video2document/video2document.git
git branch -M main
git push -uf origin main
```
## Integrate with your tools
- [ ] [Set up project integrations](https://gitlab.rlp.net/proj-wise2526-video2document/video2document/-/settings/integrations)
## Collaborate with your team
- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
- [ ] [Set auto-merge](https://docs.gitlab.com/user/project/merge_requests/auto_merge/)
## Test and Deploy
Use the built-in continuous integration in GitLab.
- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/)
- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
***
# Editing this README
When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
## Suggestions for a good README
Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
## Name
Choose a self-explaining name for your project.
## Description
Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
## Badges
On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
## Visuals
Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
## Installation
Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
Follow the steps below to install Video2Document (v2d):
## Usage
Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
### 1. Install Node.js
## Support
Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
Download and install Node.js from [https://nodejs.org/en](https://nodejs.org/en)
## Roadmap
If you have ideas for releases in the future, it is a good idea to list them in the README.
### 2. Clone the Repository
## Contributing
State if you are open to contributions and what your requirements are for accepting them.
Clone the repository using Git:
For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
```bash
git clone https://gitlab.rlp.net/proj-wise2526-video2document/video2document.git
```
You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
Alternatively, you can download the ZIP file and extract it manually.
## Authors and acknowledgment
Show your appreciation to those who have contributed to the project.
### 3. Start the Program
## License
For open source projects, say how it is licensed.
The start scripts automatically install dependencies and launch the program. Choose the appropriate method for your operating system:
**Windows:**
```bash
start.bat
```
**Linux:**
```bash
./start.sh
```
**macOS:**
```bash
./start.sh
```
#### Alternative: Manual Installation and Start
If the start scripts don't work, you can manually install dependencies and start the program:
```bash
cd video2document
npm install
npm start
```
### 5. Install FFmpeg
Make sure that **ffmpeg** is installed on your system, as it may be required for video processing.
---
**Installation complete!** You're now ready to use Video2Document.
###General Despription
## Project Overview
V2D (Video to Document Framework) is a student project developed to convert video and audio content into structured, readable documents using AI-based text processing. The tool is designed to help users automatically generate documents such as meeting reports, summaries or structured texts from recorded videos or audio files.
The main problem V2D addresses is the time-consuming manual effort required to listen to recordings and write documents afterwards. By automating transcription, structuring and document generation, the tool improves efficiency and usability for students, teams and small organizations.
The project was created as part of a university software engineering course and is developed using agile methods (Scrum). It focuses on modular design, usability and extensibility, allowing new document types and features to be added easily.
### Used Packages and Dependencies
This project uses several Node.js packages to handle video processing, AI-based document generation, backend communication, and the desktop user interface. Below is an overview of the most important dependencies and their purpose.
##Core Dependencies:
Electron:
Used to build the desktop application. It allows the project to run as a cross-platform GUI application using web technologies.
Express:
Acts as a lightweight backend server that handles internal API requests and communication between different parts of the application.
Axios:
Used for making HTTP requests, for example when communicating with external APIs such as AI services.
dotenv:
Used to securely load API keys and other sensitive configuration values from environment variables instead of hardcoding them in the source code.
@google/genai:
Provides access to Googles Generative AI models. This package is used to generate structured documents from transcribed text based on configurable prompts.
ffmpeg-static:
Provides a static FFmpeg binary so that video and audio processing works without requiring FFmpeg to be installed separately on the system.
fluent-ffmpeg:
Used together with FFmpeg to process video and audio files, for example extracting audio tracks from uploaded videos.
puppeteer:
Used to render and process HTML content programmatically. This is helpful for document previews and automated content generation.
html-to-docx:
Converts generated HTML documents into downloadable DOCX files, which are provided to the user as the final output.
mocha:
A testing framework used to run unit tests and ensure that core functionalities work as expected.
##Development Dependencies:
TypeScript:
Used to add static typing to the project, improving code quality, readability, and maintainability.
ts-node:
Allows running TypeScript files directly without manually compiling them first.
@types/node:
Provides TypeScript type definitions for Node.js APIs.
@types/fluent-ffmpeg:
Type definitions for fluent-ffmpeg to improve development experience and error checking.
@types/cli-progress:
Provides type support for progress bar functionality used during processing tasks.
###Why These Packages Are Needed
Together, these packages enable:
*Processing video and audio files
*Communicating with AI models for document generation
*Secure handling of API keys
*Generating structured documents (DOCX)
*Providing a user-friendly desktop interface
*Ensuring code quality through testing
###API Keys and Configuration
The V2D Video to Document tool uses external AI and media processing services to convert video and audio content into structured documents.
To access these services, several API keys are required. For security reasons, API keys are not stored in the repository and must be provided via environment variables.
##Supported API Keys
The project currently supports the following API keys. Depending on the configuration and selected provider, one or more of these keys may be used.
Google Gemini API
Environment variable: GOOGLE_API_KEY
Usage:
Used for AI-based document generation. The Large Language Model processes transcripts and creates structured documents such as meeting reports.
OpenAI (ChatGPT)
Environment variable: OPENAI_API_KEY
Usage:
Alternative AI provider for text processing and document generation.
AssemblyAI
Environment variable: ASSEMBLYAI_API_KEY
Usage:
Speech-to-text processing for audio and video files.
Saya
Environment variable: SAYA_API_KEY
Usage:
Additional or experimental AI provider that can be integrated into the document generation pipeline.
##How to Set API Keys
API keys must be configured as environment variables before starting the application.
Linux / macOS
export GOOGLE_API_KEY="your_api_key_here"
export OPENAI_API_KEY="your_api_key_here"
export ASSEMBLYAI_API_KEY="your_api_key_here"
export SAYA_API_KEY="your_api_key_here"
Windows (PowerShell)
setx GOOGLE_API_KEY "your_api_key_here"
setx OPENAI_API_KEY "your_api_key_here"
setx ASSEMBLYAI_API_KEY "your_api_key_here"
setx SAYA_API_KEY "your_api_key_here"
Alternatively, for local development, a .env file can be used:
GOOGLE_API_KEY=your_api_key_here
OPENAI_API_KEY=your_api_key_here
ASSEMBLYAI_API_KEY=your_api_key_here
SAYA_API_KEY=your_api_key_here
⚠️ Important:
The .env file must not be committed to the repository and should be listed in .gitignore.
Security Notes:
*API keys are injected at runtime
*No secrets are stored in the source code
*Prevents accidental exposure of sensitive data
*Supports secure collaboration in GitLab and CI/CD environments
*Follows best practices for secret management
###End-to-End User Guide (Video → Final Document)
This section describes how a user can create a structured document from a video using the V2D Video to Document tool.
Start the Application:
Ensure all required API keys are configured as environment variables.
Install dependencies:
npm install
Start the application:
npm start
The Electron-based GUI will open.
#Upload a Video File:
In the application interface, select Upload Video.
Choose a supported video file (e.g. .mp4, .mov).
The video is loaded into the system for processing.
#Audio Extraction:
The application automatically extracts audio from the uploaded video.
This is handled internally using FFmpeg.
No user interaction is required for this step.
#Speech-to-Text Transcription:
The extracted audio is sent to the speech-to-text service.
The transcription process converts spoken content into text.
The generated transcript is stored internally and used for further processing.
#Select Document Type:
The user selects a document type (e.g. Meeting Report).
Each document type is based on a predefined prompt template.
The selected template defines the structure and style of the final document.
#Document Generation:
The transcript and selected prompt are sent to the AI service.
The AI model processes the input and generates a structured document.
The output is formatted in Markdown.
#Document Preview:
The generated document is displayed in the application preview.
Users can review the content before exporting.
No manual editing is required, but validation is possible.
#Export the Final Document:
The user exports the document in the desired format.
#Supported formats include:
Markdown (.md)
Word (.docx)
The document is saved locally.
#Completion:
The final document is now ready for use.
The user can repeat the process with another video if needed.
###Resources
This section lists the main technologies, libraries, and external resources used in the V2D (Video to Document) project. These resources are required to understand, run, and further develop the application.
##Project Dependencies
The following packages and tools are used in this project (as defined in package.json):
Application & Backend
Node.js JavaScript runtime environment used for backend processing
Electron Framework for building the desktop application
Express Backend web framework for handling requests and internal APIs
AI & API Communication
@google/genai Used for AI-based document generation
Axios HTTP client for communicating with external APIs (LLMs)
Video & Audio Processing
ffmpeg-static Extracts audio from uploaded video files
fluent-ffmpeg Controls FFmpeg operations programmatically
Document Generation & Preview
html-to-docx Converts structured content into Word documents
Puppeteer Renders HTML content for document preview and processing
Configuration & Security
dotenv Loads API keys securely from environment variables
Testing & Development
Mocha Unit testing framework
TypeScript Improves code quality and type safety
These dependencies enable the complete end-to-end workflow from video input to structured document output.
##Relevant Repositories
V2D Main Repository:
https://gitlab.rlp.net/proj-wise2526-video2document/video2document
This repository contains the full source code, configuration files, and documentation for the V2D project.
Downloads & External Resources
The following tools and documentation may be required to run or understand the project:
Node.js: https://nodejs.org
Electron Documentation: https://www.electronjs.org/docs
FFmpeg: https://ffmpeg.org
Google Generative AI: https://ai.google.dev
Puppeteer: https://pptr.dev
## Project status
If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
-116
View File
@@ -1,116 +0,0 @@
# Documenation of our Program
## Table of Contents
1. [How to run the Software](#how-to-run-the-software)
2. [How it works](#how-it-works)
3. [Modules](#modules)
3. [IPC](#ipc)
## How to run the Software
If you read the readme file, you will see the basic setup command in order to run the program.
You will need nodejs, the newer the better.
The software is tested with `nodejs-19`, `nodejs-20`, `nodejs-22` and `nodejs-24`.
These versions are confirmed to work with our software, but prior versions may work aswell.
To get nodejs, simply go to their [website](https://nodejs.org/en/download) and download whatever version you want and install it.
Afterward go into the directory of our program, and run the command `npm i`, this will install all the necessary libraries.
Next up you need to set up the .env file.
The file must contain your keys for the modules you want to use.
The .env file looks like this:
```
ASSEMBLYAI_API_KEY=wefhjhjakeghjkahejkghjkaegh
GOOGLE_API_KEY=wefhjhjakeghjkahejkghjkaegh
SAIA_API_KEY=wefhjhjakeghjkahejkghjkaegh
```
Note that if you write your module in the same format we did, then you will only need to supply the api keys to the individual services you will actually use.
If you dont want to use Assembly AI, you can for example just leave this row out of your .env, and the program will just work fine.
Only issue will be that it will throw an error if you do run the Assembly AI module anyways.
Once that is done, you can run the command `npm start` to actually start the program.
Alternatively you can double click the start.bat if you are on Windows for example.
## How it works
Our software is fully modular, this means, every part can easily be edited, replaced, removed or added without needing to make many adjustments in the code.
The modules can be found under `./services/modules`
The Structure is as follows:
Inside of `modules` are folders named after the general thing the module does.
For example, `transcription-remote`, this folder contains all the modules that do transcription on a remote service, such as assembly-ai for example.
Inside of these folders we put our modules.
The name of the folder and the module dont matter, as long as the structure is kept, and the module filename ends with .js, it will work.
The program iterates through all of the folders within `./services/modules`, and then iterates over each `.js` file within each of these folders, and then loads them into a specific map called `mapFunctions`.
This map is available ANYWHERE in the backend code, even within a module, which means, you can call a module, from within a module, from within a module, from within yet another module.
## Modules
Building a new module is super easy, any idiot can get it done.
All you need to do is follow the previously mentioned structure.
When you have created your module file, the `.js` file, you simply copy paste this code snippet into it.
```js
module.exports = {
name:"example", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type:"example-type", // value used to differentiate each module to order them in the UI
displayname:"Example", // The displayname used within the UI
async function(randomParameter){
// Here we put a simple console.log to show how the system works
// This function will be called from the @startup.js function in the utility folder
console.log(`\n------------\nThis is the example function called by the ${randomParameter} function\n------------\n`);
}
}
```
If by this point, you cared enough to actually look at the code and the modules and so on, you might have spotted a file in `./services/modules/utility` called `example.js`.
This is a template file that you can just copy paste and use as a base for your new module.
It has the same exact code as mentioned right above.
Now as for how the code works.
Each module is essentially just a JSON object that is being exported, so that the main process can load it into the `mapFunctions` map.
the required fields are as follows
- name: This field contains the internal name through which it will be called. It HAS TO BE unique.
- type: This field contains the type of the module. Is it an LLM module, transcription module, or whatever.
- displayname: This field contains the Displayname used in the UI.
And lastly the function call.
This function call is what is being called by other functions, it is generally the main entrypoint for a module.
Sure, you can always set custom function names, but this is a general solution that works without having to manage function names.
You can always define custom functions inside your module that you call from the entrypoint function, but it is highly advised just to call the entrypoint function from outside of the module as it prevents headaches by just working as intended.
Note, there are also other module fields for specific module types, such as:
- description: Used by any module that needs to be shown on the UI, such as Transcription and LLM modules.
- audioformat: Used by transcription modules to tell the audio extraction module what audio format to use.
## IPC
Our software is split up into 2 pieces, the main process (Backend) and the frontend.
The frontend is written in Electron, so it is essentially just a website.
This makes it relatively easy to edit the frontend.
But it comes with one downside, which is, the frontend and backend cant just directly communicate, you first need to set up an IPC channel between them.
As for the base functionality, all of this is already done.
The frontend gets a list of all the available LLM and Transcription modules sent by the backend on startup.
The JSON object for this information looks like this:
```json
{
"ai_modules":[
{"name": "Example", "displayname": "Example"}
],
"transcription_modules":[
{"name": "Example", "displayname": "Example"}
]
}
```
The backend needs a specific set of informations from the frontend in order to start the pipeline.
The JSON for that looks like this:
```json
{
"video": {
"module": "extraction-video-to-audio",
"inputVideoPath": "A:\\programing\\@projects\\video2document\\test\\unit\\testvideo.mp4"
},
"transcription": {
"module": "assembly"
},
"document": {
"module": "llm-saia_openai_gpt",
"type": "followup-report",
"outputType": "pdf"
}
}
```
As you can see in this JSON object, each part specifies which module is being used for each step.
The module names are each the name field specified in the module itself.
As for the rest of the fields, they are pretty self explanatory except `document.type`, that is a predefined report type.
This is the minimum required setup for the currently implemented pipeline to work.
You can always add fields to it, but dont remove the ones from above.
