中国，代理用的是v2ray N，shadowsocks和vmess都试过了，都不行。
located in China, use the v2rayN as the proxy software, tried both shadowsocks and vmess nodes, none of them worked
给powershell配置了proxy
1. set the proxy for the powershell
如果开启代理，那么运行python visual_chatgpt.py --load "ImageCaptioning_cuda:0,Text2Image_cuda:0"时，会报如下错误：
2. with the vpn on, if I runpython visual_chatgpt.py --load "ImageCaptioning_cuda:0,Text2Image_cuda:0", it will give the error below:
SSLError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url:
/Salesforce/blip-image-captioning-base/resolve/main/preprocessor_config.json (Caused by SSLError(SSLEOFError(8, 'EOF occurred in
violation of protocol (_ssl.c:1131)')))
所以，只能不开代理先把模型load起来，以及网页服务器跑起来； [thus, I have to turn off the vpn, and let the model and the web server run first]
如果不开启代理，进入0.0.0.0:1015后，输入prompt后，无法连接OpenAI服务器，报如下错误：
3. but if I turn off the VPN, after I tried prompting in the local web server, it tells me thatapi.openai.comcannot be reached
Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x000001CDEA35C4C0>: 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。')).
Retrying langchain.llms.openai.completion_with_retry.<locals>._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 NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x000001CDEA35CE20>: 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。')).
请问有人遇到过类似问题吗？如何解决的呢？
is there anyone could provide a solution?
MaJining92
commented
1 year ago
中国，代理用的是v2ray N，shadowsocks和vmess都试过了，都不行。
located in China, use the v2rayN as the proxy software, tried both shadowsocks and vmess nodes, none of them worked具体问题描述：
win10，已经配置好了各种环境，安装好了requirements中的包
0. requirements.txt installed给powershell配置了proxy
1. set the proxy for the powershell如果开启代理，那么运行
python visual_chatgpt.py --load "ImageCaptioning_cuda:0,Text2Image_cuda:0"时，会报如下错误：2. with the vpn on, if I runpython visual_chatgpt.py --load "ImageCaptioning_cuda:0,Text2Image_cuda:0", it will give the error below:所以，只能不开代理先把模型load起来，以及网页服务器跑起来； [thus, I have to turn off the vpn, and let the model and the web server run first]
0.0.0.0:1015后，输入prompt后，无法连接OpenAI服务器，报如下错误：3. but if I turn off the VPN, after I tried prompting in the local web server, it tells me thatapi.openai.comcannot be reached请问有人遇到过类似问题吗？如何解决的呢？
is there anyone could provide a solution?