请求适配gpt-3.5-turbo模型

[letianpai-lpt]

就在今天，OPENai更新了gpt-3.5-turbo语言模型

[chrisyy2003]

在配置文件里可以自己指定语言模型的，d4e867c

[letianpai-lpt]

改了,这个在哪里改啊,找不见 发生错误: This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?

[letianpai-lpt]

希望你有在适配而不是在摸鱼）

[chrisyy2003]

？

[letianpai-lpt]

它这个模型的API地址变了，可能还有一些其他参数也有所调整，简而言之就是直接换模型会报错

[chrisyy2003]

add gpt-3.5-turbo, 9d562e0

用pip install nonebot-plugin-gpt3 -U，安装最新版

[letianpai-lpt]

报错如下 配置文件如下

会话如下

init文件修改过公共模式为true

[YipSzeho]

坏掉力

03-03 13:29:23 [INFO] nonebot | Event will be handled by Matcher(type='message', module=nonebot_plugin_gpt3)
03-03 13:29:23 [INFO] nonebot | Matcher(type='message', module=nonebot_plugin_gpt3) running complete
03-03 13:29:23 [ERROR] nonebot | Running Matcher(type='message', module=nonebot_plugin_gpt3) failed.
Traceback (most recent call last):
  File "<string>", line 17, in <module>
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/__init__.py", line 273, in run
    get_driver().run(*args, **kwargs)
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/drivers/fastapi.py", line 187, in run
    uvicorn.run(
  File "/root/nb/.venv/lib/python3.10/site-packages/uvicorn/main.py", line 569, in run
    server.run()
  File "/root/nb/.venv/lib/python3.10/site-packages/uvicorn/server.py", line 60, in run
    return asyncio.run(self.serve(sockets=sockets))
  File "/usr/lib/python3.10/asyncio/runners.py", line 44, in run
    return loop.run_until_complete(main)
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/message.py", line 141, in _check_matcher
    await _run_matcher(Matcher, bot, event, state, stack, dependency_cache)
> File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/message.py", line 187, in _run_matcher
    await matcher.run(bot, event, state, stack, dependency_cache)
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/internal/matcher/matcher.py", line 732, in run
    await self.simple_run(bot, event, state, stack, dependency_cache)
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/internal/matcher/matcher.py", line 707, in simple_run
    await handler(
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot/dependencies/__init__.py", line 108, in __call__
    return await cast(Callable[..., Awaitable[R]], self.call)(**values)
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot_plugin_gpt3/__init__.py", line 361, in handle_chat
    resp = await get_user_session(session_id).get_chat_response(msg, checker(event))
  File "/root/nb/.venv/lib/python3.10/site-packages/nonebot_plugin_gpt3/__init__.py", line 112, in get_chat_response
    logger.debug(res['usage'])
TypeError: string indices must be integers

[chrisyy2003]

试试1.1.3版 pip3 install nonebot-plugin-gpt3==1.1.3

[YipSzeho]

1.1.3读取不到key了

[chrisyy2003]

改了，再看看readme，有问题可以及时反馈

[hellfancy]

佬，和机器人聊天出现这个是不是api-key不行了

发生错误: 
Error communicating with OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): 
Max retries exceeded with url: 
/v1/chat/completions (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x00000223C140AD00>: 
Failed to establish a new connection: [WinError 10060]
 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。'))

[chrisyy2003]

佬，和机器人聊天出现这个是不是api-key不行了

发生错误: 
Error communicating with OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): 
Max retries exceeded with url: 
/v1/chat/completions (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x00000223C140AD00>: 
Failed to establish a new connection: [WinError 10060]
 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。'))

网络的问题，可能需要代理

[YipSzeho]

我也这样提示。之前好像直接可以用来着。大佬可以考虑加个代理设置吗・∀・

[chrisyy2003]

可，不过你可以先配置命令行代理，类似于这种

export https_proxy=http://127.0.0.1:6152;
export http_proxy=http://127.0.0.1:6152;
export all_proxy=socks5://127.0.0.1:6153

[YipSzeho]

okok

[hellfancy]

这个命令行代理要咋配啊佬，目前挂服务器和本地都出问题了，昨天白天还行的，晚上到现在就不行了QAQ

[chrisyy2003]

https://github.com/chrisyy2003/nonebot-plugin-gpt3/issues/31 增加了代理的配置，请查看最新的readme