6cff6b9981
Merge branch 'develop' into 'feature/38-sprecher-audio-snippets-s4-11'
...
# Conflicts:
# main.js
2025-12-16 16:18:17 +01:00
0003d99041
extract speaker snippets mit main verknüpft.
2025-12-16 15:32:31 +01:00
04b2457ca3
Changes to the LLMs to return a Promise (outp path) and main now calls the export process
2025-12-15 17:58:03 +01:00
a8c284edd2
Merge branch 'feature/30-backend-export-funktion-des-dokuments-in-verschiedene-datei-formate-s4-05' into 'develop'
...
Feature/30 backend export funktion des dokuments in verschiedene datei formate s4 05
See merge request proj-wise2526-video2document/video2document!43
2025-12-15 15:03:36 +01:00
3a5808d97c
Merge branch 'develop' into feature/30-backend-export-funktion-des-dokuments-in-verschiedene-datei-formate-s4-05
2025-12-15 14:41:28 +01:00
405a32098c
Remove success and error icons from console log messages for consistency
2025-12-15 14:15:40 +01:00
1683502aa1
Merge branch 'develop' into 'feature/35-backend-llm-chat-gpt-integration-s4-10'
...
# Conflicts:
# services/modules/llm-gemini/gemini.js
2025-12-15 14:07:32 +01:00
ec57411992
Refactor document generation to output HTML format and update system instructions for clarity
2025-12-15 13:53:14 +01:00
271fe78b7b
Changed the module to use puppeteer and html-to-docx
2025-12-14 18:14:16 +01:00
1e38cc79f4
Extended the Role description
2025-12-14 16:53:35 +01:00
746fec05d4
Changed model from llama to quen3 because llama was timing out due to token limit
2025-12-14 16:28:48 +01:00
5ea8ec6a1a
Merge branch 'feature/implementation-of-ci-s4-09' into 'develop'
...
implemented first CI pipeline version with a test test that only checks if 1...
See merge request proj-wise2526-video2document/video2document!34
2025-12-13 14:13:06 +01:00
7cd334645f
Added a module that safes the file in a requested format.
2025-12-11 14:22:04 +01:00
15e2e35bda
Merge branch 'feature/35-backend-llm-chat-gpt-integration-s4-10' into 'develop'
...
Feature/35 backend llm chat gpt integration s4 10
See merge request proj-wise2526-video2document/video2document!35
2025-12-11 13:30:14 +01:00
53508b175a
changed Display name
2025-12-11 13:27:00 +01:00
2b597add6c
fixed a unicode bug
2025-12-11 13:03:04 +01:00
3af038d195
Multiple AI models implemented - chatgpt, llama
2025-12-11 12:41:11 +01:00
b546c96238
Refactor code structure for improved readability and maintainability
2025-12-11 12:08:07 +01:00
emily
faee605f12
Initial version of the working CI pipeline
...
Added mocha based unit tests for each module
Did a bit of cleanup in the modules to remove debug console.log calls
Removed the Progress bar in the extractor and the library requirement
Promisified the gemini module to make sure it returns the path as a promise instead of just on the cli
Fixed gitignore so that it now only ignores the content int the storage directories, and not the whole directories
Added neetingReport.json for the LLMs to use
2025-12-09 22:07:43 +01:00
emily
f858f2edbb
added functionality for transcription tool to tell the frontend what audio format to use
2025-12-05 15:58:17 +01:00
425e24853e
Similar to the Gemini LLM we now have a ChatGPT REST call. The API Key is still missing
2025-12-04 10:58:50 +01:00
84cc94aa34
REST API & Auto Naming
2025-11-26 21:55:19 +01:00
9ab98825a2
made it so that the transcript summary file name is not hardcoded anymore
2025-11-24 17:24:08 +01:00
emily
9a0a349813
Switched to transcription summarizer2 due to a better output format
2025-11-24 17:01:49 +01:00
emily
9dfc05e987
Fixed Transcription Summarizer, and now the whole pipeline works (except for LLM, because we need the keys for that)
2025-11-24 16:51:48 +01:00
a5a60635fc
worked on fixing the code
2025-11-24 16:40:12 +01:00
emily
812bca8cfb
working on implementing everything
...