-154
View File
@@ -1,154 +0,0 @@
<!DOCTYPE html>
<html lang="de">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Custom Document</title>
<style>
</style>
</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>
</html>
-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

+36 -216
View File
@@ -1,234 +1,54 @@
<!DOCTYPE html>
<html lang="de">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title id="title">Video to document</title>
<link rel="stylesheet" href="style.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/themes/light.css">
</head>
<body>
<div id="h1-wrapper">
<section class="p-menu1">
<nav id="navbar" class="navigation" role="navigation">
<input id="toggle1" type="checkbox" />
<label class="hamburger1" for="toggle1">
<div class="top"></div>
<div class="meat"></div>
<div class="bottom"></div>
</label>
<nav class="menu1">
<button id="customDocBtn" onclick="showCD()">Manage document types</button>
<a href="help_page.html" class="li1">Help</a>
</nav>
</nav>
</section>
<h1 id="h1">Video to document</h1>
<div class="gui-language">
<select name="language_option" id="language_option"></select>
</div>
<div class="mitte" id="mitte">
<div class="flagsBtns" id="flagsBtns">
<select name="ai_type" id="ai_type">
</select>
<select name="language_option" id="language_option">
</select>
</div>
<div class="step-nav">
<div class="step-item active" data-step="1" id="step_nav1">1. Step</div>
<div class="step-item" data-step="2" id="step_nav2">2. Step</div>
<div class="step-item" data-step="3" id="step_nav3">3. Step</div>
<div class="step-item" data-step="4" id="step_nav4">4. Step</div>
<div class="step-item" data-step="5" id="step_nav5">5. Step</div>
<div class="step-item" data-step="6" id="step_nav6">6. Step</div>
<h1 id="h1">Video to document</h1>
<div class="upload-container" id="uploadContainer">
<p id="p1">Drag and drop video file</p>
<div class="file-name" id="fileName">No video chosen</div>
</div>
<div id="middleContainerWrapper" class="middle-container-wrapper">
<button id="prevBtn" class="navBtn" disabled>&larr;</button>
<!-- Visible middle part-->
<div class="mitte" id="mitte">
<!--Costum document section-->
<div class="container" id="cdContainer" style="display:none;">
<h1 id="cd_h1">Manage document types</h1>
<label for="existingDocs" id="cd_existingDocs">Select existing documents (optional):</label>
<!--Drop Down-->
<select name="existingDocs" id="existingDocs">
<option value="newDoc" id="newDoc">-- Create new document --</option>
</select>
<div id="docNameWrapper">
<label for="docName" id="cd_docName">Document name:</label>
<input type="text" id="docName" placeholder="Enter the document name here">
</div>
<label for="prompt" id="cd_promt">Your prompt:</label>
<textarea id="prompt" placeholder="Type the prompt for your document here..."></textarea>
<div class="buttons">
<button id="goBackBtn">Return</button>
<button id="deleteBtn">Delete document</button>
<button id="generateBtn">Save document</button>
</div>
<div id="result"></div>
</div>
<!-- Here starts code from step 1-->
<div class="step" id="step1">
<h2 class="h2">Upload your video here:</h2>
<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>
<!-- Here starts code from step 2-->
<div class="step" id="step2" style="display:none;">
<h2 class="h2">Choose your preferences:</h2>
<div class="KI-wrapper">
<label id="labelKI">Select ki:</label>
<select name="ai_type" id="ai_type"></select>
</div>
<div class="transcript-wrap">
<label id="labelTranscription">Select transcription:</label>
<select name="transkript_type" id="transkript_type"></select>
</div>
<div class="type-wrapper">
<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="txt">.txt</option>
</select>
</div>
<div class="language-wrapper">
<label id="labelLanguage">Select language:</label>
<select name="document_language_option" id="document_language_option">
</select>
</div>
</div>
<!-- Here starts code from step 3-->
<!-- Hover Effekt für Dokumentenvorschau, Fragezeichen hinter Text, drüber hoven zeigt Beispieldokument -->
<div class="step" id="step3" style="display:none;">
<div class="checkbox-group">
<h2 class="h2">Choose prefered document style:</h2>
<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>
<div class="figure2">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover2" src="flags/india-flag-png-large.png">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatSummary2" value="result-protocol">
<label id="label_summary" for="docFormatSummary">Resultprotocol</label>
<div class="figure3">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover3" src="flags/united-kingdom-flag-png-large.jpg">
</div>
</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>
<div class="figure4">
<img class="img-icon" src="icons/question-mark-button-icon--free-clip-art-30.png">
<img class="img-hover4" src="flags/germany-flag-png-large.jpg">
</div>
</div>
<div class="checkbox-container">
<input type="checkbox" name="docFormat" id="docFormatCustom" value="custom">
<select name="customDocumentTypes" id="customDocumentTypes">
</select>
</div>
</div>
</div>
<!-- Here starts code from step 4-->
<div class="step" id="step4" style="display:none;">
<h2 class="h2">Click to submit:</h2>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()" disabled>Submit</button>
<div class="testy" id="testy">
<div class="box2" id="box1">
</div>
<p id="box1_p1">---Starting---</p>
<div class="box2" id="box2">
</div>
<p id="box2_p2">---Transkribing---</p>
<div class="box2" id="box3">
</div>
<p id="box3_p3">---Document creation---</p>
<div class="box2" id="box4">
</div>
</div>
</div>
<!-- Here starts code from step 5-->
<div class="step" id="step5" style="display:none;">
<h2 class="h2">Change names of the speakers:</h2>
<div class="speakerView" id="speakerView">
<label id="labelSpeaker">Select Speaker:</label>
<select name="cur_speaker" id="cur_speaker">
</select>
</div>
<div class="speakerAudio" id="speakerAutio">
<label id="labelSpeakerAudio">Selected Speaker:</label>
<audio controls id="speakerAudioViewer">
Currently there is no audio file here.
</audio>
</div>
<div class="speakerWrite" id="speakerWrite">
<label id="labelSpeakerWriter">Write name:</label>
<input type="text" id="newSpeaker">
</div>
<div class="speakerButton-group">
<button id="speakerLocker" onclick="rewriteSpeakerName()">Rename Speaker</button>
<button id="speakerResender" onclick="sendSpeakerPackages()">Rewrite document</button>
</div>
</div>
<!-- Here starts code from step 6-->
<div class="step" id="step6" style="display:none;">
<h2 class="h2">Klick to download your document:</h2>
<button class="download-btn" id="downloadButton" onclick="fileDownload()">Download</button>
</div>
</div>
<button id="nextBtn" class="navBtn">&rarr;</button>
<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">
<label id="label_format" for="docFormat">Meeting report</label>
</div>
<script src="https://cdn.jsdelivr.net/npm/lc-select@1.3.0/lc_select.min.js"></script>
<script src="languages.js"></script>
<script src="script.js"></script>
<script src="./renderer.js"></script>
<div class="checkbox-container">
<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()">Submit</button>
<div class="progressbar">
<div class="progress_fill"></div>
<span class="progress_text">0%</span>
</div>
</div>
<script src="languages.js"></script>
<script src="script.js"></script>
<script src="./renderer.js"></script>
</body>
</html>
+3 -104
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",
@@ -12,43 +8,9 @@ var languageOptions = {
"checkbox_group": "Choose prefered document style:",
"label_format": "Meeting report",
"label_summary": "Summary with timestamps",
"submitButton": "Submit",
"step_nav1": "Step 1",
"step_nav2": "Step 2",
"step_nav3": "Step 3",
"step_nav4": "Step 4",
"step_nav5": "Step 5",
"step_nav6": "Step 6",
"h2": "Upload your video here:",
"labelSpeaker": "Select Speaker:",
"labelSpeakerAudio": "Selected Speaker:",
"labelSpeakerWriter": "Write name:",
"speakerLocker": "Rename speaker",
"speakerResender": "Rewrite document",
"downloadButton": "Download",
"box1_p1": "---Starting---",
"box2_p2": "---Transkribing---",
"box3_p3": "---Document creation---",
"labelType": "Select document type:",
"customDocBtn": "Manage document types",
"cd_h1": "Manage document types",
"cd_existingDocs": "Select existing documents (optional):",
"cd_docName": "Document name",
"docName": "Enter the document name here",
"cd_promt": "Your prompt:",
"prompt": "Type the prompt for your document here...",
"goBackBtn": "Return",
"deleteBtn": "Delete document",
"generateBtn": "Save document",
"newDoc": "-- Create new document --"
"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",
@@ -57,42 +19,9 @@ var languageOptions = {
"checkbox_group": "Bevorzugte Dokumentvarianten:",
"label_format": "Meeting Bericht",
"label_summary": "Zusammenfassung mit Zeitstempeln",
"submitButton": "Absenden",
"step_nav1": "Schritt 1",
"step_nav2": "Schritt 2",
"step_nav3": "Schritt 3",
"step_nav4": "Schritt 4",
"step_nav5": "Schritt 5",
"step_nav6": "Schritt 6",
"h2": "Uploade dein Video hier:",
"labelSpeaker": "Wähle Sprecher:",
"labelSpeakerAudio": "Ausgewählter Sprecher:",
"labelSpeakerWriter": "Schreib Namen:",
"speakerLocker": "Ersetze Namen",
"speakerResender": "Überschreibe Dokument",
"downloadButton": "Download",
"box1_p1": "---Startet---",
"box2_p2": "---Transkribing---",
"box3_p3": "---Dokument kreieren---",
"labelType": "Wähle Dokumenttype:",
"customDocBtn": "Dokumenttypen verwalten",
"cd_h1": "Dokumenttypen verwalten",
"cd_existingDocs": "Vorhandene Dokumente auswählen (optional):",
"cd_docName": "Dokument Name",
"docName": "Geben Sie hier den Dokumentnamen ein",
"cd_promt": "Ihr Prompt:",
"prompt": "Geben Sie hier die Eingabeaufforderung für Ihr Dokument ein...",
"goBackBtn": "Zurück",
"deleteBtn": "Lösche Dokument",
"generateBtn": "Speicher Dokument",
"newDoc": "-- Neues Dokument erstellen --"
"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",
@@ -101,37 +30,7 @@ var languageOptions = {
"checkbox_group": "पसंदीदा दस्तावेज़ शैली चुनें:",
"label_format": "बैठक रिपोर्ट",
"label_summary": "टाइमस्टैम्प के साथ सारांश",
"submitButton": "जमा करना",
"step_nav1": "स्टेप 1",
"step_nav2": "स्टेप 2",
"step_nav3": "स्टेप 3",
"step_nav4": "स्टेप 4",
"step_nav5": "स्टेप 5",
"step_nav6": "स्टेप 6",
"h2": "अपना वीडियो यहां अपलोड करें:",
"labelSpeaker": "स्पीकर चुनें:",
"labelSpeakerAudio": "चयनित वक्ता:",
"labelSpeakerWriter": "नाम लिखें:",
"speakerLocker": "स्पीकर का नाम बदलें",
"speakerResender": "दस्तावेज़ पुनः लिखें",
"downloadButton": "डाउनलोड करना",
"box1_p1": "---प्रारंभ---",
"box2_p2": "---प्रतिलेखन---",
"box3_p3": "---दस्तावेज़ निर्माण---",
"labelType": "दस्तावेज़ प्रकार चुनें:",
"customDocBtn": "दस्तावेज़ प्रकार प्रबंधित करें",
"cd_h1": "दस्तावेज़ प्रकार प्रबंधित करें",
"cd_existingDocs": "मौजूदा दस्तावेज़ों का चयन करें (वैकल्पिक):",
"cd_docName": "दस्तावेज़ का नाम",
"docName": "यहां दस्तावेज़ का नाम दर्ज करें",
"cd_promt": "आपका संकेत:",
"prompt": "अपने दस्तावेज़ के लिए प्रॉम्प्ट यहां टाइप करें...",
"goBackBtn": "वापस करना",
"deleteBtn": "दस्तावेज़ हटाएँ",
"generateBtn": "दस्तावेज़ सहेजें",
"newDoc": "-- नया दस्तावेज़ बनाएँ --"
"submitButton": "जमा करना"
}
};
+3 -36
View File
@@ -4,45 +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) }
getFilePath: (file) => {return webUtils.getPathForFile(file)}
})
contextBridge.exposeInMainWorld("onStartup", {
getModuleNames: () => ipcRenderer.invoke('get-module-names')
})
contextBridge.exposeInMainWorld('electron', {
progress: (callback) => ipcRenderer.on('progress', callback)
})
contextBridge.exposeInMainWorld('audios', {
speakerAudios: (callback) => ipcRenderer.on('speakerAudios', callback)
})
contextBridge.exposeInMainWorld("submitSpeaker", {
speaker_submit: (speaker_names) => { ipcRenderer.send("speaker_submit", speaker_names) }
})
contextBridge.exposeInMainWorld("download", {
file_download: () => { ipcRenderer.send("file_download") }
})
//documenttypes
contextBridge.exposeInMainWorld('api', {
getTxtFiles: () => ipcRenderer.invoke('get-txt-files'),
saveTxtFile: (name, content) =>
ipcRenderer.invoke('save-txt-file', name, content),
readTxtFile: (fileName) =>
ipcRenderer.invoke('read-txt-file', fileName),
deleteTxtFile: (fileName) =>
ipcRenderer.invoke('delete-txt-file', fileName)
});
ipcRenderer.on("error", (event, err) => { alert(err) })
} catch (error) {
console.log("Error in preload.js");
}
+26 -376
View File
@@ -1,391 +1,41 @@
/*
Listeners for the program setup and changes
*/
//Listener for when the gui has been loaded so it can fill the dop down menus in step 2 and the language options
window.addEventListener('load', async (e) => {
try {
loadLanguageOptions();
const value = await window.onStartup.getModuleNames();
loadAiOptions(value.ai_modules);
loadTranscriptionOptions(value.transcription_modules);
} catch (error) {
console.log("Error in the window listener load in the renderer.js \n");
console.log(error);
}
});
//Listener if the language of the displayed text's in the gui should be changed
language_option.addEventListener('change', (e) => {
try {
const select = document.getElementById('language_option');
changeLanguage(select.value);
} catch (error) {
console.log("Error in the language_option change listener in the renderer.js");
console.log(error);
}
});
stepButtons.forEach(btn => {
btn.addEventListener("click", () => {
uploadContainer.addEventListener("dragover", (e) =>{
try {
const step = parseInt(btn.dataset.step);
showStep(step);
e.stopPropagation();
e.preventDefault();
} catch (error) {
console.log("Error in renderer.js dragover listener function")
}
});
});
//Listener if the button to change the current step to the previus one is pressed
prevBtn.addEventListener("click", () => {
try {
if (currentStep > 1) showStep(currentStep - 1);
} catch (error) {
}
});
//Listener if the button to change the current step to the next one is pressed
nextBtn.addEventListener("click", () => {
try {
if (currentStep < totalSteps) showStep(currentStep + 1);
} catch (error) {
}
});
/*
Listeners for Step 1
*/
//Listener if a file has been draged over the drop down field
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))) {
const files1 = e.dataTransfer.files;
handleFiles(files1);
} else {
alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
}
try {
e.stopPropagation()
e.preventDefault()
const files = e.dataTransfer.files
const filePath = window.explorer.onFileDrop(files[0])
var holdy = filePath + "";
if(holdy.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
console.log(filePath)
} catch (error) {
console.log("Error in renderer.js with the listerner for the drop function");
console.log(error);
}
const files1 = e.dataTransfer.files;
handleFiles(files1);
}
} catch (error) {
console.log("Error in renderer.js with the listerner for the drop function");
}
})
//listener for the file explorer search when something got selected
videoUpload.addEventListener("change", () => {
try {
if (videoUpload.files.length > 0) {
const file = videoUpload.files;
handleFiles(file);
}
} catch (error) {
console.log(error);
}
window.addEventListener('load', (e) => {
console.log("test");
loadLanguageOptions();
});
//listener for the file explorer search
manualUploadBtn.addEventListener('click', () => {
try {
videoUpload.click();
} catch (error) {
console.log("Error in manualBtn EventListener click");
