Solved merge conflicts (hopefully)

Implemented a dropdown field for the languages as well as functions and a file...

See merge request proj-wise2526-video2document/video2document!23

.gitlab-ci.yml

@@ -1,6 +1,33 @@
-build-job:
+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:
+  - setup
+  - test
+
+setup_environment:
+  stage: setup
   script:
-        - echo "Building the Project.."
-test-job:
+    - 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
+
+test_app:
+  stage: test
   script:
-        - echo "Running Tests.."        
+    - echo "Running V2D Framework basic test..."
+    - python -m unittest discover || echo "No tests found."
+
+  only:
+    - main
+    - feature/ci-pipeline-s1-09a-1
+

app/main.py

@@ -0,0 +1,7 @@
+from fastapi import FastAPI
+
+app = FastAPI()
+
+@app.get("/health")
+def health_check():
+    return {"status": "ok"}

electron/main/index.html

@@ -10,9 +10,10 @@
  
 <div class="mitte" id="mitte"> 
   <div class="flagsBtns" id="flagsBtns">
-    <button class="de_Btn" id="de_Btn" onclick="changeLanguage('de')"><img src="flags/germany-flag-png-large.jpg" width="25px" height="20px"/></button>
-    <button class="eng_Btn" id="eng_Btn" onclick="changeLanguage('en')"><img src="flags/united-kingdom-flag-png-large.jpg" width="25px" height="20px"/></button>
-    <button class="in_Btn" id="in_Btn" onclick="changeLanguage('in')"><img src="flags/india-flag-png-large.png" width="25px" height="20px"/></button>
+    <select name="ai_type" id="ai_type">
+    </select>
+    <select name="language_option" id="language_option">
+    </select>
   </div>
 
   <h1 id="h1">Video to document</h1> 
@@ -46,6 +47,7 @@
 </div>
 </div>
   
+<script src="languages.js"></script>
 <script src="script.js"></script>
 <script src="./renderer.js"></script>
 </body>

electron/main/languages.js

@@ -0,0 +1,36 @@
+var languageOptions = {
+    "eng":{
+        "title": "Video to document",
+        "h1": "Video to document",
+        "p1": "Drag and drop video file",
+        "fileName": "No video chosen",
+        "manualUploadBtn": "Search video",
+        "checkbox_group": "Choose prefered document style:",
+        "label_format": "Meeting report",
+        "label_summary": "Summary with timestamps",
+        "submitButton": "Submit"
+    },
+    "de":{
+        "title": "Video zu Dokument",
+        "h1": "Video zu Dokument",
+        "p1": "Video per Drag & Drop ablegen",
+        "fileName": "Kein Video ausgewaehlt",
+        "manualUploadBtn": "Video suchen",
+        "checkbox_group": "Bevorzugte Dokumentvarianten:",
+        "label_format": "Meeting Bericht",
+        "label_summary": "Zusammenfassung mit Zeitstempeln",
+        "submitButton": "Absenden"
+    },
+    "in":{
+        "title": "दस्तावेज़ के लिए वीडियो",
+        "h1": "दस्तावेज़ के लिए वीडियो",
+        "p1": "वीडियो फ़ाइल खींचें और छोड़ें",
+        "fileName": "कोई वीडियो नहीं चुना गया",
+        "manualUploadBtn": "वीडियो खोजें",
+        "checkbox_group": "पसंदीदा दस्तावेज़ शैली चुनें:",
+        "label_format": "बैठक रिपोर्ट",
+        "label_summary": "टाइमस्टैम्प के साथ सारांश",
+        "submitButton": "जमा करना"
+    }
+    
+};

electron/main/preload.js

@@ -1,5 +1,3 @@
-
-
 const { contextBridge, ipcRenderer, webUtils } = require('electron')
 
 try {
@@ -15,4 +13,3 @@ try {
 } catch (error) {
     console.log("Error in preload.js");
 }
-

