XFE Git
XFE Studio Git
Git 首页 全局搜索
XFE 主站 文档 NuGet
公开
关注 0 Fork 0 Star 1
返回提交历史

XFEstudio/gpt4free

Update README.md

37dba12e
Vaibhav Chauhan <95951482+rover07@users.noreply.github.com>
提交于

代码差异

1 个文件 +6 -6
Modified README.md +6 -6
@@ -300,16 +300,16 @@ response = g4f.ChatCompletion.create(
300 300 print(f"Result:", response)
301 301 ```
302 302
303 ### interference openai-proxy api (use with openai python package)
303 ### interference openai-proxy API (use with openai python package)
304 304
305 #### run interference api from pypi package:
305 #### run interference API from pypi package:
306 306 ```py
307 307 from g4f.api import run_api
308 308
309 309 run_api()
310 310 ```
311 311
312 #### run interference api from repo:
312 #### run interference API from repo:
313 313 If you want to use the embedding function, you need to get a Hugging Face token. You can get one at https://huggingface.co/settings/tokens make sure your role is set to write. If you have your token, just use it instead of the OpenAI api-key.
314 314
315 315 run server:
@@ -539,7 +539,7 @@ Call in your terminal the "create_provider" script:
539 539 python etc/tool/create_provider.py
540 540 ```
541 541 1. Enter your name for the new provider.
542 2. Copy & Paste a cURL command from your browser developer tools.
542 2. Copy and paste a cURL command from your browser developer tools.
543 543 3. Let the AI ​​create the provider for you.
544 544 4. Customize the provider according to your needs.
545 545
@@ -571,8 +571,8 @@ class HogeService(AsyncGeneratorProvider):
571 571 yield ""
572 572 ```
573 573
574 4. Here, you can adjust the settings, for example if the website does support streaming, set `supports_stream` to `True`...
575 5. Write code to request the provider in `create_async_generator` and `yield` the response, _even if_ its a one-time response, do not hesitate to look at other providers for inspiration
574 4. Here, you can adjust the settings, for example, if the website does support streaming, set `supports_stream` to `True`...
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
576 576 6. Add the Provider Name in [g4f/provider/**init**.py](./g4f/provider/__init__.py)
577 577
578 578 ```py