Currently getting stuck on the assembly module as assembly ai for some fucking reason blocks me from making any requests
This includes making a new user account
2025-11-24 15:35:32 +01:00
emily
34d644d7d7
Merge commit '2f5efee9c7f81cadc22f033f9ba20bb5cbc2d66e' into develop
2025-11-24 14:41:10 +01:00
2f5efee9c7
Summarizer und weiters angepasst
2025-11-24 14:27:49 +01:00
465fe8bd41
Summarizer angepasst
2025-11-24 14:25:29 +01:00
emily
474e587ff2
Added functionality to group modules for frontend
2025-11-24 12:53:05 +01:00
emily
c2f22b3525
merged Mikes code for the google gemini module
...
included the requires libraries in the package.json
implemented the library into requires.js
cleaned up ffmpeg from the events
2025-11-24 12:12:46 +01:00
emily
6257ad05a8
Merge commit '4ade9575f33fd353522a07abe2f60e2d1be6feb4' into feature/modular-ipc-system-implementation
2025-11-24 12:08:35 +01:00
emily
bf7438b753
cleaned up ffmpegextractor.js
2025-11-24 12:07:54 +01:00
emily
868945fb92
Merge commit '925eb33eab45c084e9386ada66d9cb14b966e312' into feature/modular-ipc-system-implementation
2025-11-24 12:06:58 +01:00
a0ed2ab7bd
feat(extraction): add audio_ready event emission
...
- Add EventEmitter to emit audio_ready when extraction completes
- Pass sessionId and audioPath in event data
- Export audioEvents for Main process orchestrator
Refs: S3-06 AC1,AC3,AC7
2025-11-20 14:05:52 +01:00
b87bfd444d
Test erstellt
2025-11-20 13:27:15 +01:00
97b571b7f9
Einbindung des Summarizer
2025-11-20 11:51:34 +01:00
455147a41b
Summarizer Tool erstellt zur zusammenfassung der vom TranskriptionTool kommenden json
2025-11-20 10:15:11 +01:00
a178ccf30f
Added comments to my code to make it more understandable
2025-11-18 19:53:19 +01:00
a1d804f463
Test created and changes to gemini.js file
2025-11-18 19:16:51 +01:00
8e7e0b5043
Implement Gemini LLM module for document generation (first non tested prototype)
2025-11-17 21:16:50 +01:00
emily
4dc53b9d5f
implemented first version of the modular IPC system
2025-11-17 18:00:04 +01:00
6083773f88
New Folder structure
2025-11-15 14:45:13 +01:00
emily
d9eacafc3a
fixed the program by moving the example module back to where the program can ACTUALLY load it
2025-11-14 14:28:11 +01:00
9254ddc57f
Changed the Folder Structure for better maintainability
2025-11-13 17:34:22 +01:00
c021272ca4
merge: Resolve conflicts with develop
2025-11-13 15:22:33 +01:00
e7e97a7f60
feat(S2-02b): Implement AssemblyAI external transcription with speaker diarization
...
- Add assembly.ts module for REST API transcription via AssemblyAI
- Implement 5-step pipeline: upload → create job → poll status → download → save
- Enable speaker_labels for diarization (Speaker A, B, C...)
- Add millisecond-precision timestamps for each utterance
- Store JSON transcripts in storage/transcripts/{session_id}.json
- Add axios, dotenv dependencies
- Add transcribeLatest.ts helper for quick testing
User Story: S2-02b - Externe Transkription per REST API
2025-11-13 13:07:18 +01:00
emily
94f390f28b
Implemented audio extractor into IPC call, sooooooo, frontend and backend are now officially linked successfully
2025-11-12 20:28:55 +01:00
emily
92043440fe
Combined Frontend with backend, and implemented the extractor function into the module structure
2025-11-10 16:18:57 +01:00
Spanier, Pit
santa
MikeHughes-BIN
Hughes, Mike
emily
Azeufack Noupeu Willy