就是chatgpt边回复的时候边输出，不要等它回复完再一起显示，这样可以更快阅读到回复的内容，以及知道它是否卡住/卡死

这个问题有点难搞，是个HTML/CSS问题。出于某种诡异的本地化考虑，"在系统语言为中文的浏览器上会显示为中文引号。

安装了安装了配置文件和gradio，仍报错：ModuleNotFoundError: No module named 'gradio'

返回错误信息：
raise error.APIConnectionError(
openai.error.APIConnectionError: Error communicating with OpenAI: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:1131)')))

我试过更换API KEY、使用全局代理都显示这个错误。

Chatgpt说：该代码中使用了Python的raise语句来抛出APIConnectionError异常，这是一个自定义的异常类，表示与OpenAI API通讯时发生了错误。其中的错误信息包括了请求的URL地址以及导致错误的具体原因。从错误信息中可以看出，这个异常是由OpenAI API返回的，表明与该API的通讯过程中出现了SSLError（SSL错误）的异常，而具体的错误原因是违反了SSL协议。因此，这是一个由于与OpenAI API通讯时出现SSL连接问题而导致的异常。

部署在阿里云华北服务器上,key认证一直过不去, 是api也被墙了吗?

您好，我部署在了国外的vps上，启动后发现ws连接都是超时的，知道是啥情况吗

在ChuanhuChatbot.py中设置my_api_key后，在网页中提示要验证APIkey，敲回车验证APIkey时出错，提示“发生了未知错误Orz”

运行 pip install gradio --upgrade --force-reinstall 遇到错误，求解

Building wheels for collected packages: orjson
Building wheel for orjson (pyproject.toml) ... error
error: subprocess-exited-with-error

× Building wheel for orjson (pyproject.toml) did not run successfully.
│ exit code: 1
╰─> [1462 lines of output]
Running maturin pep517 build-wheel -i c:\users\woshi\appdata\local\programs\python\python38-32\python.exe --compatibility off --target i686-pc-windows-msvc
馃摝 Including license file "C:\Users\woshi\AppData\Local\Temp\pip-install-l8q22sjy\orjson_67485430601d4ac5858f65d14f071b31\LICENSE-APACHE"
馃摝 Including license file "C:\Users\woshi\AppData\Local\Temp\pip-install-l8q22sjy\orjson_67485430601d4ac5858f65d14f071b31\LICENSE-MIT"
馃嵐 Building a mixed python/rust project
馃敆 Found pyo3-ffi bindings
馃悕 Found CPython 3.8 at c:\users\woshi\appdata\local\programs\python\python38-32\python.exe
Compiling target-lexicon v0.12.6
Compiling autocfg v1.1.0
Compiling once_cell v1.17.1
Compiling serde v1.0.152
Compiling version_check v0.9.4
Compiling rustversion v1.0.11
Compiling libc v0.2.139
Compiling itoa v1.0.5
Compiling cfg-if v1.0.0
Compiling ryu v1.0.12
Compiling cc v1.0.79
Compiling serde_json v1.0.93
Compiling num-traits v0.2.15
error: could not compile cfg-if due to 3 previous errors
warning: build failed, waiting for other jobs to finish...
error: could not compile itoa due to 10 previous errors
error: could not compile ryu due to 39 previous errors
error: could not compile once_cell due to 145 previous errors
馃挜 maturin failed
Caused by: Failed to build a native library through cargo
Caused by: Cargo build finished with "exit code: 101": "cargo" "rustc" "--release" "--target" "i686-pc-windows-msvc" "--manifest-path" "C:\\Users\\woshi\\AppData\\Local\\Temp\\pip-install-l8q22sjy\\orjson_67485430601d4ac5858f65d14f071b31\\Cargo.toml" "--message-format" "json" "--lib"
error[E0463]: can't find crate for core
|
= note: the i686-pc-windows-msvc target may not be installed
= help: consider downloading the target with rustup target add i686-pc-windows-msvc

  error[E0463]: can't find crate for `compiler_builtins`


  error: aborting due to 2 previous errors


  For more information about this error, try `rustc --explain E0463`.