console.log(error);
}
language_option.addEventListener('change', (e)=>{
const select = document.getElementById('language_option');
console.log(select.value);
changeLanguage(select.value);
});
/*
Listeners for Step 2
*/
/*
Listeners for Step 3
*/
window.api.getTxtFiles().then(files => {
var menu = document.getElementById('customDocumentTypes');
var l = document.getElementById('customDocumentTypes').options.length - 1;
for (i = l; i >= 0; i--) {
menu.remove(i);
}
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
menu.appendChild(option);
});
});
//Checkboxlistener so that only one can be selected at a time
docFormat.addEventListener("change", (e) => {
try {
if (docFormat.checked) {
docFormatSummary1.checked = false;
docFormatSummary2.checked = false;
docFormatSummary3.checked = false;
docFormatCustom.checked = false;
}
} catch (error) {
}
});
docFormatSummary1.addEventListener("change", (e) => {
try {
if (docFormatSummary1.checked) {
docFormat.checked = false;
docFormatSummary2.checked = false;
docFormatSummary3.checked = false;
docFormatCustom.checked = false;
}
} catch (error) {
}
});
docFormatSummary2.addEventListener("change", (e) => {
try {
if (docFormatSummary2.checked) {
docFormatSummary1.checked = false;
docFormat.checked = false;
docFormatSummary3.checked = false;
docFormatCustom.checked = false;
}
} catch (error) {
}
});
docFormatSummary3.addEventListener("change", (e) => {
try {
if (docFormatSummary3.checked) {
docFormatSummary1.checked = false;
docFormatSummary2.checked = false;
docFormat.checked = false;
docFormatCustom.checked = false;
}
} catch (error) {
}
});
docFormatCustom.addEventListener("change", (e) => {
try {
if (docFormatCustom.checked) {
docFormatSummary1.checked = false;
docFormatSummary2.checked = false;
docFormatSummary3.checked = false;
docFormat.checked = false;
}
} catch (error) {
}
});
/*
Listeners for Step 4
*/
//Functions the the displayed progress in the progressbar can be changed out of the main process
window.electron.progress((event, arg) => {
if (arg.curstep == 1) {
setCircleOne();
} else if (arg.curstep == 2) {
setCircleZwo();
} else if (arg.curstep == 3) {
setCircleThree();
} else if (arg.curstep == 4) {
setCircleFour();
}
});
function setCircleOne() {
try {
if (document.getElementById("box1").style.backgroundColor == "green") {
document.getElementById("box1").style.backgroundColor = "red";
} else {
document.getElementById("box1").style.backgroundColor = "green";
}
} catch (error) {
}
};
function setCircleZwo() {
try {
if (document.getElementById("box2").style.backgroundColor == "green") {
document.getElementById("box2").style.backgroundColor = "red";
} else {
document.getElementById("box2").style.backgroundColor = "green";
}
} catch (error) {
}
};
function setCircleThree() {
try {
if (document.getElementById("box3").style.backgroundColor == "green") {
document.getElementById("box3").style.backgroundColor = "red";
} else {
document.getElementById("box3").style.backgroundColor = "green";
}
} catch (error) {
}
};
function setCircleFour() {
try {
if (document.getElementById("box4").style.backgroundColor == "green") {
document.getElementById("box4").style.backgroundColor = "red";
} else {
document.getElementById("box4").style.backgroundColor = "green";
}
} catch (error) {
}
};
/*
Listeners for Step 5
*/
//Speaker change listener
cur_speaker.addEventListener("change", (e) => {
try {
document.getElementById("speakerAudioViewer").src = speakerAudios[document.getElementById("cur_speaker").value].src;
} catch (error) {
}
});
//Function so the main process can give the gui a json with the speakers and their audio
window.audios.speakerAudios((event, arg) => {
loadSpeakerOptions(arg);
setSpeakerAudiosValue(arg);
});
/*
Listeners for the costum documents section
*/
goBackBtn.addEventListener("click", () => {
showCD();
});
// dokumente speichern
generateBtn.addEventListener("click", () => {
const name = docName.value.trim();
const content = document.getElementById("prompt").value.trim();
if (!name || !content) {
result.textContent = "Bitte Dokumentname und Prompt ausfüllen.";
console.log(name + " " + content);
setTimeout(() => {
result.textContent = "";
}, 3000);
return;
}
window.api.saveTxtFile(name, content).then();
result.textContent = "Dokument erfolgreich gespeichert!";
setTimeout(() => {
result.textContent = "";
}, 3000);
reloadDocuments();
});
// dokumente löschen
deleteBtn.addEventListener("click", () => {
const name = docName.value.trim();
if (!name) {
result.textContent = "Bitte Dokumentname angeben.";
setTimeout(() => {
result.textContent = "";
}, 3000);
return;
}
const confirmDelete = confirm(
`Möchtest du das Dokument "${name}" wirklich löschen?`
);
if (!confirmDelete) return;
window.api.deleteTxtFile(name).then((success) => {
if (success) {
result.textContent = "Dokument erfolgreich gelöscht!";
reloadDocuments();
existingDocs.value = "newDoc";
existingDocs.dispatchEvent(new Event("change"));
} else {
result.textContent = "Dokument konnte nicht gelöscht werden.";
}
setTimeout(() => {
result.textContent = "";
}, 3000);
});
});
//function to load existingDoc options to the drop down list
window.api.getTxtFiles().then(files => {
reloadDocuments();
});
//content anzeigen
existingDocs.addEventListener("change", async () => {
const existingDocsed = existingDocs.value;
const exampleText = "";
if (existingDocsed === "newDoc") {
docNameWrapper.classList.remove("hidden");
docName.value = "";
prompt.value = exampleText;
return;
}
docNameWrapper.classList.add("hidden");
const content = await window.api.readTxtFile(existingDocsed);
prompt.value = content;
docName.value = existingDocsed.replace(".txt", "");
});
+63 -433
View File
@@ -1,117 +1,69 @@
let currentVideoPath = null;
/*
Functions used in the setup or affect most of the gui
*/
var showCDValue = 0;
function showCD() {
if(showCDValue == 0){
document.getElementById('cdContainer').style.display = "block";
document.getElementById('step1').style.display ="none";
document.getElementById('step2').style.display ="none";
document.getElementById('step3').style.display ="none";
document.getElementById('step4').style.display ="none";
document.getElementById('step5').style.display ="none";
document.getElementById('step6').style.display ="none";
showCDValue = 1;
} else {
currentStep = 1;
showCDValue = 0;
document.getElementById('cdContainer').style.display = "none";
showStep(1);
//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;
checkboxes.forEach(function(checkbox){
if(checkbox.checked){
isChecked = true;
}
});
if(isChecked){
//Code to submit the video
var pathTest = window.electronAPI.getFilePath(videoUpload.files[0]);
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)
}
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
}
//language changing feature => changes the language of every displayed text
//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('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;
document.getElementById('step_nav1').textContent = languageOptions[language].step_nav1;
document.getElementById('step_nav2').textContent = languageOptions[language].step_nav2;
document.getElementById('step_nav3').textContent = languageOptions[language].step_nav3;
document.getElementById('step_nav4').textContent = languageOptions[language].step_nav4;
document.getElementById('step_nav5').textContent = languageOptions[language].step_nav5;
document.getElementById('step_nav6').textContent = languageOptions[language].step_nav6;
//document.getElementById('h2').textContent = languageOptions[language].h2;
document.getElementById('labelSpeaker').textContent = languageOptions[language].labelSpeaker;
document.getElementById('labelSpeakerAudio').textContent = languageOptions[language].labelSpeakerAudio;
document.getElementById('labelSpeakerWriter').textContent = languageOptions[language].labelSpeakerWriter;
document.getElementById('speakerLocker').textContent = languageOptions[language].speakerLocker;
document.getElementById('speakerResender').textContent = languageOptions[language].speakerResender;
document.getElementById('downloadButton').textContent = languageOptions[language].downloadButton;
document.getElementById('box1_p1').textContent = languageOptions[language].box1_p1;
document.getElementById('box2_p2').textContent = languageOptions[language].box2_p2;
document.getElementById('box3_p3').textContent = languageOptions[language].box3_p3;
document.getElementById('labelType').textContent = languageOptions[language].labelType;
document.getElementById('customDocBtn').textContent = languageOptions[language].customDocBtn;
document.getElementById('cd_h1').textContent = languageOptions[language].cd_h1;
document.getElementById('cd_existingDocs').textContent = languageOptions[language].cd_existingDocs;
document.getElementById('cd_docName').textContent = languageOptions[language].cd_docName;
document.getElementById('docName').placeholder = languageOptions[language].docName;
document.getElementById('cd_promt').textContent = languageOptions[language].cd_promt;
document.getElementById('prompt').placeholder = languageOptions[language].prompt;
document.getElementById('goBackBtn').textContent = languageOptions[language].goBackBtn;
document.getElementById('deleteBtn').textContent = languageOptions[language].deleteBtn;
document.getElementById('generateBtn').textContent = languageOptions[language].generateBtn;
document.getElementById('newDoc').textContent = languageOptions[language].newDoc;
} catch (error) {
console.log("Error in script.js changeLanguage function");
console.log(error);
}
}
/*
Functions used for the step navigation
*/
//Step-navigation
const steps = document.querySelectorAll(".step");
const stepButtons = document.querySelectorAll(".step-item");
let currentStep = 1;
const totalSteps = steps.length;
function showStep(stepNumber) {
if (stepNumber < 1 || stepNumber > totalSteps) {
console.error("StepNumber out of Bounds", stepNumber);
return;
//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");
}
steps.forEach(step => step.style.display = "none");
document.getElementById("step" + stepNumber).style.display = "flex";
stepButtons.forEach(btn => btn.classList.remove("active"));
document.querySelector(`.step-item[data-step="${stepNumber}"]`).classList.add("active");
const activeBtn = document.querySelector(`.step-item[data-step="${stepNumber}"]`);
if (activeBtn) activeBtn.classList.add("active");
prevBtn.disabled = stepNumber == 1;
nextBtn.disabled = stepNumber === totalSteps;
currentStep = stepNumber;
}
/*
Functions used in Step 1
*/
});
//function to display the file path in the drop down box
function handleFiles(files) {
@@ -119,58 +71,38 @@ function handleFiles(files) {
if (files.length > 0) {
const file = files[0];
if (file.type.startsWith('video/')) {
const filePath = window.explorer.onFileDrop(files[0])
videoUpload.files = files;
fileName.textContent = `Chosen video: ${file.name}`;
currentVideoPath = filePath;
generateThumbnail(filePath);
activateSubmitBtn(true);
}
}
} catch (error) {
console.log("Error in script.js handleFiles function");
console.log(error);
}
}
//Video thumbnail generation. Shows a scene from the selected video file as a preview
function generateThumbnail(path) {
//function to regulate the progress on the progressbar
function updateProgressBar(bar, value){
try {
const videoElement = document.getElementById("previewThumbnail");
while (videoElement.firstChild) videoElement.removeChild(videoElement.firstChild);
videoElement.src = path;
videoElement.type = "video/mov";
videoElement.load();
videoElement.style.maxWidth = 40;
videoElement.style.maxHeight = 40;
videoElement.autoplay = false;
value = Math.round(value);
bar.querySelector(".progress_fill").style.width = `${value}%`;
bar.querySelector(".progress_text").textContent = `${value}%`;
} catch (error) {
console.log("Error in the generateThumbnail function in the script.js file \n");
console.log(error);
console.log("Error in scripts.js updateProgressBar function");
}
}
/*
Functions used in Step 2
*/
//function to load ai options to the drop down list
function loadAiOptions(options) {
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;
for(i = 0; i < options.length; i++){
var opty = options[i];
var namey = "option" + i;
var choice = document.createElement(namey);
choice.textContent = "t";
choice.value = i;
menu.appendChild(choice);
}
} catch (error) {
@@ -179,324 +111,22 @@ 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 data type options to the drop down list
function loadDataTypeOptions(options) {
try {
var menu = document.getElementById('output_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 loadDataTypeOptions");
console.log(error);
}
}
//function to load language options to the drop down list
function loadLanguageOptions() {
function loadLanguageOptions(){
try {
var menu = document.getElementById('language_option');
var menu_doc = document.getElementById('document_language_option');
var object_holdy;
var choice;
var choice2;
var choice ;
object_holdy = Object.keys(languageOptions);
for (i = 0; i < object_holdy.length; i++) {
for(i = 0; i < object_holdy.length; i++){
choice = document.createElement('option');
choice.textContent = object_holdy[i];
choice.value = object_holdy[i];
choice.setAttribute('data-image', languageOptions[object_holdy[i]].flagPath);
choice2 = document.createElement('option');
choice2.textContent = object_holdy[i];
choice2.value = object_holdy[i];
choice2.setAttribute('data-image', languageOptions[object_holdy[i]].flagPath);
menu_doc.appendChild(choice2);
menu.appendChild(choice);
}
new lc_select(document.getElementById('language_option')); //loads the flag images so they get displayed in the gui
new lc_select(document.getElementById('document_language_option'));
} catch (error) {
console.log("Error in script.js loadLanguageOptions function");
console.log(error);
}
}
/*
Functions used in Step 3
*/
/*
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 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))) {
//assembly of the json for the main
var typeCheckbox;
if (document.getElementById("docFormat").checked) typeCheckbox = document.getElementById("docFormat").value;
if (document.getElementById("docFormatSummary1").checked) typeCheckbox = document.getElementById("docFormatSummary1").value;
if (document.getElementById("docFormatSummary2").checked) typeCheckbox = document.getElementById("docFormatSummary2").value;
if (document.getElementById("docFormatSummary3").checked) typeCheckbox = document.getElementById("docFormatSummary3").value;
if (document.getElementById("docFormatCustom").checked) typeCheckbox = document.getElementById("docFormatCustom").value;
document.getElementById("testy").style.visibility = "visible"
document.getElementById("box1").style.backgroundColor = "red";
document.getElementById("box2").style.backgroundColor = "red";
document.getElementById("box3").style.backgroundColor = "red";
document.getElementById("box4").style.backgroundColor = "red";
console.log(selectedCheckboxes);
const outputType = document.getElementById("output_type");
const transcriptionType = document.getElementById("transkript_type");
const aiType = document.getElementById("ai_type");
const docLanguage = document.getElementById("document_language_option");
const sendingPackage = {
"video": {
"module": "extraction-video-to-audio",