electron/main/renderer.js

@@ -26,6 +26,16 @@ uploadContainer.addEventListener("drop", (e) => {
     } catch (error) {
         console.log("Error in renderer.js with the listerner for the drop function");
     } 
-    
-    
 })
+
+
+ window.addEventListener('load', (e) => { 
+    console.log("test");
+    loadLanguageOptions(); 
+});
+
+language_option.addEventListener('change', (e)=>{
+    const select = document.getElementById('language_option');
+    console.log(select.value);
+    changeLanguage(select.value);
+});

electron/main/script.js

@@ -1,4 +1,3 @@
-
 //listener for the file explorer search
 manualUploadBtn.addEventListener('click', () => {
   try {
@@ -40,39 +39,21 @@ function checkBoxes() {
 
 //language changing feature
 function changeLanguage(language) {
-    if (language === 'en') {
-        document.getElementById('title').textContent = 'Video to document';
-        document.getElementById('h1').textContent = 'Video to document';
-        document.getElementById('p1').textContent = 'Drag and drop video file';
-        document.getElementById('fileName').textContent = 'No video chosen';
-        document.getElementById('manualUploadBtn').textContent = 'Search video';
-        document.getElementById('checkbox_group').textContent = 'Choose prefered document style:';
-        document.getElementById('label_format').textContent = 'Meeting report';
-        document.getElementById('label_summary').textContent = 'Summary with timestamps';
-        document.getElementById('submitButton').textContent = 'Submit';
-    } else if (language === 'de') {
-        document.getElementById('title').textContent = 'Video zu Dokument';
-        document.getElementById('h1').textContent = 'Video zu Dokument';
-        document.getElementById('p1').textContent = 'Video per Drag & Drop ablegen';
-        document.getElementById('fileName').textContent = 'Kein Video ausgewaehlt';
-        document.getElementById('manualUploadBtn').textContent = 'Video suchen';
-        document.getElementById('checkbox_group').textContent = 'Bevorzugte Dokumentvarianten:';
-        document.getElementById('label_format').textContent = 'Meeting Bericht';
-        document.getElementById('label_summary').textContent = 'Zusammenfassung mit Zeitstempeln';
-        document.getElementById('submitButton').textContent = 'Absenden';
-    } else if(language == "in") {
-        document.getElementById('title').textContent = 'दस्तावेज़ के लिए वीडियो';
-        document.getElementById('h1').textContent = 'दस्तावेज़ के लिए वीडियो';
-        document.getElementById('p1').textContent = 'वीडियो फ़ाइल खींचें और छोड़ें';
-        document.getElementById('fileName').textContent = 'कोई वीडियो नहीं चुना गया';
-        document.getElementById('manualUploadBtn').textContent = 'वीडियो खोजें';
-        document.getElementById('checkbox_group').textContent = 'पसंदीदा दस्तावेज़ शैली चुनें:';
-        document.getElementById('label_format').textContent = 'बैठक रिपोर्ट';
-        document.getElementById('label_summary').textContent = 'टाइमस्टैम्प के साथ सारांश';
-        document.getElementById('submitButton').textContent = 'जमा करना';
-    }
+  try {
+    document.getElementById('title').textContent = languageOptions[language].title;
+    document.getElementById('h1').textContent = languageOptions[language].h1;
+    document.getElementById('p1').textContent = languageOptions[language].p1;
+    document.getElementById('fileName').textContent = languageOptions[language].fileName;
+    document.getElementById('manualUploadBtn').textContent = languageOptions[language].manualUploadBtn;
+    document.getElementById('checkbox_group').textContent = languageOptions[language].checkbox_group;
+    document.getElementById('label_format').textContent = languageOptions[language].label_format;
+    document.getElementById('label_summary').textContent = languageOptions[language].label_summary;
+    document.getElementById('submitButton').textContent = languageOptions[language].submitButton;
+  } catch (error) {
+    console.log(error);
   }
         
+}
 
 //listener for the file explorer search when something got selected
 videoUpload.addEventListener('change', () => {
@@ -84,8 +65,6 @@ videoUpload.addEventListener('change', () => {
   
 });
 
-
-
 //function to display the file path in the drop down box
 function handleFiles(files) {
   try {
@@ -113,3 +92,41 @@ function updateProgressBar(bar, value){
   }
   
 }
+
+//function to load ai options to the drop down list
+function loadAiOptions(options){
+  try {
+    var menu = document.getElementById('ai_type');
+    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) {
+    console.log("Error in script.js loadAiOptions function");
+    console.log(error);
+  }
+}
+
+//function to load language options to the drop down list
+function loadLanguageOptions(){
+  try {
+    var menu = document.getElementById('language_option');
+    var object_holdy;
+    var choice ;
+    object_holdy = Object.keys(languageOptions);
+    for(i = 0; i < object_holdy.length; i++){
+      choice = document.createElement('option');
+      choice.textContent = object_holdy[i];
+      choice.value = object_holdy[i];
+      menu.appendChild(choice);
+    }
+    
+  } catch (error) {
+    console.log("Error in script.js loadLanguageOptions function");
+    console.log(error);
+  }
+}

package-lock.json

@@ -9,7 +9,9 @@
       "version": "1.0.0",
       "license": "ISC",
       "dependencies": {
+        "@types/axios": "^0.9.36",
         "cli-progress": "^3.12.0",
+        "dotenv": "^17.2.3",
         "electron": "^39.1.1",
         "express": "^5.1.0",
         "ffmpeg-static": "^5.2.0",
@@ -149,6 +151,12 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/@types/axios": {
+      "version": "0.9.36",
+      "resolved": "https://registry.npmjs.org/@types/axios/-/axios-0.9.36.tgz",
+      "integrity": "sha512-NLOpedx9o+rxo/X5ChbdiX6mS1atE4WHmEEIcR9NLenRVa5HoVjAvjafwU3FPTqnZEstpoqCaW7fagqSoTDNeg==",
+      "license": "MIT"
+    },
     "node_modules/@types/cacheable-request": {
       "version": "6.0.3",
       "resolved": "https://registry.npmjs.org/@types/cacheable-request/-/cacheable-request-6.0.3.tgz",
@@ -198,6 +206,7 @@
       "resolved": "https://registry.npmjs.org/@types/node/-/node-24.9.2.tgz",
       "integrity": "sha512-uWN8YqxXxqFMX2RqGOrumsKeti4LlmIMIyV0lgut4jx7KQBcBiW6vkDtIBvHnHIquwNfJhk8v2OtmO8zXWHfPA==",
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "undici-types": "~7.16.0"
       }
@@ -584,6 +593,18 @@
         "node": ">=0.3.1"
       }
     },
+    "node_modules/dotenv": {
+      "version": "17.2.3",
+      "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz",
+      "integrity": "sha512-JVUnt+DUIzu87TABbhPmNfVdBDt18BLOWjMUFJMSi/Qqg7NTYtabbvSNJGOJ7afbRuv9D/lngizHtP7QyLQ+9w==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://dotenvx.com"
+      }
+    },
     "node_modules/dunder-proto": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
@@ -1824,6 +1845,7 @@
       "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
       "dev": true,
       "license": "Apache-2.0",
+      "peer": true,
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"

package.json

@@ -1,6 +1,8 @@
 {
   "dependencies": {
+    "@types/axios": "^0.9.36",
     "cli-progress": "^3.12.0",
+    "dotenv": "^17.2.3",
     "electron": "^39.1.1",
     "express": "^5.1.0",
     "ffmpeg-static": "^5.2.0",