  error[E0463]: can't find crate for `core`
    |
    = note: the `i686-pc-windows-msvc` target may not be installed
    = help: consider downloading the target with `rustup target add i686-pc-windows-msvc`


  error[E0463]: can't find crate for `compiler_builtins`


  error[E0463]: can't find crate for `core`

请问怎么合理的关闭服务，ctrl-C 会提示关闭中，再来一次看起来是退了，但是看起来会堵死，导致下次启动的时候报 getaddrinfo failed

生成的编程代码直接粘贴会报错，发现符号都成为了中文符号，需要手动替换，请在下个版本帮忙更新。

在个人搭建的服务器中通过服务器地址访问会直接进入聊天，能否在进入聊天之前，添加一个个人认证模块，用户名密码登录？

抱歉大佬，我确实是小白。
下载了py文件，本地修改好，cp到容器内，还是不行。
大佬的docker安装方法，能否加个目录映射。

感谢辛苦了。

下面是报错内容，麻烦up主了，谢谢您

chat_counter - 0
payload is - {'model': 'gpt-3.5-turbo', 'messages': [{'role': 'system', 'content': 'You are a helpful assistant.'}, {'role': 'user', 'content': '你好'}], 'temperature': 1, 'top_p': 1, 'n': 1, 'stream': True, 'presence_penalty': 0, 'frequency_penalty': 0}
Traceback (most recent call last):
  File "C:\Miniconda3\lib\site-packages\urllib3\connectionpool.py", line 696, in urlopen
    self._prepare_proxy(conn)
  File "C:\Miniconda3\lib\site-packages\urllib3\connectionpool.py", line 964, in _prepare_proxy
    conn.connect()
  File "C:\Miniconda3\lib\site-packages\urllib3\connection.py", line 364, in connect
    conn = self._connect_tls_proxy(hostname, conn)
  File "C:\Miniconda3\lib\site-packages\urllib3\connection.py", line 501, in _connect_tls_proxy
    socket = ssl_wrap_socket(
  File "C:\Miniconda3\lib\site-packages\urllib3\util\ssl_.py", line 453, in ssl_wrap_socket
    ssl_sock = _ssl_wrap_socket_impl(sock, context, tls_in_tls)
  File "C:\Miniconda3\lib\site-packages\urllib3\util\ssl_.py", line 495, in _ssl_wrap_socket_impl
    return ssl_context.wrap_socket(sock)
  File "C:\Miniconda3\lib\ssl.py", line 500, in wrap_socket
    return self.sslsocket_class._create(
  File "C:\Miniconda3\lib\ssl.py", line 1040, in _create
    self.do_handshake()
  File "C:\Miniconda3\lib\ssl.py", line 1309, in do_handshake
    self._sslobj.do_handshake()
ssl.SSLEOFError: EOF occurred in violation of protocol (_ssl.c:1129)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Miniconda3\lib\site-packages\requests\adapters.py", line 440, in send
    resp = conn.urlopen(
  File "C:\Miniconda3\lib\site-packages\urllib3\connectionpool.py", line 755, in urlopen
    retries = retries.increment(
  File "C:\Miniconda3\lib\site-packages\urllib3\util\retry.py", line 574, in increment
    raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:1129)')))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Miniconda3\lib\site-packages\gradio\routes.py", line 384, in run_predict
    output = await app.get_blocks().process_api(
  File "C:\Miniconda3\lib\site-packages\gradio\blocks.py", line 1032, in process_api
    result = await self.call_function(
  File "C:\Miniconda3\lib\site-packages\gradio\blocks.py", line 858, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Miniconda3\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Miniconda3\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "C:\Miniconda3\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "C:\Miniconda3\lib\site-packages\gradio\utils.py", line 448, in async_iteration
    return next(iterator)
  File "D:\Desktop\ChuanhuChatGPT-main\ChuanhuChatbot.py", line 99, in predict
    response = requests.post(API_URL, headers=headers,
  File "C:\Miniconda3\lib\site-packages\requests\api.py", line 117, in post
    return request('post', url, data=data, json=json, **kwargs)
  File "C:\Miniconda3\lib\site-packages\requests\api.py", line 61, in request
    return session.request(method=method, url=url, **kwargs)
  File "C:\Miniconda3\lib\site-packages\requests\sessions.py", line 529, in request
    resp = self.send(prep, **send_kwargs)
  File "C:\Miniconda3\lib\site-packages\requests\sessions.py", line 645, in send
    r = adapter.send(request, **kwargs)
  File "C:\Miniconda3\lib\site-packages\requests\adapters.py", line 517, in send
    raise SSLError(e, request=request)
requests.exceptions.SSLError: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:1129)')))