"inputVideoPath": pathTest
},
"transcription": {
"module": transcriptionType.value
},
"document": {
"module": aiType.value,
"type": typeCheckbox,
"outputType": outputType.value,
"outputLanguage": docLanguage.value
}
};
console.log(docLanguage.value);
window.submit.submit(sendingPackage)
} else {
alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
}
} else {
//language only english at the moment
alert('Please select at least one document type.');
}
} catch (error) {
console.log("Error in script.js checkBoxes function");
console.log(error);
}
}
//function the the submit button on step 4 can be pressed
function activateSubmitBtn(hasFile) {
try {
document.getElementById("submitButton").disabled = !hasFile;
} catch (error) {
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 hide the progressbar
function deaktivateProgressbar() {
try {
document.getElementById("progressbar").style.visibility = "hidden";
} catch (error) {
console.log(error);
}
}
/*
Functions used in Step 5
*/
//function to load speaker options to the drop down list
function loadSpeakerOptions(options) {
try {
var menu = document.getElementById('cur_speaker');
var l = document.getElementById('cur_speaker').options.length - 1;
for (i = l; i >= 0; i--) {
menu.remove(i);
}
var object_holdy;
var choice;
object_holdy = Object.keys(options);
for (i = 0; i < object_holdy.length; i++) {
choice = document.createElement('option');
choice.textContent = options[object_holdy[i]].name;
choice.value = object_holdy[i];
menu.appendChild(choice);
}
document.getElementById("speakerAudioViewer").src = options.speakerA.src;
} catch (error) {
console.log("Error in script.js loadSpeakerOptions function");
console.log(error);
}
}
//function to load speaker audio file options to the drop down list
function loadSpeakerAudio(option) {
try {
var menu = document.getElementById('speakerAudioViewer');
var aud = document.createElement("source");
aud.src = options;
menu.appendChild(aud);
} catch (error) {
console.log("Error in script.js loadSpeakerAudio function");
console.log(error);
}
}
//Audio value setter
var speakerAudios = {};
var speakerEndValues = {};
function setSpeakerAudiosValue(valy) {
try {
speakerAudios = valy;
speakerRewriten = valy;
document.getElementById("speakerAudioViewer").src = valy.speakerA.src;
} catch (error) {
}
}
//Function to rewrite the speaker name in the json
function rewriteSpeakerName() {
try {
const select = document.getElementById("cur_speaker");
const newName = document.getElementById("newSpeaker").value.trim();
if (!newName) {
alert("Please enter a new speaker name");
return;
}
const selectedIndex = select.selectedIndex;
const selectedValue = select.value;
// Update speakerAudios data
speakerAudios[selectedValue].name = newName;
// Update the specific option text and keep value
select.options[selectedIndex].text = newName;
select.options[selectedIndex].value = selectedValue;
// Keep it selected
select.selectedIndex = selectedIndex;
console.log("Speaker renamed:", newName);
} catch (error) {
console.log("Error renaming speaker:", error);
}
}
/*
Functions for Step 6
*/
function fileDownload() {
try {
window.download.file_download();
} catch (error) {
console.error("Download failed:", error);
}
}
/*
Functions for the custom document section
*/
//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);
});
});
}
+32 -590
View File
@@ -5,43 +5,21 @@ body {
justify-content: center;
align-items: center;
height: 100vh;
background-color: #f2f3f4;
gap: 10px;
background-color: #555;
gap: 15px;
margin: 0;
}
#h1 {
position: absolute;
left: 50%;
top: 50%;
transform: translate(-50%, -50%);
margin: 0;
z-index: 20;
}
#h1-wrapper {
position: relative;
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
width: 780px;
height: 60px;
background-color: #FFF;
box-shadow: 0px 4px 10px rgba(0, 0, 0, 0.1);
border-radius: 5px;
margin-bottom: 10px;
display: flex;
align-items: center;
}
.upload-container {
background: white;
padding: 40px;
border-radius: 12px;
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.1);
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;
}
@@ -62,35 +40,11 @@ body {
margin-top: 10px;
font-size: 14px;
color: #333;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
#thumbnailContainer {
width: 100%;
display: flex;
justify-content: center;
margin-bottom: 15px;
}
#thumbnailImage {
width: 200px;
height: auto;
border-radius: 10px;
box-shadow: 0px 4px 10px rgba(0, 0, 0, 0.1);
object-fit: cover;
}
#previewThumbnail {
width: 150px;
height: 100px;
/*border: 1px dashed black;*/
}
.custom-btn {
padding: 10px 20px;
margin-top: 10px;
background-color: #007BFF;
color: white;
border: none;
@@ -108,185 +62,28 @@ body {
background-color: #0056b3;
}
#step2 {
gap: 25px;
}
.KI-wrapper {
margin-top: 10px;
}
input[type="file"] {
display: none;
}
.checkbox-container{
margin-top: 8px;
display: flex;
align-items: center;
gap: 5px;
}
.checkbox-group {
--borderColor: #007bfff5;
--borderWidth: .125em;
}
.checkbox-group input[type=checkbox] {
-webkit-appearance: none;
appearance: none;
vertical-align: middle;
background: #fff;
font-size: 1.8em;
border-radius: 0.125em;
display: inline-block;
border: var(--borderWidth) solid var(--borderColor);
width: 1em;
height: 1em;
position: relative;
}
.checkbox-group input[type=checkbox]:before,
.checkbox-group input[type=checkbox]:after {
content: "";
position: absolute;
background: var(--borderColor);
width: calc(var(--borderWidth) * 3);
height: var(--borderWidth);
top: 50%;
left: 10%;
transform-origin: left center;
}
.checkbox-group input[type=checkbox]:before {
transform: rotate(45deg) translate(calc(var(--borderWidth) / -2), calc(var(--borderWidth) / -2)) scaleX(0);
transition: transform 200ms ease-in 200ms;
}
.checkbox-group input[type=checkbox]:after {
width: calc(var(--borderWidth) * 5);
transform: rotate(-45deg) translateY(calc(var(--borderWidth) * 2)) scaleX(0);
transform-origin: left center;
transition: transform 200ms ease-in;
}
.checkbox-group input[type=checkbox]:checked:before {
transform: rotate(45deg) translate(calc(var(--borderWidth) / -2), calc(var(--borderWidth) / -2)) scaleX(1);
transition: transform 200ms ease-in;
}
.checkbox-group input[type=checkbox]:checked:after {
width: calc(var(--borderWidth) * 5);
transform: rotate(-45deg) translateY(calc(var(--borderWidth) * 2)) scaleX(1);
transition: transform 200ms ease-out 200ms;
}
.checkbox-group input[type=checkbox]:focus {
outline: calc(var(--borderWidth) / 2) dotted rgba(0, 0, 0, 0.25);
}
.checkbox-container {
margin-top: 8px;
margin-top: 15px;
margin-bottom: 15px;
display: flex;
justify-items: left;
align-items: center;
gap: 5px;
}
/* Hover effects for all different document options (with placeholders)*/
.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;
z-index: 999;
}
.figure1:hover .img-hover1 {
display: flex;
}
.figure2 {
position: relative;
}
.img-hover2 {
position: absolute;
width: 200px;
height: 200px;
top: 0;
right: 40%;
left: 0;
bottom: 0;
object-fit: contain;
display: none;
transition: opacity .2s;
z-index: 999;
}
.figure2:hover .img-hover2 {
display: flex;
}
.figure3 {
position: relative;
}
.img-hover3 {
position: absolute;
width: 200px;
height: 200px;
top: 0;
right: 40%;
left: 0;
bottom: 0;
object-fit: contain;
display: none;
transition: opacity .2s;
z-index: 999;
}
.figure3:hover .img-hover3 {
display: flex;
}
.figure4 {
position: relative;
}
.img-hover4 {
position: absolute;
width: 200px;
height: 200px;
top: 0;
right: 40%;
left: 0;
bottom: 0;
object-fit: contain;
display: none;
transition: opacity .2s;
z-index: 999;
}
.figure4:hover .img-hover4 {
display: flex;
}
.img-icon {
width: 15px;
height: 15px;
flex-direction: column;
gap: 10px;
align-items: flex-start;
}
.submit-btn {
display: flex;
align-items: center;
justify-content: center;
padding: 10px 20px;
margin: 110px auto 10px auto;
background-color: #007BFF;
color: white;
border: none;
@@ -295,47 +92,40 @@ input[type="file"] {
font-size: 14px;
}
.submit-btn:disabled {
opacity: 0.5;
cursor: not-allowed;
pointer-events: none;
}
.mitte {
background-color: #FFF;
background-color: #f2f3f4;
display: flex;
width: 780px;
height: 550px;
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);
padding-top: 50px;
}
.progressbar {
h1 {
align-content: center;
}
.progressbar{
position: relative;
width: 210px;
height: 30px;
margin: 50px 20px 5px 20px;
background: rgb(42, 46, 78);
border-radius: 5px;
overflow: hidden;
visibility: hidden;
}
.progress_fill {
.progress_fill{
width: 0%;
height: 100%;
background: green;
transition: all 0.2s;
}
.progress_text {
.progress_text{
position: absolute;
top: 50%;
right: 5px;
@@ -343,363 +133,15 @@ input[type="file"] {
color: white;
}
.dropdownMenus {
.flagsBtns {
display: flex;
justify-content: center;
margin-top: 1px;
margin-bottom: 30px;
gap: 170px;
padding: 2px 10px 2px 10px;
justify-content: flex-end;
}
#ai_type,
#transkript_type,
#language_option {
padding: 3px;
}
.labelDiv {
gap: 60px;
display: flex;
justify-content: center;
overflow-wrap: inherit;
padding-bottom: 20px;
margin-top: 40px;
margin-bottom: 10px;
}
/*Step bar*/
.step-nav {
display: flex;
gap: 20px;
justify-content: center;
background: #fff;
padding: 10px 30px;
border-radius: 6px;
box-shadow: 0 4px 10px rgba(0, 0, 0, 0.1);
max-width: 720px;
min-width: 720px;
}
.step-item {
padding: 10px 25px;
border-radius: 8px;
background: #eee;
cursor: pointer;
font-weight: bold;
transition: 0.2s;
}
.step-item.active {
background: #007BFF;
color: white;
}
.step-item:hover {
background: #d9d9d9;
}
/*panels*/
.step {
margin-top: 40px;
margin-bottom: 40px;
;
display: flex;
flex-direction: column;
min-height: 425px;
}
/*Navigation arrows*/
.step-nav-arrows {
display: flex;
justify-content: space-between;
align-items: center;
}
.middle-container-wrapper {
display: flex;
align-items: center;
justify-content: center;
gap: 30px;
width: max-content;
height: auto;
}
.navBtn {
display: flex;
justify-content: center;
padding: 10px 25px;
background-color: #007BFF;
.de_Btn, .eng_Btn, .in_Btn {
padding: 8px 16px;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
font-size: 14px;
}
.navBtn:disabled {
background-color: #ccc;
cursor: not-allowed;
}
.testy {
background-color: #FFF;
display: flex;
width: auto;
flex-direction: row;
align-items: center;
margin-top: 20px;
gap: 10px;
border: 0px;
border-color: black;
border-style: solid;
border-radius: 6px;
visibility: hidden;
}
.box2 {
background-color: red;
width: 40px;
height: 40px;
padding: 5px;
border: 1px solid black;
margin: 5px;
border-radius: 100px;
}
li {
color: #FFF;
}
.p-menu1 {
margin-left: 20px;
z-index: 10;
}
.hamburger1 {
height: 45px;
margin: 0;
padding-top: 8px;
display: grid;
grid-template-rows: repeat(3, 1fr);
justify-items: center;
z-index: 120;
}
.hamburger1 div {
background-color: rgb(61, 61, 61);
position: relative;
width: 40px;
height: 5px;
margin-top: 0;
-webkit-transition: all 0.2s ease-in-out;
transition: all 0.2s ease-in-out;
}
#toggle1 {
display: none;
}
#toggle1:checked+.hamburger1 .top {
-webkit-transform: rotate(-45deg);
transform: rotate(-45deg);
margin-top: 22.5px;
}
#toggle1:checked+.hamburger1 .meat {
-webkit-transform: rotate(45deg);
transform: rotate(45deg);
margin-top: -5px;
}
#toggle1:checked+.hamburger1 .bottom {
-webkit-transform: scale(0);
transform: scale(0);
}
#toggle1:checked~.menu1 {
height: 150px;
width: 300px;
}
/* Menu */
.menu1 {
position: absolute;
top: 55px;
left: 20px;
width: 240px;
border-radius: 5px;
background-color: #1C3B69;
margin: 0;
display: grid;
grid-template-rows: 1fr repeat(4, 0.5fr);
grid-row-gap: 25px;
padding: 0;
list-style: none;
clear: both;
width: auto;
text-align: center;
height: 0px;
overflow: hidden;
transition: height 0.3s ease, width 0.3s ease;
z-index: 9999;
-webkit-transition: all 0.3s ease;
}
#customDocBtn {
border: none;
background-color:#1C3B69;
font: 700 20px 'Oswald', sans-serif;
border-radius: 0%;
}
.menu1 button:first-child {
margin-top: 30px;
}
.menu1 a:last-child {
margin-bottom: 30px;
}
.li1 {
color: #fff;
width: 100%;
margin: 0;
padding: 10px 0px;
font: 700 20px 'Oswald', sans-serif;
text-decoration: none;
}
.li1:hover, #customDocBtn:hover{
background-color: #FFF;
color: rgb(61, 61, 61);
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
-webkit-transition: all 0.3s ease;
transition: all 0.3s ease;
}
#step2,
#step3,
#step5 {
font-size: larger;
}
#step4 {
align-items: center;
}
#step5 {
align-items: flex-start;
}
.button-group {
display: flex;
gap: 12px;
justify-content: center;
margin-top: 10px;
}
.download-btn {
display: flex;
align-items: center;
justify-content: center;
padding: 10px 20px;
margin: 110px auto 10px auto;
background-color: #007BFF;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
font-size: 14px;
}
#speakerLocker,
#speakerResender {
padding: 10px 20px;
margin: 20px auto;
background-color: #007BFF;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
font-size: 14px;
}
.h2 {
font-size: 25px;
}
.speakerView,
.speakerAudio,
.speakerWrite {
margin-top: auto;
margin-bottom: auto;
}
.container {
background: white;
padding: 10px;
margin-top: 30px;
border-radius: 12px;
width: 90%;
max-width: 650px;
}
input[type="text"],
textarea,
select {
width: 80%;
padding: 10px;
margin-top: 5px;
border-radius: 6px;
border: 1px solid #ccc;
font-size: 14px;
}
textarea {
height: 120px;
resize: vertical;
}
.buttons {
display: flex;
justify-content: space-between;
margin-top: 25px;
}
.hidden {
visibility: hidden;
}
button {
padding: 10px 20px;
font-size: 14px;
border: none;
border-radius: 6px;
cursor: pointer;
transition: 0.2s;
background-color: #007BFF;
color: white;
}
button:hover {
background-color: #0056b3;
}
@media (max-width: 500px) {
.buttons {
flex-direction: column;
}
.buttons button {
width: 100%;
margin-top: 10px;
}
}
#result {
margin-top: 20px;
color: #333;
word-break: break-word;
}
+45 -334
View File
@@ -1,368 +1,79 @@
// Last modified: 2024-06-11 12:28:00
// Loading required packages
require("./requires.js");
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();
mapFunctions = new Map()
// Loading the Function Map
var path = `${mainDir}/services/modules`;
var path = `${mainDir}/services/modules`
var folders = fs.readdirSync(path).filter(function (file) {
return fs.statSync(path + "/" + file).isDirectory();
return fs.statSync(path+'/'+file).isDirectory();
});
folders.forEach((element) => {
var commandFiles = fs
.readdirSync(`${path}/${element}`)
.filter((file) => file.endsWith(".js") && !file.startsWith("index"));
for (const file of commandFiles) {
delete require.cache[require.resolve(`${path}/${element}/${file}`)];
const command = require(`${path}/${element}/${file}`);
mapFunctions.set(command.name, command);
}
folders.forEach(element => {
var commandFiles = fs.readdirSync(`${path}/${element}`).filter(file => file.endsWith('.js') && !file.startsWith("index"));
for (const file of commandFiles) {
delete require.cache[require.resolve(`${path}/${element}/${file}`)];
const command = require(`${path}/${element}/${file}`);
mapFunctions.set(command.name, command);
}
});
// The startup information for the project, here you can add stuff that might be nice to see when the app starts
mapFunctions.get("Startup_function").function();
console.log(
"------------------------------------ Status ------------------------------------"
);
mapFunctions.get("Startup_function").function()
