-
Notifications
You must be signed in to change notification settings - Fork 184
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
test_net 时测试 openai 库失败 #10
Comments
挂上梯子可以打开 gpt测试外网环境(vscode 调试正常)
测试openai库(调试失败)
|
貌似你openai一分钟请求超过3次,请求太频繁了,openai有频率限制 |
可以使用 https://aigc2d.com 这个平台,支持GPT3.5 GPT4.0接口 |
我的也是一样,你有解决吗? |
Retrying langchain.llms.openai.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised APIConnectionError: Error communicating with OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/completions (Caused by SSLError(SSLError(1, '[SSL: SSLV3_ALERT_HANDSHAKE_FAILURE] sslv3 alert handshake failure (_ssl.c:1131)'))). |
我的提示这个,一直失败 |
|
那设置里要更改吗?没看到更改接口地址的地方 |
需要改下代码 |
请问一下更改哪个代码,没找到,谢谢 |
|
manager.py # 测试openai库
llm = OpenAI(temperature=config.temperature, openai_api_key=get_openai_key(), verbose=config.debug,openai_api_base="https://api.aigc2d.com") core/vup.py chat = ChatOpenAI(temperature=config.temperature, max_retries=2, max_tokens=150,
openai_api_key=get_openai_key(),openai_api_base="https://api.aigc2d.com") 如果不行就把 https://api.aigc2d.com 换成 https://api.aigc2d.com/v1 然后需要把 config.sample.ini 里的 api_key 换成 aigc2d平台的 apikey |
是在这两个代码里添加这行代码是吧。我试试,谢谢 |
还需要把 config.ini 里的 proxy 改为空
|
openai_api_base 的值改成 https://api.aigc2d.com/v1 |
显示成功了,但是又有一个问题 During handling of the above exception, another exception occurred: Traceback (most recent call last): |
python manager.py action |
ModuleNotFoundError: No module named 'pymilvus' 应该是没有安装 pymilvus 这个包 |
装了 后面提示 这个 During handling of the above exception, another exception occurred: Traceback (most recent call last): |
那还有安装 milvus 数据库,看代码是需要这个数据库,配置文件里也有这个milvus host 配置 |
都有安装 During handling of the above exception, another exception occurred: Traceback (most recent call last): |
pymilvus.client.exceptions.BaseException: <BaseException: (code=2, message=Fail connecting to server on xxxxxx:19530. Timeout)> 都有安装 ,那就配置好 milvus 正确的主机地址
|
好复杂,好难弄 麻烦问一下这个要怎么配置呢?完全不懂 |
PS C:\Users\63568\Desktop\GPT-vup> & 'C:\Users\63568\AppData\Local\Microsoft\WindowsApps\python3.11.exe' 'c:\Users\63568.vscode\extensions\ms-python.python-2023.10.0\pythonFiles\lib\python\debugpy\adapter/../..\debugpy\launcher' '53845' '--' 'C:\Users\63568\Desktop\GPT-vup\src\manager.py' 'run' 'bilibili'
Retrying langchain.llms.openai.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Your access was terminated due to violation of our policies, please check your email for more information. If you believe this is in error and would like to appeal, please contact us through our help center at help.openai.com..
Retrying langchain.llms.openai.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Your access was terminated due to violation of our policies, please check your email for more information. If you believe this is in error and would like to appeal, please contact us through our help center at help.openai.com..
Retrying langchain.llms.openai.completion_with_retry.._completion_with_retry in 4.0 seconds as it raised RateLimitError: Your access was terminated due to violation of our policies, please check your email for more information. If you believe this is in error and would like to appeal, please contact us through our help center at help.openai.com..
Retrying langchain.llms.openai.completion_with_retry.._completion_with_retry in 8.0 seconds as it raised RateLimitError: Your access was terminated due to violation of our policies, please check your email for more information. If you believe this is in error and would like to appeal, please contact us through our help center at help.openai.com..
PS C:\Users\63568\Desktop\GPT-vup>
The text was updated successfully, but these errors were encountered: