返回提交历史
Modified
README.md
+4
-4
XFEstudio/gpt4free
docs(README): current available link Provider path
acdcad31
代码差异
1 个文件
+4
-4
@@ -327,7 +327,7 @@ python -m g4f.api
327
327
```py
328
328
import openai
329
329
330
openai.api_key = "Empty if you don't use embeddings, otherwise your hugginface token"
330
openai.api_key = "Empty if you don't use embeddings, otherwise your Hugging Face token"
331
331
openai.api_base = "http://localhost:1337/v1"
332
332
333
333
@@ -546,8 +546,8 @@ python etc/tool/create_provider.py
546
546
#### Create Provider
547
547
548
548
1. Check out the current [list of potential providers](https://github.com/zukixa/cool-ai-stuff#ai-chat-websites), or find your own provider source!
549
2. Create a new file in [g4f/provider](./g4f/provider) with the name of the Provider
550
3. Implement a class that extends [BaseProvider](./g4f/provider/base_provider.py).
549
2. Create a new file in [g4f/Provider](./g4f/Provider) with the name of the Provider
550
3. Implement a class that extends [BaseProvider](./g4f/Provider/base_provider.py).
551
551
552
552
```py
553
553
from __future__ import annotations
@@ -573,7 +573,7 @@ class HogeService(AsyncGeneratorProvider):
573
573
574
574
4. Here, you can adjust the settings, for example, if the website does support streaming, set `supports_stream` to `True`...
575
575
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
576
6. Add the Provider Name in [g4f/provider/**init**.py](./g4f/provider/__init__.py)
576
6. Add the Provider Name in [g4f/Provider/**init**.py](./g4f/Provider/__init__.py)
577
577
578
578
```py
579
579
from .HogeService import HogeService