requirements.txt

@@ -0,0 +1,3 @@
+fastapi
+uvicorn
+pytest

scripts/commands.txt

@@ -1,5 +0,0 @@
-npx ts-node ./extract.ts /Users/mikehughes/Downloads/Testvideo/Kurzgesagt.mov
-npx ts-node ./transcribe.ts ../storage/audio/Kurzgesagt.wav
-
-npx ts-node ./extract.ts /Users/mikehughes/Downloads/Testvideo/GitLabMeeting.mov
-npx ts-node ./transcribe.ts ../storage/audio/GitLabMeeting.wav

scripts/extract.ts

@@ -1,23 +0,0 @@
-#!/usr/bin/env ts-node
-
-import { extractAudioFromVideo } from "../services/modules/extraction/ffmpegExtractor.ts";
-
-const videoPath = process.argv[2];
-
-if (!videoPath) {
-  console.error("Usage: ts-node extractAudio.ts <videoPath>");
-  process.exit(1);
-}
-
-(async () => {
-  try {
-    console.log(`Extracting audio from: ${videoPath}`);
-
-    await extractAudioFromVideo(videoPath); // Call the extraction function (ffmpegExtractor.ts in services/modules/extraction)
-
-    console.log("Audio extraction completed successfully.");
-  } catch (err) {
-    console.error("Audio extraction failed:", err);
-    process.exit(1);
-  }
-})();

scripts/transcribe.ts

@@ -1,18 +0,0 @@
-import { whisperLocal } from "../services/modules/transcription/local/whisperLocal.ts";
-
-const audioPath = process.argv[2];
-if (!audioPath) {
-  console.error("Please provide an audio file path as argument.");
-  process.exit(1);
-}
-
-const whisper = new whisperLocal();
-
-(async () => {
-  try {
-    const text = await whisper.transcribe(audioPath);
-    console.log(text);
-  } catch (err) {
-    console.error("Transcription failed:", err);
-  }
-})();

services/modules/llm-gemini/gemini.js

@@ -0,0 +1,76 @@
+const outputDir = path.join(__dirname, "../../../storage/documents"); //  path for output directory
+
+if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
+}
+
+// Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
+
+const GEMINI_API_KEY = process.env.GOOGLE_API_KEY; // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
+const GEMINI_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent"; //URL for the REST call, used model and action
+
+module.exports = {
+    name: "llm-gemini",
+    type: "llm",
+    displayname: "Gemini LLM",
+    description: "Generates documents using Google Gemini LLM",
+
+    async function(parameter) {
+        try {
+            console.log("Gemini LLM module invoked with parameters:", parameter);
+
+            await this.createDocumentFromTranscript( //Call the function to create document with transcript, document type and language
+                parameter.inputTranscriptPath, // Path to input transcript file
+                parameter.documentTypePath, // Path to document type file which is chosen in the front end by the user
+                parameter.language // Language for the document which is chosen in the front end by the user
+            );
+
+        } catch (error) {
+            console.error("Error in Gemini LLM module:", error);
+        }
+    },
+
+    createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
+        try {
+            const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
+            const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
+            const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed
+
+            // --- REST CALL ---
+            const response = await fetch(`${GEMINI_URL}?key=${GEMINI_API_KEY}`, { //safe model response in variable
+                method: "POST",
+                headers: {
+                    "Content-Type": "application/json"
+                },
+                body: JSON.stringify({
+                    contents: [
+                        {
+                            parts: [
+                                { text: promptText } // Input prompt for content generation
+                            ]
+                        }
+                    ]
+                })
+            });
+
+            if (!response.ok) { //ok is true when a responce was successfull
+                const text = await response.text();
+                throw new Error(`Gemini API error (${response.status}): ${text}`);
+            }
+
+            const data = await response.json();
+
+            // Get generated text from response or default to empty string (if null)
+            const output = data?.candidates?.[0]?.content?.parts?.[0]?.text || "";
+            let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file 
+            console.log(inputTranscriptName);
+            const outPath = path.join(outputDir, `${inputTranscriptName}.md`); // Output file path & name to make naming dynamic. Pulled from input transcript name
+            fs.writeFileSync(outPath, output, "utf8"); // Write output to file
+
+            console.log("Generated document written to:", outPath);
+
+        } catch (error) {
+            console.error("Error generating Gemini content:", error);
+        }
+    }
+};

