Skip to content

Latest commit

 

History

History
62 lines (48 loc) · 1.99 KB

create_provider.md

File metadata and controls

62 lines (48 loc) · 1.99 KB

Create Provider with AI Tool

Call in your terminal the create_provider script:

python -m etc.tool.create_provider
  1. Enter your name for the new provider.
  2. Copy and paste the cURL 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

  1. Check out the current list of potential providers, or find your own provider source!
  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://chat-gpt.com"
    working               = True
    supports_gpt_35_turbo = True

    @classmethod
    async def create_async_generator(
        cls,
        model: str,
        messages: Messages,
        proxy: str = None,
        **kwargs
    ) -> AsyncResult:
        yield ""
  1. Here, you can adjust the settings, for example, if the website does support streaming, set supports_stream to True...
  2. 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
  3. Add the Provider Import in g4f/Provider/__init__.py
from .HogeService import HogeService

__all__ = [
  HogeService,
]
  1. You are done !, test the provider by calling it:
import g4f

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

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