> ## Documentation Index
> Fetch the complete documentation index at: https://docs.g4f.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Contribute

> How to contribute to G4F

<b>Create Provider with AI Tool</b>

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

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.

<b>Create provider without AI tools</b>

<Note>
  List of  list of potential providers available <a href="https://github.com/zukixa/cool-ai-stuff">here</a>
</Note>

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

```python theme={null}
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:

```python theme={null}
from .YourProviderName import YourProviderName

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

__all__ = [
    YourProviderName,
]
```

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

```python theme={null}
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='')
```