Originally: A proof of concept to know if an AI can answer any question about any user reading all their timeline.
At the end: Get an abbreviated description made by an AI of you based on your latest tweets. What do other users perceive from what you tweet?
You can do several things, like:
Some limits you must be aware of:
If you have any question or you find a bug, please, let me know. If you want to contribute, go ahead and do it. If you want to do something similar with that code, DM me for help; especially if you belong to an underrepresented group in technology. I might not answer, but if I have time, I am willing to help.
You can adapt this code to use any database or server. In my case, I use firebase, so this is a guide to make it work in firebase.
Create a firebase project in https://console.firebase.google.com
Add it as default in your project:
firebase use --addcd functionscp .env-example .envEdit ".env" file and add your own API keys (from twitter and openAI)
Use node 16. I usually use NVM in order to use different node versions.
nvm usenpm installChange the ROLE_SYSTEM and the prompt, in following files:
In your root folder again
cd ..Add a "service-account.json" for firebase database connection.
Run an emulator
firebase emulators:startThe rest of this, I leave it to you!
MIT License. Read LICENSE.md
It is not mandatory to notify me if you use this code, but it would be great to know that you use it.
Thanks @dianait_ for the abbreviame logo.