Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove API key dependencies by reverse engineer backend api's #36

Open
dikkietrom opened this issue May 14, 2023 · 6 comments
Open

Remove API key dependencies by reverse engineer backend api's #36

dikkietrom opened this issue May 14, 2023 · 6 comments

Comments

@dikkietrom
Copy link

for google use curl
for openAI check https://github.com/FlamingFury00/Free-AUTO-GPT-with-NO-API
or through nat.dev https://nat.dev 's backend api
wolfram "
news "

I can add more info when it is not clear how to go about it.

@philip06
Copy link
Contributor

I wouldn't remove API key dependencies for anything existing, APIs are always more reliable and faster. Also this wouldn't save you from configuration. Instead of an API key it'd be a cookie which you would have to keep changing or login credentials.

However, I think adding an integration to nat.dev is worth looking into to open up GPT-4 access.

@Cormanz
Copy link
Owner

Cormanz commented May 14, 2023

However, I think adding an integration to nat.dev is worth looking into to open up GPT-4 access.

I don't think this is a good idea unfortunately, nat.dev doesn't promote API use (although they technically don't prohibit it), and working with an unstable, and very-prone-to-rapid-changes API wouldn't be a great idea.

@dikkietrom
Copy link
Author

dikkietrom commented May 18, 2023

at this point I cannot use the api because i have no access, the goal is not perse to use nat.dev but to simply be able to use gpt4 for automations. OpenAI has an open backend api, it has no documentation though but it can be copied from the networkview. It gives back clean text, the formatting is post fetch. I would not mind giving it a shot myself and make a separate plugin if you can give me some direction. Ps the objective is not to replace anything but have it optional by plugin arch

@philip06
Copy link
Contributor

philip06 commented May 20, 2023

I looked at the ChatGPT backend, it's using an Authorization request header with a JWT. Meaning you might have trouble with the 25 message limit when testing. Something to consider.

See the LLMs folder for examples of what adding an LLM source would look like.

@dikkietrom
Copy link
Author

I wrote some stuff but I better consider this is your personal project that is meant to work for you and you only, and for reasons unknown you make it a github. At this point I cannot do anything with it but I will keep an eye on it to see where it is going.

@Cormanz
Copy link
Owner

Cormanz commented May 20, 2023

I wrote some stuff but I better consider this is your personal project that is meant to work for you and you only, and for reasons unknown you make it a github. At this point I cannot do anything with it but I will keep an eye on it to see where it is going.

The project is still solely maintained by me (although a lot of others have been helping a lot at this point), but it is a public project now and it should work for as many as we can.

Feel free to make a draft pull request for the code you wrote, I'll check it out.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants