SevaSk / ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.
https://github.com/SevaSk/ecoute
MIT License
5.85k stars 817 forks source link

Option to include prompts/documentation #4

Closed JhdChk closed 1 year ago

JhdChk commented 1 year ago

Hi,

First of all thank you for sharing this very interesting project.

I was wondering if it would be possible to add a prompt feature in order to guide chatgpt answering in a specific tone or with specific information etc. It would be also very interesting to include files upload too (pdf, csv) in order to give it some data and base the answers upon those files.

What do you think about that?

SevaSk commented 1 year ago

Thanks! It would certainly be possible. We have the prompt creation in the create_prompt method: https://github.com/SevaSk/ecoute/blob/main/prompts.py. You can modify that method to take addition information as well as the transcript.

SevaSk commented 1 year ago

Opened another issue related to improve the response generated https://github.com/SevaSk/ecoute/issues/12.