console.log("------------------------------------ Status ------------------------------------");
console.log(__dirname);
console.log(platform);
console.log(`The Startup took ${new Date() - start}ms`);
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;
function createWindow() {
mainWindow = new electron.BrowserWindow({
width: 1200,
height: 800,
width: 800,
height: 600,
webPreferences: {
nodeIntegration: false,
contextIsolation: true,
preload: `${mainDir}/electron/main/preload.js`,
},
preload: `${mainDir}/electron/main/preload.js`
}
});
mainWindow.loadFile("./electron/main/index.html");
mainWindow.loadFile('./electron/main/index.html');
}
electron.app.whenReady().then(createWindow);
electron.ipcMain.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)
// })
var globalArgs = {};
var globalFinalHtmlPath = "";
electron.ipcMain.on("file_submit", async (event, args) => {
try {
globalArgs = args;
let curstep = 0;
let totalsteps = 4;
const TEMPLATE_MAP = {
"followup-report": "followup_report.txt",
agenda: "agenda.txt",
"result-protocol": "result_protocol.txt",
"sprint-planning": "sprint_planning_note.txt",
custom: "custom_document.txt",
};
const templateFile = TEMPLATE_MAP[args.document.type];
if (!templateFile) {
throw new Error("Unknown document type: " + args.document.type);
}
console.log(args);
let audiopath = "";
let transcriptpath = "";
console.log("\n\n Running the Video to Audio Extractor");
// This code handles the Video to Audio extraction module call
await mapFunctions
.get("module-handler")
.function(args.video.module, {
inputVideoPath: args.video.inputVideoPath,
outputType: mapFunctions.get(args.transcription.module).audioformat,
})
.then((resp) => {
console.log(resp);
audiopath = resp;
curstep++;
mainWindow.webContents.send("progress", {
curstep: curstep,
totalsteps: totalsteps,
});
})
.catch((err) => {
mainWindow.webContents.send("error", err);
console.log(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);
console.log(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);
console.log(err);
return;
});
console.log("\n\n Running the LLM module");
// TODO implement documentation module
// This code handles the Text to Document processing module call
console.log(
`\n\n Running the LLM for Document Style ${args.document.type}`
);
await mapFunctions
.get("module-handler")
.function(args.document.module, {
inputTranscriptPath: transcriptpath,
documentTypePath: "./storage/documentType/" + templateFile,
language: "en",
})
.then((resp) => {
console.log(resp);
globalFinalHtmlPath = resp;
curstep++;
mainWindow.webContents.send("progress", {
curstep: curstep,
totalsteps: totalsteps,
});
})
.catch((err) => {
mainWindow.webContents.send("error", err);
console.log(err);
return;
});
await mapFunctions
.get("extract-speaker-snippets")
.function({ audioPath: audiopath, jsonPath: transcriptpath })
.then((resp) => {
mainWindow.webContents.send("speakerAudios", resp);
})
.catch((err) => {
mainWindow.webContents.send("error", err);
console.log(err);
return;
});
} catch (error) {
console.log(error);
}
});
electron.ipcMain.on("file_download", async () => {
await mapFunctions
.get("htmlDocumentConverter")
.convert({
inputPath: globalFinalHtmlPath,
format: globalArgs.document.outputType,
showDialog: true,
});
});
electron.ipcMain.on("speaker_submit", async (event, args) => {
console.log("\n\n\nJa also hier kam was an \n\n\n");
console.log(args);
try {
await mapFunctions.get("replace_speaker").function(args);
event.reply("speaker_submit_response", { success: true });
} catch (error) {
console.error("Error:", error);
event.reply("speaker_submit_response", {
success: false,
error: error.message,
});
}
});
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",
},
],
},
};
//gibt Documentfiles an preload zurück
electron.ipcMain.handle("get-txt-files", () => {
const storagePath = `${mainDir}/storage/documentType`;
return fs.readdirSync(storagePath).filter((f) => f.endsWith(".txt"));
});
//speichern neuer document types
electron.ipcMain.handle("save-txt-file", (event, fileName, content) => {
const filePath = `${mainDir}/storage/documentType/${fileName}.txt`;
fs.writeFileSync(filePath, content, "utf8");
return true;
});
//read file content
electron.ipcMain.handle('read-txt-file', (event, fileName) => {
const filePath = `${mainDir}/storage/documentType/${fileName}`;
return fs.readFileSync(filePath, 'utf8');
});
//delete documentfiles
electron.ipcMain.handle('delete-txt-file', (event, fileName) => {
const filePath = `${mainDir}/storage/documentType/${fileName}.txt`;
if (fs.existsSync(filePath)) {
fs.unlinkSync(filePath);
return true;
} else {
return false;
}
});
electron.ipcMain.on("extract", (event, args) => {
mapFunctions.get("extraction-video-to-audio").function(args)
})
+42 -2696
View File
File diff suppressed because it is too large Load Diff
+4 -8
View File
@@ -1,16 +1,12 @@
{
"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",
"express": "^5.1.0",
"ffmpeg-static": "^5.3.0",
"fluent-ffmpeg": "^2.1.3",
"html-to-docx": "^1.8.0",
"mocha": "^11.7.5",
"puppeteer": "^24.33.0"
"ffmpeg-static": "^5.2.0",
"fluent-ffmpeg": "^2.1.3"
},
"devDependencies": {
"@types/cli-progress": "^3.11.6",
@@ -29,7 +25,7 @@
},
"scripts": {
"start": "electron main.js",
"test": "mocha ./test/unit/test.js"
"test": "echo \"Error: no test specified\" && exit 1"
},
"repository": {
"type": "git",
+3
View File
@@ -0,0 +1,3 @@
fastapi
uvicorn
pytest
+1 -8
View File
@@ -6,20 +6,13 @@ platform = process.platform
mainDir = __dirname
fs = require("fs")
readline = require("readline")
puppeteer = require("puppeteer")
htmltodocx = require("html-to-docx")
config = require("./config/config")
ffmpegPath = require('ffmpeg-static');
ffmpeg = require('fluent-ffmpeg');
path = require('path');
// cliProgress = require('cli-progress');
cliProgress = require('cli-progress');
// { app, BrowserWindow, ipcMain, dialog } = require('electron');
electron = require('electron');
axios = require("axios")
require('dotenv').config({path: __dirname + '/.env'});
-47
View File
@@ -1,47 +0,0 @@
const fs = require('fs');
const path = require('path');
//node show-models.js, remember to set SAIA_API_KEY in your environment before running the script
const SAIA_API_KEY = process.env.SAIA_API_KEY;
const SAIA_MODELS_URL = "https://chat-ai.academiccloud.de/v1/models";
// Script to list available models
(async () => {
if (!SAIA_API_KEY) {
console.error("ERROR: SAIA_API_KEY environment variable is not set!");
process.exit(1);
}
console.log("Fetching available models from SAIA...\n");
try {
const response = await fetch(SAIA_MODELS_URL, {
method: "GET",
headers: {
"Authorization": `Bearer ${SAIA_API_KEY}`,
"Accept": "application/json"
}
});
if (!response.ok) {
const text = await response.text();
throw new Error(`SAIA API error (${response.status}): ${text}`);
}
const data = await response.json();
console.log("Available models:");
console.log(JSON.stringify(data, null, 2));
if (data.data && Array.isArray(data.data)) {
console.log("\n\nModel IDs:");
data.data.forEach(model => {
console.log(`- ${model.id}`);
});
}
} catch (error) {
console.error("Error fetching models:", error);
}
})();
@@ -1,102 +0,0 @@
const ffmpeg = require("fluent-ffmpeg");
const ffmpegPath = require("ffmpeg-static");
ffmpeg.setFfmpegPath(ffmpegPath);
module.exports = {
name: "extract-speaker-snippets",
type: "audio",
displayname: "Extract Speaker Snippets",
async function(parameter) {
return new Promise(async (resolve, reject) => {
let output = {}
// console.log("Extract Speaker Snippets\n");
// Pfade
const AUDIO_PATH = parameter.audioPath; // Gesamt-Audio
const JSON_PATH = parameter.jsonPath; // json summary
const OUTPUT_DIR = path.join(__dirname, "/../../../storage/audio/speakerSnippets");
if (!AUDIO_PATH || !JSON_PATH) {
// console.error("no audioPath or jsonPath available");
reject(new Error("no audioPath or jsonPath available"));
return;
}
// Output-Ordner
if (!fs.existsSync(OUTPUT_DIR)) {
fs.mkdirSync(OUTPUT_DIR, { recursive: true });
}
// JSON laden
let entries;
try {
entries = JSON.parse(fs.readFileSync(JSON_PATH, "utf8"));
} catch (err) {
// console.error("JSON reading failed", err);
reject(new Error(err));
return;
}
if (!Array.isArray(entries)) {
// console.error("JSON is not an Array");
reject(new Error("JSON is not an Array"));
return;
}
// Pro Speaker genau EINEN Satz merken
const speakerMap = {};
for (const item of entries) {
if (!speakerMap[item.speaker]) {
speakerMap[item.speaker] = item;
}
}
// FFmpeg pro Speaker ausführen (sequenziell)
for (const speaker of Object.keys(speakerMap)) {
const data = speakerMap[speaker];
// ms → Sekunden
const startSec = data.start / 1000;
const durationSec = (data.end - data.start) / 1000;
if (durationSec <= 0) {
// console.log(`invalid times for Speaker ${speaker}`);
continue;
}
const outFile = path.join(OUTPUT_DIR, `speaker_${speaker}.wav`);
try {
await new Promise((res, rej) => {
ffmpeg(AUDIO_PATH)
.setStartTime(startSec)
.setDuration(durationSec)
.output(outFile)
.on("end", () => {
output[`speaker${speaker}`] = {src: outFile, name: `speaker${speaker}`}
// console.log(`Snippet erstellt: speaker_${speaker}.wav`);
res();
})
.on("error", (err) => {
// console.error(`FFmpeg Fehler (${speaker})`, err.message);
rej(err);
return
})
.run();
});
} catch (error) {
reject(error)
return
}
}
resolve(output)
// console.log("\nAlle Speaker-Snippets erstellt\n");
})
}
};
-197
View File
@@ -1,197 +0,0 @@
const fs = require('fs');
const path = require('path');
const puppeteer = require('puppeteer');
const htmlToDocx = require('html-to-docx');
const { execSync } = require('child_process');
const os = require('os');
const outputDir = path.join(__dirname, "../../../storage/documents");
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
async function showSaveDialog(defaultName, format) {
const platform = os.platform();
if (platform === 'darwin') {
// macOS
const applescript = `
set defaultName to "${defaultName}.${format}"
set theFile to choose file name with prompt "Dokument speichern als:" default name defaultName
POSIX path of theFile
`;
try {
const result = execSync(`osascript -e '${applescript}'`, { encoding: 'utf8' });
return result.trim();
} catch (err) {
if (err.status === 1) return null; // User canceled
throw err;
}
} else if (platform === 'win32') {
const safeName = decodeURIComponent(defaultName);
const powershell = `
Add-Type -AssemblyName System.Windows.Forms;
$dialog = New-Object System.Windows.Forms.SaveFileDialog;
$dialog.FileName = '${safeName}.${format}';
$dialog.Filter = '${format.toUpperCase()} Dateien (*.${format})|*.${format}|Alle Dateien (*.*)|*.*';
$dialog.Title = 'Dokument speichern als';
$result = $dialog.ShowDialog();
if ($result -eq 'OK') { $dialog.FileName }
`;
try {
const result = execSync(
`powershell -NoProfile -Command "${powershell.replace(/\r?\n/g, ' ')}"`,
{ encoding: 'utf8' }
);
return result.trim() || null;
} catch (err) {
if (err.status === 1) return null; // User cancelled
throw new Error("Save dialog failed: " + err.message);
}
} else {
// Linux - zenity oder kdialog
try {
const result = execSync(
`zenity --file-selection --save --confirm-overwrite --filename="${defaultName}.${format}"`,
{ encoding: 'utf8' }
);
return result.trim();
} catch (err) {
try {
const result = execSync(
`kdialog --getsavefilename . "${defaultName}.${format}"`,
{ encoding: 'utf8' }
);
return result.trim();
} catch (err2) {
// Fallback
return path.join(os.homedir(), 'Downloads', `${defaultName}.${format}`);
}
}
}
}
const module_exports = {
name: "htmlDocumentConverter",
type: "converter",
displayname: "HTML Document Converter",
description: "Converts LLM-generated HTML to PDF, DOCX, TXT, or HTML",
/**
* Main conversion function
* @param {Object} options
* @param {string} options.inputPath - Path to the HTML input
* @param {string} options.format - 'pdf' | 'docx' | 'html' | 'txt'
* @param {string} [options.outputName] - Optional output filename (without extension)
* @param {boolean} [options.showDialog] - Show save dialog (default: false in module mode, true in CLI mode)
*/
async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) {
if (!fs.existsSync(inputPath)) {
throw new Error(`Input file not found: ${inputPath}`);
}
const ext = path.extname(inputPath).toLowerCase();
const baseName = outputName || path.basename(inputPath, ext);
let outputFile;
if (showDialog) {
// Zeige nativen Dialog
outputFile = await showSaveDialog(baseName, format);
if (!outputFile) {
console.log('Speichervorgang abgebrochen.');
return null;
}
} else {
// Nutze Standard-Ausgabeverzeichnis
outputFile = path.join(outputDir, `${baseName}.${format.toLowerCase()}`);
}
let htmlContent = fs.readFileSync(inputPath, 'utf8');
// Remove <think> tags if present
htmlContent = htmlContent.replace(/<think>[\s\S]*?<\/think>/gi, '');
switch (format.toLowerCase()) {
case 'html':
fs.writeFileSync(outputFile, htmlContent, 'utf8');
break;
case 'pdf':
await this.htmlToPDF(htmlContent, outputFile);
break;
case 'docx':
await this.htmlToDOCX(htmlContent, outputFile);
break;
case 'txt':
fs.writeFileSync(outputFile, this.htmlToTXT(htmlContent), 'utf8');
break;
default:
throw new Error(`Unsupported format: ${format}`);
}
console.log(`Erfolgreich gespeichert: ${outputFile}`);
return outputFile;
},
// HTML → PDF
async htmlToPDF(html, outputPath) {
const browser = await puppeteer.launch({
headless: true,
args: ['--no-sandbox', '--disable-setuid-sandbox']
});
const page = await browser.newPage();
await page.setContent(html, { waitUntil: 'networkidle0' });
await page.pdf({
path: outputPath,
format: 'A4',
printBackground: true,
margin: { top: '20mm', right: '20mm', bottom: '20mm', left: '20mm' }
});
await browser.close();
},
// HTML → DOCX
async htmlToDOCX(html, outputPath) {
const buffer = await htmlToDocx(html);
fs.writeFileSync(outputPath, buffer);
},
// HTML → TXT (rudimentär)
htmlToTXT(html) {
return html.replace(/<[^>]*>/g, '').replace(/\s+\n/g, '\n').trim();
}
};
module.exports = module_exports;
// CLI usage mit Dialog
if (require.main === module) {
(async () => {
const args = process.argv.slice(2);
if (args.length < 1) {
console.log('Usage: node htmlDocumentConverter.js <input.html> [format]');
console.log('Formats: pdf (default), docx, html, txt');
console.log('');
console.log('Ein nativer "Speichern unter" Dialog wird automatisch geöffnet.');
process.exit(1);
}
const inputPath = args[0];
const format = args[1] || 'pdf';
try {
await module_exports.convert({
inputPath,
format,
showDialog: true
});
} catch (err) {
console.error('Konvertierung fehlgeschlagen:', err.message);
process.exit(1);
}
})();
}
+28 -9
View File
@@ -1,3 +1,4 @@
// Ensure ffmpeg binary is available
if (!ffmpegPath) {
throw new Error('FFmpeg binary not found!');
@@ -24,12 +25,18 @@ module.exports = {
outputType: String // Audio file output format
}
*/
let progressBar = new cliProgress.SingleBar({
format: 'Processing |{bar}| {percentage}% | {timemark}',
barCompleteChar: '\u2588',
barIncompleteChar: '\u2591',
hideCursor: true
});
try {
return new Promise((resolve, reject) => {
this.extractAudioFromVideo(parameter.inputVideoPath, parameter.outputType)
.then((resp) => resolve(resp))
.catch((err) => {reject(err)});
})
// if (meta.url === `file://${process.argv[1]}`) {
this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
.then(() => console.log('Audio extraction successful.'))