services/modules/transcription-local/whisperLocal.ts

@@ -5,7 +5,7 @@ import { fileURLToPath } from "url"; // To handle __dirname in ES modules
 
 const __filename = fileURLToPath(import.meta.url); // Get current file path
 const __dirname = path.dirname(__filename); // Get current directory path
-const transcriptsDir = path.resolve(__dirname, "../../storage/transcriptions");
+const transcriptsDir = path.resolve(__dirname, "../../../storage/transcriptions");
 
 
 export class whisperLocal { // is called by transcribe.ts
@@ -26,7 +26,6 @@ export class whisperLocal { // is called by transcribe.ts
 
   async transcribe(audioPath: string): Promise<string> { //asyncronous function to transcribe audio
     return new Promise((resolve, reject) => {
-        const transcriptsDir = path.resolve(__dirname, "../../../../storage/transcripts"); //storage directory for transcripts
 
         if (!fs.existsSync(transcriptsDir)) { //if transcripts directory does not exist, create it
             fs.mkdirSync(transcriptsDir, { recursive: true });

services/modules/transcription-remote/assembly.ts

@@ -0,0 +1,133 @@
+import 'dotenv/config';
+import axios from 'axios';
+import fs from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const API_KEY = process.env.ASSEMBLYAI_API_KEY;
+const BASE_URL = 'https://api.assemblyai.com/v2';
+
+/**
+ * Uploads audio file to AssemblyAI
+ */
+async function uploadAudio(audioPath: string): Promise<string> {
+  const audioData = fs.readFileSync(audioPath);
+  
+  const response = await axios.post<{ upload_url: string }>(`${BASE_URL}/upload`, audioData, {
+    headers: {
+      'authorization': API_KEY,
+      'content-type': 'application/octet-stream'
+    }
+  });
+  
+  return response.data.upload_url;
+}
+
+/**
+ * Extract a session id (basename without extension) from a local path or a URL
+ */
+function getSessionId(inputPath: string): string {
+  try {
+    const parsed = new URL(inputPath);
+    const base = path.basename(parsed.pathname);
+    return base.replace(/\.[^.]+$/, '');
+  } catch (err) {
+    // not a URL, treat as local path
+    return path.basename(inputPath, path.extname(inputPath));
+  }
+}
+
+/**
+ * Creates transcription job with speaker diarization
+ */
+async function createTranscript(audioUrl: string): Promise<string> {
+  const response = await axios.post<{ id: string }>(`${BASE_URL}/transcript`, {
+    audio_url: audioUrl,
+    speaker_labels: true,
+    language_detection: true
+  }, {
+    headers: {
+      'authorization': API_KEY,
+      'content-type': 'application/json'
+    }
+  });
+  
+  return response.data.id;
+}
+
+/**
+ * Polls transcript status until completed
+ */
+async function pollTranscript(transcriptId: string): Promise<any> {
+  while (true) {
+    const response = await axios.get<any>(`${BASE_URL}/transcript/${transcriptId}`, {
+      headers: { 'authorization': API_KEY }
+    });
+    
+    const status = response.data.status;
+    
+    if (status === 'completed') {
+      return response.data;
+    } else if (status === 'error') {
+      throw new Error(`Transcription failed: ${response.data.error}`);
+    }
+    
+    // Wait 3 seconds before next poll
+    await new Promise(resolve => setTimeout(resolve, 3000));
+  }
+}
+
+/**
+ * Saves transcript to storage
+ */
+function saveTranscript(transcript: any, sessionId: string): void {
+  const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');
+  
+  if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true });
+  }
+  
+  const outputPath = path.join(outputDir, `${sessionId}.json`);
+  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
+  
+  console.log(`✅ Transcript saved: ${outputPath}`);
+}
+
+export default {
+  name: "assembly",
+  type: "transcription",
+  displayname: "AssemblyAI",
+  run: async (audioPath: string) => {
+    try {
+      // Determine if audioPath is an external URL or a local file
+      let audioUrl: string;
+      if (/^https?:\/\//i.test(audioPath)) {
+        console.log('🔗 Using external audio URL...');
+        audioUrl = audioPath;
+      } else {
+        console.log('🔄 Uploading local audio...');
+        if (!fs.existsSync(audioPath)) {
+          throw new Error(`Audio file not found: ${audioPath}`);
+        }
+        audioUrl = await uploadAudio(audioPath);
+      }
+      
+      console.log('🔄 Creating transcript job...');
+      const transcriptId = await createTranscript(audioUrl);
+      
+      console.log('⏳ Waiting for transcription...');
+      const transcript = await pollTranscript(transcriptId);
+      
+  const sessionId = getSessionId(audioPath);
+      saveTranscript(transcript, sessionId);
+      
+      return transcript;
+    } catch (error: any) {
+      console.error('❌ Transcription error:', error.message);
+      throw error;
+    }
+  }
+};