docker: Error response from daemon: invalid volume specification: '/root/chatGPThistory:app/history': invalid mount config for type "bind": invalid mount path: 'app/history' mount path must be absolute.

当第二次输入代码时，第一次对话的代码会自动加上非常多的
标签，然后超过token数，返回失败。

为啥这样啊大佬= = 第一次用 跟着教程搞得 就连powershell也是第一次弄
装好之后http://localhost:7860打开然后输入就弹出这个了
Something went wrong
Expecting value: line 1 column 1 (char 0)

在关闭网页之后，本次的对话就结束了，那么如何保存这次对话，让下次打开可以接着用呢？

我想使用nginx反向代理到127.0.0.1:7860，不知道是不是我的nginx配置问题，访问后返回{"detail":"Not Found"}，请问应该如何设置？

提示：

重新运行项目后可以正常访问，看报错是openai.error.APIConnectionError: Error communicating with OpenAI: ('Connection aborted.', ConnectionResetError(10054, '远程主机强迫关闭了一个现有的连接。', None, 10054, None))

遇到这个问题，账号是免费版本。免费的没法对接API吗

后端错误代码：
File "/usr/local/lib/python3.8/dist-packages/gradio/routes.py", line 384, in run_predict
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 1032, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 854, in call_function
raise ValueError("Need to enable queue to use generators.")
ValueError: Need to enable queue to use generators.
什么原因呢？
问了以下chatgpt说是enable_queue 没有设置为Ture也未能解决

Thanks for this project.

Everything seems to be functioning as expected, however, I am experiencing an issue with the save dialog. When I click on it, nothing happens. Interestingly, the loading dialog button works perfectly fine.

Just to keep you informed, I have been running the project using Docker, as I have been experiencing errors when attempting to run the project directly.

I have tried accessing the project on both Firefox and Chrome, and unfortunately, the issue persists on both browsers.

提示：
Something went wrong
Expecting value: 1ine 1 column 1 (char o)

安装依赖时报错，openai versions 最大我看只有0.10.5的版本没有大于0.27.0的版本

如题，小白不会弄，闲的时候看到了如果可以的话，教一下，视频没看明白，谢了

对于从环境变量和代码内部写入的秘钥, 请不要展示在 UI 界面上, 否则 别人可以通过F12更改 HTML password 来盗取 API key

When I set demo.launch(share=True)，the command line reminds me Could not create share link, please check your internet connection. However,My internet connection is fine,what sh

ould I do to solve this problem?

docker-compose 方便提供映射路径，将 API key、System prompt 和保留会话都保留在 NAS 硬盘存储。

另外，dockerhub 提示没有标签，不能直接通过群晖 Docker 下载。

咨询一下，浏览器打开一次地址，是一个聊天会话记录吗？
多人使用的话会是多个聊天会话吗？还是上下文会被干扰？

因为这个问题重装了urllib3也没解决，后来在b站评论里看到说要装1.25.11版本的，才终于搞定，下面是原评论：

如果有人也出现了openai.error.APIConnectionError提示的报错，那可能是urllib3的版本导致的。urllib3版本大于1.25.11，就会出现这个问题。

解决方案是卸载urllib3然后重装至1.25.11版本再重新运行一遍就可以

在终端或命令提示符中卸载urllib3
pip uninstall urllib3

然后，您可以通过使用指定版本号的pip install命令来安装所需的版本：
pip install urllib3==1.25.11

代码里就只改了 key

返回错误，检查API-key是否正确

运行一段时间后会报错
返回值：
异常：Expecting value: line 1 column 1 (char 0)

