[本地部署]: 本地部署报超时

[KrystalandBarry]

是否已存在现有反馈与解答？

• 我确认没有已有issue或discussion，且已阅读常见问题。

是否是一个代理配置相关的疑问？

• 我确认这不是一个代理配置相关的疑问。

错误描述

本地部署后，改了apikey，能正常启动，但对话报超时

复现操作

本地部署后，改了apikey，能正常启动，但对话报超时

错误日志

Traceback (most recent call last):
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
    conn = connection.create_connection(
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/util/connection.py", line 95, in create_connection
    raise err
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/util/connection.py", line 85, in create_connection
    sock.connect(sa)
TimeoutError: [Errno 60] Operation timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 715, in urlopen
    httplib_response = self._make_request(
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 404, in _make_request
    self._validate_conn(conn)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 1058, in _validate_conn
    conn.connect()
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connection.py", line 363, in connect
    self.sock = conn = self._new_conn()
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connection.py", line 179, in _new_conn
    raise ConnectTimeoutError(
urllib3.exceptions.ConnectTimeoutError: (<urllib3.connection.HTTPSConnection object at 0x122583700>, 'Connection to openaipublic.blob.core.windows.net timed out. (connect timeout=None)')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
    resp = conn.urlopen(
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 799, in urlopen
    retries = retries.increment(
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/urllib3/util/retry.py", line 592, in increment
    raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /encodings/cl100k_base.tiktoken (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x122583700>, 'Connection to openaipublic.blob.core.windows.net timed out. (connect timeout=None)'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/modules/models/base_model.py", line 668, in predict
    for chatbot, status_text in iter:
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/modules/models/base_model.py", line 347, in stream_next_chatbot
    user_token_count = self.count_token(inputs)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/modules/models/OpenAI.py", line 62, in count_token
    input_token_count = count_token(construct_user(user_input))
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/modules/utils.py", line 164, in count_token
    encoding = tiktoken.get_encoding("cl100k_base")
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/tiktoken/registry.py", line 73, in get_encoding
    enc = Encoding(**constructor())
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/tiktoken_ext/openai_public.py", line 72, in cl100k_base
    mergeable_ranks = load_tiktoken_bpe(
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/tiktoken/load.py", line 147, in load_tiktoken_bpe
    contents = read_file_cached(tiktoken_bpe_file, expected_hash)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/tiktoken/load.py", line 64, in read_file_cached
    contents = read_file(blobpath)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/tiktoken/load.py", line 25, in read_file
    resp = requests.get(blobpath)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/requests/api.py", line 73, in get
    return request("get", url, params=params, **kwargs)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/requests/api.py", line 59, in request
    return session.request(method=method, url=url, **kwargs)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
    resp = self.send(prep, **send_kwargs)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
    r = adapter.send(request, **kwargs)
  File "/Users/dingtao/work/hpr/ai/code/ChuanhuChatGPT/venv/lib/python3.10/site-packages/requests/adapters.py", line 507, in send
    raise ConnectTimeout(e, request=request)
requests.exceptions.ConnectTimeout: HTTPSConnectionPool(host='openaipublic.blob.core.windows.net', port=443): Max retries exceeded with url: /encodings/cl100k_base.tiktoken (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x122583700>, 'Connection to openaipublic.blob.core.windows.net timed out. (connect timeout=None)'))

运行环境

- OS: 
- Browser: 
- Gradio version: 
- Python version:

补充说明

No response

[Keldos-Li]

连接问题，参考 #5.
可以尝试检查 urllib 库和代理配置。

另，这类问题应该在discussion中提问

[KrystalandBarry]

好的，这个我之前也看了，版本对应urllib也按照那个issue的改了，但还是不行

[KrystalandBarry]

改了urllib版本，换了美国的ip，也还是不行

[Keldos-Li]

奇怪了，但大概总是某个环境的问题……