.catch((err) => console.error(err));
// }
} catch (error) {
console.log(parameter.outputType);
@@ -46,7 +53,7 @@ module.exports = {
* - Shows CLI progress bar
* - Handles errors gracefully (without errors)
*/
extractAudioFromVideo: async function (videoFilePath, outputType){
extractAudioFromVideo: async function (videoFilePath, progressBar, outputType){
let inputVideoName = path.basename(videoFilePath, path.extname(videoFilePath));
let outputAudioPath = path.join(outputDir, `${inputVideoName}.${outputType}`);
@@ -57,18 +64,30 @@ module.exports = {
// .audioCodec('pcm_s16le')
.audioChannels(1)
.audioFrequency(16000)
// .setFfmpegPath("./ffmpeg.exe")
.on('progress', (progress) => {
if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
if (progress.percent) {
progressBar.update(progress.percent, { timemark: progress.timemark });
}
})
.on('end', () => {
resolve(outputAudioPath);
progressBar.update(100, { timemark: 'done' });
progressBar.stop();
console.log(`Extraction completed: ${outputAudioPath}`);
resolve();
})
.on('error', (err) => {
// console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
progressBar.stop();
console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
reject(err);
})
.save(outputAudioPath);
} catch (error) {
// console.log(error);
console.log();
}
});
}
}
@@ -1,154 +0,0 @@
// Prepare output directory (always storage/transcriptionSummaries under project root)
const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
//Speaker, ALL-Sentences, Start, End
module.exports = {
name: "summarize-transcription", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type: "summarizer", // value used to differentiate each module to order them in the UI
displayname: "Summarizer", // The displayname used within the UI
async function(args) {
return new Promise(async (resolve, reject) => {
let inputJson = args.json;
//JSON Path
if (args.jsonPath) {
try {
const raw = fs.readFileSync(args.jsonPath, "utf-8");
inputJson = JSON.parse(raw);
} catch (e) {
// console.error("Failed to load JSON from file:", e);
reject(e)
return
}
}
// JSON parsen
if (typeof args === "string") {
try {
await new Promise((res, rej) => {
fs.readFile(args, 'utf8', function (err, data) {
if (err){
rej(err)
return
}
inputJson = JSON.parse(data);
res()
});
})
} catch (e) {
// console.log("Invalid JSON in summarize-transcription");
// console.log(e)
reject(e)
return
}
}
const words = inputJson.words;
if (!Array.isArray(words)) {
reject("No words Array found")
return
}
const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
const result = [];
let currentSentence = "";
let currentSpeaker = null;
let startTime = null;
let endTime = null;
for (const w of words) {
if (!currentSpeaker) currentSpeaker = w.speaker;
if (startTime === null) startTime = w.start;
endTime = w.end;
//speaker changing
if (currentSpeaker !== w.speaker && currentSentence) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
currentSentence = "";
startTime = w.start;
}
currentSpeaker = w.speaker;
currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
const lastWord = w.text.trim();
const lastChar = lastWord.slice(-1);
const isAbbreviation = ABBREVIATIONS.has(lastWord);
//sentence ending
if (ENDINGS.includes(lastChar) && !isAbbreviation) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
currentSentence = "";
startTime = null;
endTime = null;
currentSpeaker = null;
}
}
// safe last sentence
if (currentSentence) {
const lastEntry = result[result.length - 1];
if (lastEntry && lastEntry.speaker === currentSpeaker) {
lastEntry.sentence += " " + currentSentence;
lastEntry.end = endTime;
} else {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
}
// Output as Text
const output = result.map(r =>
`Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
);
// Output on cosole
//console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
try {
const jsonPath = path.join(outputDir, "transcription_result.json");
fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
const txtPath = path.join(outputDir, "transcription_result.txt");
fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
// console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
resolve(jsonPath);
} catch (err) {
// console.error("Error saving Summary:", err);
reject(err);
}
})
}
}
@@ -1,149 +0,0 @@
// Prepare output directory (always storage/transcriptionSummaries under project root)
const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
function getSessionId(inputPath) {
try {
const parsed = new URL(inputPath);
const base = path.basename(parsed.pathname);
return base.replace(/\.[^.]+$/, '');
} catch {
return path.basename(inputPath, path.extname(inputPath));
}
}
//Speaker, Sentence, Start, End
module.exports = {
name: "summarize-transcription2", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type: "summarizer", // value used to differentiate each module to order them in the UI
displayname: "Summarizer", // The displayname used within the UI
async function(args) {
return new Promise(async (resolve, reject) => {
let inputJson = args.json;
//JSON Path
if (args.jsonPath) {
try {
const raw = fs.readFileSync(args.jsonPath, "utf-8");
inputJson = JSON.parse(raw);
} catch (e) {
console.error("Failed to load JSON from file:", e);
reject("Could not read JSON from file path.")
return
}
}
// JSON parsen
if (typeof args === "string") {
try {
await new Promise((res, rej) => {
fs.readFile(args, 'utf8', function (err, data) {
if (err){
rej(err)
return
}
inputJson = JSON.parse(data);
res()
});
})
} catch (e) {
// console.log("Invalid JSON in summarize-transcription");
// console.log(e)
reject(e)
return
}
}
const words = inputJson.words;
if (!Array.isArray(words)) {
reject("No words Array found")
return;
}
const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
const result = [];
let currentSentence = "";
let currentSpeaker = null;
let startTime = null;
let endTime = null;
for (const w of words) {
if (!currentSpeaker) currentSpeaker = w.speaker;
if (startTime === null) startTime = w.start;
endTime = w.end;
//speaker changing
if (currentSpeaker !== w.speaker && currentSentence) {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
currentSentence = "";
startTime = w.start;
}
currentSpeaker = w.speaker;
currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
const lastWord = w.text.trim();
const lastChar = lastWord.slice(-1);
const isAbbreviation = ABBREVIATIONS.has(lastWord);
//sentence ending
if (ENDINGS.includes(lastChar) && !isAbbreviation) {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
currentSentence = "";
startTime = null;
endTime = null;
currentSpeaker = null;
}
}
// safe last sentence
if (currentSentence) {
result.push({
speaker: currentSpeaker,
sentence: currentSentence,
start: startTime,
end: endTime
});
}
// Output as Text
const output = result.map(r =>
`Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
);
// Output on cosole
//console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
try {
let filename = getSessionId(args);
const jsonPath = path.join(outputDir, `${filename}-${new Date().getTime()}.json`);
fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
const txtPath = path.join(outputDir, `${filename}-${new Date().getTime()}.txt`);
fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
// console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
resolve(jsonPath);
} catch (err) {
// console.error("Error saving Summary:", err);
reject(err);
}
})
}
}
+6 -136
View File
@@ -1,138 +1,8 @@
// const fs = require('fs');
// const path = require('path');
const outputDir = path.join(__dirname, "../../../storage/documents"); // path for output directory
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
}
// Ensure SAIA API key is set in environment variables: export SAIA_API_KEY="your_api_key_here"
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 = {
name: "llm-saia_openai_gpt",
type: "llm",
displayname: "GPT 120B",
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);
resolve(await this.createDocumentFromTranscript( //Call the function to create document with transcript, document type and language
parameter.inputTranscriptPath, // Path to input transcript file
parameter.documentTypePath, // Path to document type file which is chosen in the front end by the user
parameter.language // Language for the document which is chosen in the front end by the user
));
} catch (error) {
// console.error("Error in SAIA OpenAI GPT module:", error);
reject(error)
}
})
},
createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
return new Promise(async(resolve, reject) => {
try {
const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed
// return
// --- REST CALL ---
const response = await fetch(SAIA_URL, { //safe model response in variable
method: "POST",
headers: {
"Authorization": `Bearer ${SAIA_API_KEY}`,
"Accept": "application/json",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "openai-gpt-oss-120b",
messages: [
{ role: "system", content: "You are a helpful assistant that generates HTML documents from transcripts. Output only valid HTML content without any preamble, explanations, or markdown formatting." },
{ role: "user", content: promptText }
],
temperature: 0
})
});
if (!response.ok) { //ok is true when a responce was successfull
const text = await response.text();
throw new Error(`SAIA API error (${response.status}): ${text}`);
}
const data = await response.json();
// Get generated text from response or default to empty string (if null)
// SAIA uses OpenAI-compatible structure: data.choices[x].message.content
const output = data.choices?.[0]?.message?.content || "";
let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file
// console.log(inputTranscriptName);
const outPath = path.join(outputDir, `${inputTranscriptName}.html`); // Output file path & name to make naming dynamic. Pulled from input transcript name
fs.writeFileSync(outPath, output, "utf8"); // Write output to file
// console.log("Generated document written to:", outPath);
resolve(outPath)
} catch (error) {
// console.error("Error generating SAIA content:", error);
reject(error)
}
})
module.exports = {
name:"chatgpt", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type:"document", // value used to differentiate each module to order them in the UI
displayname:"ChatGPT", // The displayname used within the UI
async function(parameter){
// TODO add code to actually send the transcript to ChatGPT and get a response back
}
};
module.exports = module_exports;
// CLI Mode: Allow direct execution
if (require.main === module) {
(async () => {
const args = process.argv.slice(2);
if (args.length < 2) {
console.error("Usage: node llm-openai-gpt.js <transcriptPath> <documentTypePath> [language]");
console.error("Example: node llm-openai-gpt.js ./transcript.json ./docType.txt de");
process.exit(1);
}
const [transcriptPath, documentTypePath, language] = args;
// Check if API key is set
if (!SAIA_API_KEY) {
console.error("ERROR: SAIA_API_KEY environment variable is not set!");
console.error("Please set it with: export SAIA_API_KEY='your_api_key_here'");
process.exit(1);
}
// Check if files exist
if (!fs.existsSync(transcriptPath)) {
console.error(`ERROR: Transcript file not found: ${transcriptPath}`);
process.exit(1);
}
if (!fs.existsSync(documentTypePath)) {
console.error(`ERROR: Document type file not found: ${documentTypePath}`);
process.exit(1);
}
console.log("Starting document generation...");
console.log(`Transcript: ${transcriptPath}`);
console.log(`Document Type: ${documentTypePath}`);
console.log(`Language: ${language || 'en (default)'}`);
await module_exports.createDocumentFromTranscript(
transcriptPath,
documentTypePath,
language || 'en'
);
console.log("Done!");
})();
}
+53 -112
View File
@@ -1,135 +1,76 @@
const fs = require('fs');
const path = require('path');
const outputDir = path.join(__dirname, "../../../storage/documents"); // path for output directory
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"
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 = {
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) {
GEMINI_API_KEY = process.env.GOOGLE_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// console.log("Gemini LLM module invoked with parameters:", parameter);
try {
console.log("Gemini LLM module invoked with parameters:", parameter);
resolve(await this.createDocumentFromTranscript( //Call the function to create document with transcript, document type and language
parameter.inputTranscriptPath, // Path to input transcript file
parameter.documentTypePath, // Path to document type file which is chosen in the front end by the user
parameter.language // Language for the document which is chosen in the front end by the user
));
} catch (error) {
// console.error("Error in Gemini LLM module:", error);
reject(error)
}
})
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
return new Promise(async(resolve, reject) => {
try {
const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed
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
]
}
]
})
});
// --- 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}.html`); // Output file path & name to make naming dynamic. Pulled from input transcript name
fs.writeFileSync(outPath, output, "utf8"); // Write output to file
// console.log("Generated document written to:", outPath);
resolve(outPath)
} catch (error) {
// console.error("Error generating Gemini content:", error);
reject(error)
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);
}
}
};
module.exports = module_exports;
// CLI Mode: Allow direct execution
if (require.main === module) {
(async () => {
const args = process.argv.slice(2);
if (args.length < 2) {
console.error("Usage: node llm-gemini.js <transcriptPath> <documentTypePath> [language]");