首先，十分感谢作者的开源，使我们可以更加方便的调用API。如下是部分代码：

def parse_text(text):
    lines = text.split("\n")
    for i,line in enumerate(lines):
        if "```" in line:
            items = line.split('`')
            if items[-1]:
                lines[i] = f'<pre><code class="{items[-1]}">'
            else:
                lines[i] = f'</code></pre>'
        else:
            if i > 0:
                line = line.replace("<", "&lt;")
                line = line.replace(">", "&gt;")
                lines[i] = '<br/>'+line.replace(" ", "&nbsp;")
    return "".join(lines)

关于上述代码，我发现在web中显示时，有时候会将符号<>转换为<、&gt;，空格显示转换为 。

1.这应该是由于chatGPT在给出回复时，```包裹的代码块中，HTML相关特殊字符部分是没有转义的，需要如上代码转义。但是非代码块部分，对于特殊字符，chatGPT的回复都会带上`，因此不应该对所有行的特殊字符进行替换，而是只替换代码块中的部分
2.我发现chatGPT的回复中，````包裹的代码块不一定会给出使用的语言（如c++），因此通过tems[-1]来判断是否会有问题？

如下是我更改后的代码，目前解决了我遇到的异常显示问题。

def parse_text(text):
    lines = text.split("\n")
    count = 0 // 用于判断'''符号是起始标志还是结束标志
    for i,line in enumerate(lines):
        if "```" in line:
            count += 1
            items = line.split('`')
            if count % 2 == 1:
                lines[i] = f'<pre><code class="{items[-1]}">'
            else:
                lines[i] = f'</code></pre>'
        else:
            if i > 0:
                if count % 2 == 1:
                    line = line.replace("&", "&amp;")
                    line = line.replace("\"", "&quot;")
                    line = line.replace("\'", "&apos;")
                    line = line.replace("<", "&lt;")
                    line = line.replace(">", "&gt;")
                    line = line.replace(" ", "&nbsp;")
                lines[i] = '<br/>'+line
    return "".join(lines)

如有错误请指正

https://github.com/f/awesome-chatgpt-prompts/blob/main/prompts.csv

不断显示连接失败，请检查网络连接，对话没有任何反应，这该怎么办？

if name == 'main':
text().run()会被变成if name == ‘main’:
text().run()，并且很多符号的输出都有问题。

目前 openai 已经被墙了, 请提供 socks5/http 代理接口让程序走代理来访问 openai API

最好想 API key 一样 可以通过 代码/环境变量/网页等多种形式来输入代理地址

问题描述

依赖冲突导致无法本地安装，使用了docker
但因为网络环境build不成功，我重新写了个dockerfile文件（换源，但针对arm处理器）。但是启动后发现，host模式不可用(docker不支持mac和win的host模式)，只能使用端口转发。但是并不清楚share所使用的端口号，无法实现公网访问功能。
另外建议提供一个docker-compose.yml，方便将日志和聊天记录输出到挂载点。

环境

macbook m1
docker
dockerfile
”“” Dockerfile
FROM ubuntu:20.04
RUN sed -i 's/ports.ubuntu.com/mirrors.ustc.edu.cn/g' /etc/apt/sources.list
RUN sed -i 's/focal/jammy/g' /etc/apt/sources.list
RUN apt-get update && apt-get install -y python3 python3-pip build-essential
RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple
RUN pip install openai gradio markdown
ENV PATH=/root/.local/bin:$PATH
COPY . /app
WORKDIR /app
ENV my_api_key empty
CMD ["python3", "-u", "ChuanhuChatbot.py", "2>&1", "|", "tee", "/var/log/application.log"]
“”“

输出

”“”
Running on local URL: http://0.0.0.0:80

Could not create share link. Please check your internet connection or our status page: https://status.gradio.app/
“”“

rt

能否在配置文件上增加代理功能？
例如Socks，只需IP：端口的形式就可以