services/pipeline/jobs/transcribeLatest.ts

@@ -0,0 +1,52 @@
+// services/pipeline/jobs/transcribeLatest.ts
+import path from 'path';
+import fs from 'fs';
+import assembly from '../../modules/transcription/assembly';
+
+/**
+ * Finds the most recently modified .wav file in storage/audio/
+ */
+function getLatestWav(): string {
+  const audioDir = path.join(process.cwd(), 'storage', 'audio');
+  const files = fs.readdirSync(audioDir).filter(f => f.toLowerCase().endsWith('.wav'));
+  if (files.length === 0) throw new Error('⚠️ No .wav file found in storage/audio');
+
+  const newest = files
+    .map(f => ({ f, t: fs.statSync(path.join(audioDir, f)).mtimeMs }))
+    .sort((a, b) => b.t - a.t)[0].f;
+
+  return path.join(audioDir, newest);
+}
+
+/**
+ * Full transcription pipeline according to the defined workflow:
+ * 1. Audio Upload → AssemblyAI
+ * 2. Job Creation (transcript_id)
+ * 3. Polling Status (queued → processing → completed)
+ * 4. Download Transcript JSON
+ * 5. Storage: /transcripts/{session_id}.json
+ */
+async function main() {
+  const audioPath = getLatestWav();
+
+  console.log('1️⃣ Audio Upload → AssemblyAI');
+  console.log('   Source:', audioPath);
+
+  console.log('2️⃣ Job Creation (transcript_id)');
+  console.log('3️⃣ Polling Status (queued → processing → completed)');
+  console.log('4️⃣ Download Transcript JSON');
+  console.log('5️⃣ Storage: /transcripts/{session_id}.json');
+
+  // Execute the transcription process via the AssemblyAI module
+  const result = await assembly.run(audioPath);
+
+  console.log('✅ Transcription completed successfully');
+  console.log('🆔 Transcript ID:', result.id);
+  console.log('📁 Transcript file saved under: storage/transcripts/');
+}
+
+// Entry point
+main().catch((err) => {
+  console.error('❌ Transcription pipeline failed:', err.message || err);
+  process.exit(1);
+});

test/integration/assembly.test.js

@@ -0,0 +1,14 @@
+import 'dotenv/config';
+import assemblyModule from '../../services/modules/transcription-remote/assembly.ts';
+
+// Test: URL passed as argument OR local file ./storage/audio/test.wav
+const audioPath = process.argv[2] || './storage/audio/test.wav';
+
+assemblyModule.run(audioPath)
+  .then(result => {
+    console.log('✅ Success!');
+    console.log('Transcript ID:', result.id);
+  })
+  .catch(error => {
+    console.error('❌ Error:', error?.message || error);
+  });

test/integration/gemini/documentType.json

@@ -0,0 +1,39 @@
+
+**Goal:** Generate a structured meeting report (Markdown). **Output ONLY:** final .md. No meta.
+
+```json
+{
+  "FORMAT": "markdown",
+
+  "STRUCTURE": {
+    "titlepage": ["title","date","start","end","duration","location","host","participants"],
+    "toc": "[section](#anchor) — HH:MM:SS",
+    "section": {
+      "h2": "<topic> — HH:MM:SS",
+      "summary": "1 sentence",
+      "key_points": "<=5 bullets, quotes optional",
+      "decisions": "list: text | owner | due",
+      "actions": "table: id | task | owner | due | status"
+    },
+    "exec_summary": "3 short sentences",
+    "consolidated": ["decisions", "actions"],
+    "appendix": "optional"
+  },
+
+  "STYLE": {
+    "tone": "neutral, concise",
+    "ts_format": "HH:MM:SS",
+    "no_meta": true
+  },
+
+  "PROCESS": {
+    "timestamps": "use if present; else estimate minimal",
+    "speakers": "use labels; else Speaker X",
+    "long_transcripts": "chunk → summarize → merge",
+    "unclear": "UNKLAR:<reason>"
+  },
+
+  "JSON_OUTPUT_OPTIONAL": true,
+
+  "PROMPT_SNIPPET": "Generate meeting report in markdown using STRUCTURE and STYLE. Output only the report."
+}

test/integration/gemini/test-gemini.js

@@ -0,0 +1,7 @@
+const gemini = require("../../../services/modules/llm-gemini/gemini.js");
+
+gemini.function({
+    inputTranscriptPath: "./transcript.json",
+    documentTypePath: "./documentType.json",
+    language: "de"
+});

