Contribute

How to contribute to G4F

Create Provider with AI Tool

To create a Provider with AI tool you need cloned gpt4free repository, not PyPi version

Call in your terminal the “create_provider” script:

python etc/tool/create_provider.py

1. Enter your name for the new provider.
2. Copy and paste the URL command from your browser developer tools.
3. Let the AI create the provider for you.
4. Customize the provider according to your needs.

Create provider without AI tools

List of list of potential providers available here

1. Find provider.
2. Create a new file in g4f/Provider with the name of the Provider.
3. Implement a class that extends BaseProvider:

from __future__ import annotations

from ..typing import AsyncResult, Messages
from .base_provider import AsyncGeneratorProvider

class HogeService(AsyncGeneratorProvider):
    url                   = "https://your-base-url"
    supports_gpt_35_turbo = True
    working               = True

    @classmethod
    async def create_async_generator(
        cls,
        model: str,
        messages: Messages,
        proxy: str = None,
        **kwargs
    ) -> AsyncResult:
        yield ""

4. Here, you can adjust the settings, for example, if the website does support streaming, set supports_stream to True…

Name	Function
working	If this parameter set to True, this provider is active. Otherwise, provider will be thrown RuntimeError
supports_message_history	If this parameter set to True, this provider support message history
supports_gpt_35_turbo	If this parameter set to True, this provider support gpt-3.5-turbo
supports_gpt_4	If this parameter set to True, this provider support gpt-4
jailbreak	If this parameter set to True, this provider support emulation other models with special prompt

5. Write code to request the provider in create_async_generator and yield the response, even if it’s a one-time response, do not hesitate to look at other providers for inspiration
6. Add the Provider Name in g4f/Provider/init.py:

from .YourProviderName import YourProviderName

convert: dict[str, BaseProvider] = {
    "YourProviderName": YourProviderName,
}

__all__ = [
    YourProviderName,
]

7. You are done! Test your provider by calling it:

import g4f

response = g4f.ChatCompletion.create(model='gpt-3.5-turbo', provider=g4f.Provider.YourProviderName,
                                    messages=[{"role": "user", "content": "test"}], stream=g4f.Provider.YourProviderNameE.supports_stream)

for message in response:
    print(message, flush=True, end='')