console.error("Example: node llm-gemini.js ./transcript.json ./docType.txt de");
process.exit(1);
}
const [transcriptPath, documentTypePath, language] = args;
// Check if API key is set
if (!GEMINI_API_KEY) {
console.error("ERROR: GOOGLE_API_KEY environment variable is not set!");
console.error("Please set it with: export GOOGLE_API_KEY='your_api_key_here'");
process.exit(1);
}
// Check if files exist
if (!fs.existsSync(transcriptPath)) {
console.error(`ERROR: Transcript file not found: ${transcriptPath}`);
process.exit(1);
}
if (!fs.existsSync(documentTypePath)) {
console.error(`ERROR: Document type file not found: ${documentTypePath}`);
process.exit(1);
}
console.log("Starting document generation...");
console.log(`Transcript: ${transcriptPath}`);
console.log(`Document Type: ${documentTypePath}`);
console.log(`Language: ${language || 'en (default)'}`);
await module_exports.createDocumentFromTranscript(
transcriptPath,
documentTypePath,
language || 'en'
);
console.log("Done!");
})();
}
-137
View File
@@ -1,137 +0,0 @@
const fs = require('fs');
const path = require('path');
const outputDir = path.join(__dirname, "../../../storage/documents"); // path for output directory
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
}
// Ensure SAIA API key is set in environment variables: export SAIA_API_KEY="your_api_key_here"
let SAIA_API_KEY;
const SAIA_URL = "https://chat-ai.academiccloud.de/v1/chat/completions"; // URL for the REST call, used model and action
const module_exports = {
name: "qwen3-235b-a22b",
type: "llm",
displayname: "QWEN 3 235B",
description: "Generates documents using QWEN 3 235B via SAIA platform",
async function(parameter) {
SAIA_API_KEY = process.env.SAIA_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// console.log("SAIA QWEN 3 235B module invoked with parameters:", parameter);
resolve(await this.createDocumentFromTranscript( //Call the function to create document with transcript, document type and language
parameter.inputTranscriptPath, // Path to input transcript file
parameter.documentTypePath, // Path to document type file which is chosen in the front end by the user
parameter.language // Language for the document which is chosen in the front end by the user
));
} catch (error) {
// console.error("Error in SAIA QWEN 3 235B module:", error);
reject(error)
}
})
},
createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
return new Promise(async(resolve, reject) => {
try {
const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed
// --- REST CALL ---
const response = await fetch(SAIA_URL, { //safe model response in variable
method: "POST",
headers: {
"Authorization": `Bearer ${SAIA_API_KEY}`,
"Accept": "application/json",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "qwen3-235b-a22b",
messages: [
{ role: "system", content: "You are a helpful assistant that generates HTML documents from transcripts. Output only valid HTML content without any preamble, explanations, or markdown formatting." },
{ role: "user", content: promptText }
],
temperature: 0
})
});
if (!response.ok) { //ok is true when a responce was successfull
const text = await response.text();
throw new Error(`SAIA API error (${response.status}): ${text}`);
}
const data = await response.json();
// Get generated text from response or default to empty string (if null)
// SAIA uses OpenAI-compatible structure: data.choices[x].message.content
const output = data.choices?.[0]?.message?.content || "";
let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file
// console.log(inputTranscriptName);
const outPath = path.join(outputDir, `${inputTranscriptName}.html`); // Output file path & name to make naming dynamic. Pulled from input transcript name
fs.writeFileSync(outPath, output, "utf8"); // Write output to file
// console.log("Generated document written to:", outPath);
resolve(outPath)
} catch (error) {
// console.error("Error generating SAIA content:", error);
reject(error)
}
})
}
};
module.exports = module_exports;
// CLI Mode: Allow direct execution
if (require.main === module) {
(async () => {
const args = process.argv.slice(2);
if (args.length < 2) {
console.error("Usage: node qwen3.js <transcriptPath> <documentTypePath> [language]");
console.error("Example: node qwen3.js ./transcript.json ./docType.txt de");
process.exit(1);
}
const [transcriptPath, documentTypePath, language] = args;
// Check if API key is set
if (!SAIA_API_KEY) {
console.error("ERROR: SAIA_API_KEY environment variable is not set!");
console.error("Please set it with: export SAIA_API_KEY='your_api_key_here'");
process.exit(1);
}
// Check if files exist
if (!fs.existsSync(transcriptPath)) {
console.error(`ERROR: Transcript file not found: ${transcriptPath}`);
process.exit(1);
}
if (!fs.existsSync(documentTypePath)) {
console.error(`ERROR: Document type file not found: ${documentTypePath}`);
process.exit(1);
}
console.log("Starting document generation...");
console.log(`Transcript: ${transcriptPath}`);
console.log(`Document Type: ${documentTypePath}`);
console.log(`Language: ${language || 'en (default)'}`);
await module_exports.createDocumentFromTranscript(
transcriptPath,
documentTypePath,
language || 'en'
);
console.log("Done!");
})();
}
@@ -1,79 +0,0 @@
const fs = require('fs');
const path = require('path');
const module_exports = {
name: "replace_speaker",
type: "processor",
displayname: "Speaker Name Replacer",
description: "Replaces speaker placeholder names with actual names based on a mapping in HTML files",
async function(speakerMapping) {
// Relativ von dieser Datei aus
const documentsDir = path.resolve(__dirname, '../../../storage/documents');
const inputHtmlPath = await this.getNewestFile(documentsDir, '.html');
if (!inputHtmlPath) {
throw new Error(`No HTML files found in ${documentsDir}`);
}
return await this.replaceNames(inputHtmlPath, speakerMapping);
},
getNewestFile: async function(dirPath, extension) {
try {
const files = await fs.promises.readdir(dirPath);
const filtered = files.filter(f => f.endsWith(extension));
if (filtered.length === 0) return null;
const filesWithStats = await Promise.all(
filtered.map(async (f) => {
const fullPath = path.join(dirPath, f);
const stats = await fs.promises.stat(fullPath);
return { path: fullPath, time: stats.mtimeMs };
})
);
return filesWithStats.reduce((newest, curr) =>
curr.time > newest.time ? curr : newest
).path;
} catch (error) {
console.error("Error reading directory:", error);
throw error;
}
},
replaceNames: async function(inputHtmlPath, speakerMapping) {
try {
const htmlContent = await fs.promises.readFile(inputHtmlPath, "utf-8");
let outputContent = htmlContent;
Object.entries(speakerMapping).forEach(([placeholder, value]) => {
// Extract name if value is an object
const displayName = typeof value === 'string' ? value : value.name;
// Normalize placeholder for matching (remove case sensitivity)
const normalizedPlaceholder = placeholder.toLowerCase();
// Replace all variations: speakerA, SpeakerA, SPEAKERA, speaker_a, Speaker A, etc.
// Matches with optional spaces, underscores, and parentheses
const regex = new RegExp(
`\\b[Ss]peaker\\s*[_-]?\\s*${placeholder.charAt(placeholder.length - 1)}\\b|\\b${placeholder}\\b`,
'gi'
);
outputContent = outputContent.replace(regex, displayName);
});
await fs.promises.writeFile(inputHtmlPath, outputContent, "utf-8");
return inputHtmlPath;
} catch (error) {
console.error("Error replacing speaker names:", error);
throw error;
}
}
};
module.exports = module_exports;
@@ -1,54 +0,0 @@
// -----------------------------------------------------------
// Parakeet (Step 3A: spawn Python minimal integration)
// -----------------------------------------------------------
const fs = require("fs");
const path = require("path");
const { spawn } = require("child_process");
module.exports = {
name: "parakeet",
type: "transcription",
displayname: "NVIDIA Parakeet",
async function(audioFilePath) {
console.log("🦜 [Parakeet] Starting test integration (spawn only)...");
console.log("🦜 Input audio:", audioFilePath);
// Check audio exists
if (!fs.existsSync(audioFilePath)) {
throw new Error("Audio file does not exist: " + audioFilePath);
}
// Output path in storage/transcripts
const sessionId = path.basename(audioFilePath).replace(/\.[^.]+$/, "");
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));
}
});
});
}
};
@@ -1,71 +0,0 @@
# -----------------------------------------------------------
# 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)
Submodule services/modules/transcription-local/whisper.cpp deleted from 999a7e0cbf
@@ -1,126 +1,8 @@
let API_KEY
const BASE_URL = 'https://api.assemblyai.com/v2';
//---------------------------------------------------Upload audio---------------------------------------------------
async function uploadAudio(audioPath) {
const audioData = fs.readFileSync(audioPath);
const response = await axios.post(`${BASE_URL}/upload`, audioData, {
headers: {
authorization: API_KEY,
'content-type': 'application/octet-stream'
}
});
return response.data.upload_url;
}
////---------------------------------------------------Extract session id---------------------------------------------------
function getSessionId(inputPath) {
try {
const parsed = new URL(inputPath);
const base = path.basename(parsed.pathname);
return base.replace(/\.[^.]+$/, '');
} catch {
return path.basename(inputPath, path.extname(inputPath));
}
}
//---------------------------------------------------Create transcript---------------------------------------------------
async function createTranscript(audioUrl) {
const response = await axios.post(
`${BASE_URL}/transcript`,
{
audio_url: audioUrl,
speaker_labels: true,
language_detection: true
},
{
headers: {
authorization: API_KEY,
'content-type': 'application/json'
}
}
);
return response.data.id;
}
//---------------------------------------------------Poll transcript---------------------------------------------------
async function pollTranscript(transcriptId) {
while (true) {
const response = await axios.get(`${BASE_URL}/transcript/${transcriptId}`, {
headers: { authorization: API_KEY }
});
const status = response.data.status;
if (status === 'completed') return response.data;
if (status === 'error') throw new Error(`Transcription failed: ${response.data.error}`);
await new Promise(res => setTimeout(res, 3000));
}
}
//---------------------------------------------------Save transcript---------------------------------------------------
function saveTranscript(transcript, sessionId) {
const outputDir = path.join(__dirname, '../../../storage/transcripts');
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
const outputPath = path.join(outputDir, `${sessionId}.json`);
fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
// console.log(`Transcript saved: ${outputPath}`);
return outputPath;
}
//---------------------------------------------------Modul---------------------------------------------------
module.exports = {
name: 'assembly',
type: 'transcription',
displayname: 'AssemblyAI',
audioformat: "mp3",
async function(audioFileName) {
API_KEY = process.env.ASSEMBLYAI_API_KEY;
return new Promise(async (resolve, reject) => {
try {
// audioFileName ist nur "datei.mp3"
const audioPath = audioFileName;
let audioUrl;
if (/^https?:\/\//i.test(audioFileName)) {
audioUrl = audioFileName;
} else {
if (!fs.existsSync(audioPath)) {
throw new Error(`Audio file not found: ${audioPath}`);
}
audioUrl = await uploadAudio(audioPath);
}
const transcriptId = await createTranscript(audioUrl);
const transcript = await pollTranscript(transcriptId);
const sessionId = getSessionId(audioFileName);
resolve(saveTranscript(transcript, sessionId));
} catch (error) {
// console.error('Transcription error:', error.message);
reject(error);
return
}
})
}
};
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
}
}
-12
View File
@@ -1,4 +1,3 @@
module.exports = {
name:"Startup_function",
async function(){
@@ -7,19 +6,8 @@ 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'});
// let snippets = await mapFunctions.get("extract-speaker-snippets").function({audioPath:'/Users/santa/Proj25/video2document/storage/audio/KittyKat.wav', jsonPath1: '/Users/santa/Proj25/video2document/storage/transcriptionSummaries/KittyKat-1765806474958.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"})
}
}
@@ -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)
});
})
}
}
@@ -1,7 +1,6 @@
// 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';
/**
-23
View File
@@ -1,23 +0,0 @@
@echo off
cd /d %~dp0
:: Prüfen ob Node.js installiert ist
where node >nul 2>nul
if %errorlevel% neq 0 (
echo Node.js ist nicht installiert.
pause
exit /b 1
)
echo Node.js gefunden:
node -v
npm install
if %errorlevel% neq 0 (
echo npm install fehlgeschlagen.
pause
exit /b 1
)
npm start
pause
-15
View File
@@ -1,15 +0,0 @@
#!/bin/bash
# Prüfen ob Node.js installiert ist
if ! command -v node >/dev/null 2>&1; then
echo "Node.js ist nicht installiert."
exit 1
fi
echo "Node.js gefunden: $(node -v)"
# Abhängigkeiten installieren
npm install || exit 1
# Projekt starten
npm start
BIN
View File
Binary file not shown.
BIN
View File
Binary file not shown.
-45
View File
@@ -1,45 +0,0 @@
# Meeting Agenda Generator
Du bist ein erfahrener Moderator und Projektmanager.
## KRITISCH - SPRECHER-PLATZHALTER BEWAHREN:
**speakerA, speakerB, speakerC, etc. sind technische Platzhalter und DÜRFEN NICHT verändert werden.**
- RICHTIG: "speakerA hat entschieden..."
- FALSCH: "Speaker A", "speakerA (Name)", Klammern, Leerzeichen, Ergänzungen
Diese Token werden später durch echte Namen ersetzt. Jede Änderung bricht diesen Prozess.
---
## AUFGABE:
Erstelle eine sinnvolle Meeting-Agenda basierend auf dem Meeting-Transkript.