test/integration/gemini/transcript.json

@@ -0,0 +1,122 @@
+[
+  {
+    "speaker": "A",
+    "sentence": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter DeCarlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Good morning, Professor.",
+    "start": 240,
+    "end": 26560
+  },
+  {
+    "speaker": "B",
+    "sentence": "Good morning.",
+    "start": 28060,
+    "end": 28620
+  },
+  {
+    "speaker": "A",
+    "sentence": "So what is it about the conditions right now that have caused this round of wildfires to affect so many people so far away?",
+    "start": 29100,
+    "end": 37100
+  },
+  {
+    "speaker": "B",
+    "sentence": "Well, there's a couple of things. The season has been pretty dry already, and then the fact that we're getting hit in the US is because there's a couple weather systems that are essentially channeling the smoke from those Canadian wildfires through Pennsylvania into the mid Atlantic and the Northeast and kind of just dropping the smoke there.",
+    "start": 39100,
+    "end": 55820
+  },
+  {
+    "speaker": "A",
+    "sentence": "So what is it in this haze that makes it harmful? And I'm assuming it is harmful.",
+    "start": 56590,
+    "end": 60670
+  },
+  {
+    "speaker": "B",
+    "sentence": "It is, it is. The levels outside right now in Baltimore are considered unhealthy. And most of that is due to what's called particulate matter, which are tiny particles, microscopic, smaller than the width of your hair, that can get into your lungs and impact your respiratory system, your cardiovascular system, and even your neurological, your brain.",
+    "start": 62350,
+    "end": 82590
+  },
+  {
+    "speaker": "A",
+    "sentence": "What makes this particularly harmful? Is it the volume of particulate? Is it something in particular? What is it exactly? Can you just drill down on that a little bit more?",
+    "start": 83630,
+    "end": 92190
+  },
+  {
+    "speaker": "B",
+    "sentence": "Yeah. So the concentration of particulate matter, I was looking at some of the monitors that we have was reaching levels of what are, in science speak, 150 micrograms per meter cubed, which is more than 10 times what the annual average should be in about four times higher than what you're supposed to have on a 24 hour average. And so the concentrations of these particles in the air are just much, much, much higher than we typically see. And exposure to those high levels can lead to a host of health problems.",
+    "start": 93550,
+    "end": 123350
+  },
+  {
+    "speaker": "A",
+    "sentence": "And who is most vulnerable? I noticed that in New York City, for example, they're canceling outdoor activities. And so here it is in the early days of summer and they have to keep all the kids inside. So who tends to be vulnerable in a situation like this?",
+    "start": 123430,
+    "end": 135990
+  },
+  {
+    "speaker": "B",
+    "sentence": "It's the youngest. So children, obviously, whose bodies are still developing, the elderly who are, you know, their bodies are more in decline and they're more susceptible to the health impacts of breathing, the poor air quality. And then people who have pre existing health conditions, people with respiratory conditions or heart conditions, can be triggered by high levels of air pollution.",
+    "start": 137610,
+    "end": 156650
+  },
+  {
+    "speaker": "A",
+    "sentence": "Could this get worse?",
+    "start": 157450,
+    "end": 158650
+  },
+  {
+    "speaker": "B",
+    "sentence": "That's a good question. I mean, I think if in some areas it's much worse than others and it just depends on kind of where the smoke is concentrated. I think New York has some of the higher concentrations right now, but that's going to change as that air moves away from the New York area. But over the course of the next few days, we will see different areas being hit at different times with the highest concentrations.",
+    "start": 162170,
+    "end": 183420
+  },
+  {
+    "speaker": "A",
+    "sentence": "I was going to ask you about.",
+    "start": 183740,
+    "end": 184660
+  },
+  {
+    "speaker": "B",
+    "sentence": "More fires start burning. I don't expect the concentrations to go up too much higher.",
+    "start": 184660,
+    "end": 189020
+  },
+  {
+    "speaker": "A",
+    "sentence": "I was going to ask you how and you started to answer this, but how much longer could this last? Forgive me if I'm asking you to speculate, but what do you think?",
+    "start": 189100,
+    "end": 196220
+  },
+  {
+    "speaker": "B",
+    "sentence": "Well, I think the fires are going to burn for a little bit longer. But the key for us in the US Is the weather system changing. Right now it's the weather systems that are pulling that air into our Mid Atlantic and Northeast region. As those weather systems change and shift, we'll see that smoke going elsewhere and not impact us in this region as much. I think that's going to be the defining factor. I think the next couple days we're going to see a shift in that weather pattern and start to push the smoke away from where we are.",
+    "start": 198280,
+    "end": 227480
+  },
+  {
+    "speaker": "A",
+    "sentence": "And finally, with the impacts of climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences or circumstances?",
+    "start": 227930,
+    "end": 239850
+  },
+  {
+    "speaker": "B",
+    "sentence": "I mean, that is one of the predictions for climate change. Looking into the future, the fire season is starting earlier and lasting longer and we're seeing more frequent fires. So yeah, this is probably something that we'll be seeing more, more frequently. This tends to be much more of an issue in the western U.S. so the eastern U.S. getting hit right now is a little bit new. But yeah, I think with climate change moving forward, this is something that is going to happen more frequently.",
+    "start": 241370,
+    "end": 267570
+  },
+  {
+    "speaker": "A",
+    "sentence": "That's Peter DeCarlo, associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Professor DeCarlo, thanks so much for joining us and sharing this expertise with us.",
+    "start": 267970,
+    "end": 278210
+  },
+  {
+    "speaker": "B",
+    "sentence": "Thank you for having me.",
+    "start": 279410,
+    "end": 280530
+  }
+]

test/test_health.py

@@ -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