search

CatchTheTornado / doctor-dok

Doctor Dok is an AI based medical data framework and patient's med vault. Parse any health related PDF/Image to JSON and then use Chat GPT / LLama to discuss it! WARNING: Don't decide on your health based on AI Chat - it's just for Research purposes.
http://doctordok.com
MIT License
46 stars 8 forks source link

[feat] Add audio transcription #136

Closed pkarw closed 2 months ago

pkarw commented 2 months ago

https://github.com/chengsokdara/use-whisper

In this case we additionally need to change how parse is done to use the record text instead of only attachments - in this case probably with a different prompt (?)

pkarw commented 2 months ago

We need to display again re-parse (https://github.com/CatchTheTornado/doctor-dok/commit/53013ba1b9e7d1535f94d67bbcaf3ec10f79de92) and change how parseQueue is being managed in record-item

pkarw commented 2 months ago

Let's store the audio transcription in the record.extra[].type='transcription'