Across all OpenAI submodule settings, storing and maintaining the various settings is becoming increasingly important. Case in point:
Stumbled across this Youtube Video and am personally blown away by the observed improvement, particularly around making the ChatGPT want to write useful content with you interactively via repeated prompting.
https://www.youtube.com/watch?v=OgYQAS9LY3o
Suggest setting the default ChatGPT Profile description here:
https://git.drupalcode.org/project/openai/-/blob/1.0.x/modules/openai_ch...
To what is described in the video above:
I want you to become my prompt engineer. Your goal is to help me craft the best possible prompt for my needs. The prompt will be used by you, ChatGPT. You will follow the following process:
1. Your first response will be to ask me what the prompt should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps.
2. Based on my input, you will generate 2 sections. a) Revised prompt (provide your rewritten prompt. It should be clear, concise and easily understood by you), b) Questions (ask any relevant questions pertaining to what additional information is needed from me to improve the prompt)
3. We will continue this iteration process with me providing additional information to you and you updating the prompt in the Revised prompt section until I say we are done.
Just a thought! Naturally this larger profile has a bigger hit on the consumed tokens for the requests, and might not fit EVERYONES use cases, and has a slight learning curve (answer each question, one per line; replying with 'im done and write this' to finalize, etc), but the results with the output from ChatGPT are pretty freaking amazingly improved by getting more interactive with it.
@kevinquillen - interested to see where you want this type of submodule configuration to 'live' for OpenAI! The above would be my ChatGPT Profile setting for sure :)
Active
1.0
Code
Yes, understood. The first point of order was getting things up and out the door. Now that things are settling and we are seeing good use case areas.
It may make sense to allow 'several' configuration entities that serve as 'profiles' for certain endpoint usage. Sometimes you may want a certain model with certain token and certain temperature settings, or in ChatGPTs case, certain behavioral personas.