## ANFORDERUNGEN:
- Rekonstruiere die tatsächlichen Themenblöcke
- Ordne sie logisch und chronologisch
- Fasse ähnliche Diskussionen zusammen
- Keine irrelevanten Details aufnehmen
- Speicher-Platzhalter (speakerA, speakerB, etc.) exakt beibehalten
## STRUKTUR:
### 1. Titel der Agenda
### 2. Ziel des Meetings
- 12 präzise Sätze
### 3. Agenda-Punkte (nummeriert)
Für jeden Punkt:
- **Thema**
- **Kurzbeschreibung**
- **Ziel des Punktes:** (Information / Entscheidung / Diskussion)
## STIL:
- Klar, kompakt
- Business-orientiert
- Keine Sprecher- oder Zeitangaben
- Logische Reihenfolge
---
**TRANSKRIPT:**
-44
View File
@@ -1,44 +0,0 @@
# Custom Document Generator
Du bist ein intelligenter Dokumenten-Generator.
## KRITISCH - SPRECHER-PLATZHALTER BEWAHREN:
**speakerA, speakerB, speakerC, etc. sind technische Platzhalter und DÜRFEN NICHT verändert werden.**
- RICHTIG: "speakerA hat entschieden..."
- FALSCH: "Speaker A", "speakerA (Name)", Klammern, Leerzeichen, Ergänzungen
Diese Token werden später durch echte Namen ersetzt. Jede Änderung bricht diesen Prozess.
---
## AUFGABE:
Erstelle ein individuelles Dokument basierend auf:
1. dem Meeting-Transkript
2. der zusätzlichen Nutzeranweisung
## ANFORDERUNGEN:
- **Priorisiere die Nutzeranweisung** über standardisierte Strukturen
- Nutze das Transkript als Wissensquelle
- Struktur, Tonalität und Detailgrad nach Nutzervorgabe anpassen
- Inhalte logisch zusammenführen
- Speicher-Platzhalter (speakerA, speakerB, etc.) exakt beibehalten
## VORGEHEN:
1. Lese die Nutzeranweisung sorgfältig
2. Extrahiere aus dem Transkript die relevanten Informationen
3. Erstelle das Dokument nach der gewünschten Struktur
4. Behalte Sprecher-Platzhalter unverändert
## ALLGEMEINE RICHTLINIEN:
- Entferne Redundanzen und Smalltalk
- Keine Zeitstempel oder Sprecherangaben (wenn nicht gefordert)
- Sachlich, präzise, professionell
- Keine Spekulationen oder Meinungen (wenn nicht gefordert)
---
**NUTZERANWEISUNG:**
[Hier kommt die Anforderung des Nutzers hin]
**TRANSKRIPT:**
[Hier kommt das Meeting-Transkript hin]
-61
View File
@@ -1,61 +0,0 @@
# Follow-up Report Generator
Du bist ein professioneller Meeting-Analyst und Business Writer.
## KRITISCH - SPRECHER-PLATZHALTER BEWAHREN:
**speakerA, speakerB, speakerC, etc. sind technische Platzhalter und DÜRFEN NICHT verändert werden.**
- RICHTIG: "speakerA hat entschieden..."
- FALSCH: "Speaker A", "speakerA (Name)", Klammern, Leerzeichen, Ergänzungen
Diese Token werden später durch echte Namen ersetzt. Jede Änderung bricht diesen Prozess.
---
## AUFGABE:
Erstelle einen strukturierten Follow-up Report basierend auf dem Meeting-Transkript.
## ANFORDERUNGEN:
- Fasse Inhalte sinngemäß zusammen
- Entferne Redundanzen und Smalltalk
- Formuliere klar, präzise und professionell
- Verwende neutrale Business-Sprache
- Leite Entscheidungen und Aufgaben logisch ab, wenn sie implizit sind
- Markiere offene Punkte klar
- Speicher-Platzhalter (speakerA, speakerB, etc.) exakt beibehalten
## STRUKTUR DES DOKUMENTS:
### 1. Titel & Metadaten
- Meetingtitel (ableiten)
- Datum (falls im Transkript erwähnt, sonst „nicht angegeben")
- Teilnehmer (zusammengefasst)
### 2. Executive Summary
- Max. 5 Bullet Points
- Kernpunkte zusammenfassen
### 3. Besprochene Themen
- Thema
- Kernaussagen
- Relevante Erkenntnisse
### 4. Entscheidungen
- Entscheidung
- Kontext / Begründung
### 5. Action Items
- Aufgabe
- Verantwortlich (falls ableitbar)
- Ziel / Zweck
### 6. Offene Fragen & Risiken
## STIL:
- Überschriften klar strukturiert
- Bullet Points bevorzugen
- Präzise, keine Umgangssprache
- Keine Zeitstempel oder Sprecherangaben
---
**TRANSKRIPT:**
-54
View File
@@ -1,54 +0,0 @@
# Result Protocol Generator
Du bist ein professioneller Protokollführer.
## KRITISCH - SPRECHER-PLATZHALTER BEWAHREN:
**speakerA, speakerB, speakerC, etc. sind technische Platzhalter und DÜRFEN NICHT verändert werden.**
- RICHTIG: "speakerA hat entschieden..."
- FALSCH: "Speaker A", "speakerA (Name)", Klammern, Leerzeichen, Ergänzungen
Diese Token werden später durch echte Namen ersetzt. Jede Änderung bricht diesen Prozess.
---
## AUFGABE:
Erstelle ein Ergebnisprotokoll basierend auf dem Meeting-Transkript.
## FOKUS:
- Ergebnisse statt Diskussionen
- Entscheidungen, Beschlüsse, Vereinbarungen
- Klare, überprüfbare Aussagen
- Speicher-Platzhalter (speakerA, speakerB, etc.) exakt beibehalten
## STRUKTUR:
### 1. Meeting-Informationen
- Titel
- Datum
- Teilnehmer
### 2. Ergebnisse je Thema
- **Thema**
- **Ergebnis / Beschluss**
### 3. Entscheidungen
- Klare Entscheidungen mit Kontext
### 4. Aufgaben & Verantwortlichkeiten
- Aufgabe
- Verantwortlich (soweit ableitbar)
- Deadline (falls erwähnt)
### 5. Offene Punkte
- Ungelöste Fragen
- Ausstehende Klärungen
## REGELN:
- Keine Meinungen oder Spekulationen
- Keine Zeit- oder Sprecherangaben
- Sachlich, formal
- Fokus auf Fakten und Ergebnisse
---
**TRANSKRIPT:**
@@ -1,61 +0,0 @@
# Sprint Planning Note Generator
Du bist ein erfahrener Scrum Master.
## KRITISCH - SPRECHER-PLATZHALTER BEWAHREN:
**speakerA, speakerB, speakerC, etc. sind technische Platzhalter und DÜRFEN NICHT verändert werden.**
- RICHTIG: "speakerA hat entschieden..."
- FALSCH: "Speaker A", "speakerA (Name)", Klammern, Leerzeichen, Ergänzungen
Diese Token werden später durch echte Namen ersetzt. Jede Änderung bricht diesen Prozess.
---
## AUFGABE:
Erstelle Sprint Planning Notes aus dem Meeting-Transkript.
## FOKUS:
- Sprint-Ziele
- User Stories / Tasks
- Abhängigkeiten
- Risiken
- Commitments
- Speicher-Platzhalter (speakerA, speakerB, etc.) exakt beibehalten
## STRUKTUR:
### 1. Sprint Overview
- **Sprint-Ziel:** (Kurz und prägnant)
- **Zeitraum:** (Falls im Transkript erwähnt)
### 2. Geplante Arbeit
Für jede User Story / Task:
- **Titel**
- **Beschreibung**
- **Akzeptanzkriterien** (falls ableitbar)
- **Story Points** (falls erwähnt)
### 3. Abhängigkeiten & Blocker
- Externe Abhängigkeiten
- Potenzielle Blocker
- Klärungsbedarf
### 4. Risiken & Annahmen
- Identifizierte Risiken
- Annahmen für den Sprint
- Mitigation-Strategien (falls diskutiert)
### 5. Team-Commitments / Vereinbarungen
- Vereinbarte Commitments
- Rollen und Verantwortlichkeiten
- Definition of Done (falls diskutiert)
## STIL:
- Agile-konform
- Klar & umsetzungsorientiert
- Bullet Points bevorzugen
- Keine Zeitstempel oder Sprecherangaben
---
**TRANSKRIPT:**
-18
View File
@@ -1,18 +0,0 @@
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);
}
})();
File diff suppressed because it is too large Load Diff
@@ -1,12 +0,0 @@
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
});
+8
View File
@@ -0,0 +1,8 @@
from fastapi.testclient import TestClient
from app.main import app
client = TestClient(app)
def test_health():
response = client.get("/health")
assert response.status_code == 200
-243
View File
@@ -1,243 +0,0 @@
// DO NOT TOUCH THIS
require("../../requires.js")
mapFunctions = new Map()
// Loading the Function Map
var path = `${mainDir}/services/modules`
var folders = fs.readdirSync(path).filter(function (file) {
return fs.statSync(path+'/'+file).isDirectory();
});
folders.forEach(element => {
var commandFiles = fs.readdirSync(`${path}/${element}`).filter(file => file.endsWith('.js') && !file.startsWith("index"));
for (const file of commandFiles) {
delete require.cache[require.resolve(`${path}/${element}/${file}`)];
const command = require(`${path}/${element}/${file}`);
mapFunctions.set(command.name, command);
}
});
// You can touch beyond this point
let audiopath
let transcriptPath
let summarizePath
let llmpath
let speakers
describe("Unit Tests", function() {
describe('Audio Extraction', function () {
this.slow(1000)
this.timeout(3000)
it('Extract .mp4 to .mp3', function (done) {
mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: __dirname.replaceAll("\\","/")+"/testvideo.mp4", outputType: "mp3"}).then(resp => {
audiopath = resp
// console.log(resp);
done()
}).catch(err => {
done(err);
})
})
it('Extract .mp4 to .flac', function (done) {
mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: __dirname.replaceAll("\\","/")+"/testvideo.mp4", outputType: "flac"}).then(resp => {
// console.log(resp);
done()
}).catch(err => {
done(err);
})
})
it('Extracting to a nonexistant format', function (done) {
mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: __dirname.replaceAll("\\","/")+"/testvideo.mp4", outputType: "qqq"}).then(resp => {
// console.log(resp);
done("Didnt crash")
}).catch(err => {
done()
})
})
it('Extracting from nonexistant file', function (done) {
mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: "a", outputType: "mp3"}).then(resp => {
// console.log(resp);
done("Didnt crash")
}).catch(err => {
done()
})
})
it('Extracting from nonexistant file to nonexistant format', function (done) {
mapFunctions.get("extraction-video-to-audio").function({inputVideoPath: "a", outputType: "qqq"}).then(resp => {
// console.log(resp);
done("Didnt crash")
}).catch(err => {
done()
})
})
});
describe("Audio Transcription", function() {
this.slow(20000)
this.timeout(120000)
it('Assembly', function (done) {
mapFunctions.get("assembly").function(audiopath).then(resp => {
// console.log(resp);
transcriptPath = resp
done()
}).catch(err => {
done(err)
})
})
it('Assembly Wrong file', function (done) {
mapFunctions.get("assembly").function("a").then(resp => {
// console.log(resp);
// transcriptPath = resp
done("Didnt crash")
}).catch(err => {
// console.log(err);
done()
})
})
// TODO add more Transcription Tool tests here
})
describe("Transcript Summarizer", function() {
this.slow(100)
this.timeout(1000)
it("Summarizer 1", function (done){
mapFunctions.get("summarize-transcription").function(transcriptPath).then(resp => {
done()
}).catch(err => {
done(err)
})
})
it("Summarizer 1 Wrong File", function (done){
mapFunctions.get("summarize-transcription").function("a").then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Summarizer 2 (Main)", function (done){
mapFunctions.get("summarize-transcription2").function(transcriptPath).then(resp => {
summarizePath = resp
done()
}).catch(err => {
done(err)
})
})
it("Summarizer 2 (Main) Wrong File", function (done){
mapFunctions.get("summarize-transcription2").function("a").then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
})
describe("Large Language Model", function() {
this.slow(30000)
this.timeout(120000)
it("ChatGPT", function (done){
mapFunctions.get("llm-saia_openai_gpt").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/followup_report.txt", language: "en"}).then(resp => {
llmpath = resp
done()
}).catch(err => {
done(err)
})
})
it("Gemini", function (done){
mapFunctions.get("llm-gemini").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/followup_report.txt", language: "en"}).then(resp => {
done()
}).catch(err => {
if(err.includes("(503)")){done()} // Error 503 is gemini overload, so an Error that they can at any time throw at us which would crash the pipeline, so we just ignore it and we just imagine that the test passed
else{
console.log(err);
done(err)
}
})
})
it("Qwen3", function (done){
mapFunctions.get("qwen3-235b-a22b").function({inputTranscriptPath: summarizePath, documentTypePath: "./storage/documentType/followup_report.txt", language: "en"}).then(resp => {
done()
}).catch(err => {
done(err)
})
})
it("ChatGPT (Nonexistant Type File)", function (done){
mapFunctions.get("llm-saia_openai_gpt").function({inputTranscriptPath: summarizePath, documentTypePath: "a", language: "en"}).then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Gemini (Nonexistant Type File)", function (done){
mapFunctions.get("llm-gemini").function({inputTranscriptPath: summarizePath, documentTypePath: "a", language: "en"}).then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Qwen3 (Nonexistant Type File)", function (done){
mapFunctions.get("qwen3-235b-a22b").function({inputTranscriptPath: summarizePath, documentTypePath: "a", language: "en"}).then(resp => {
done("Didnt crash")
}).catch(err => {
done()
})
})
})
describe("Audio Snippet", function() {
this.slow(1000)
this.timeout(5000)
// transcriptPath = "A:\\programing\\@projects\\video2document\\storage\\transcriptionSummaries\\testvideo-1765900665001.json"
// audiopath = "A:\\programing\\@projects\\video2document\\storage\\audio\\testvideo.mp3"
it("Audio Snipper Generator", function (done){
mapFunctions.get("extract-speaker-snippets").function({audioPath: audiopath, jsonPath: summarizePath }).then(resp => {
speakers = resp
done()
}).catch(err => {
done(err)
})
})
it("Audio Snipper Generator (Nonexistant Transcript File)", function (done){
mapFunctions.get("extract-speaker-snippets").function({audioPath: audiopath, jsonPath: "a" }).then(resp => {
speakers = resp
done("Didnt crash")
}).catch(err => {
done()
})
})
it("Audio Snipper Generator (Nonexistant Audio File)", function (done){
mapFunctions.get("extract-speaker-snippets").function({audioPath: "a", jsonPath: summarizePath }).then(resp => {
speakers = resp
done("Didnt crash")
}).catch(err => {
done()
})
})
})
after(function() {
console.log(`\n\n\n${audiopath} \n${transcriptPath} \n${summarizePath} \n${llmpath}`);
})
})
Binary file not shown.