chatgpt-mirai-qq-bot
chatgpt-mirai-qq-bot copied to clipboard
Published
20 hours ago •
lss233
lss233
Go-cqhttp版本 API 模式无法连上OpenAI
提交 issue 前，请先确认：
- [x] 我已看过 FAQ，此问题不在列表中
- [x] 我已看过其他 issue，他们不能解决我的问题
- [x] 我认为这不是 Mirai 或者 OpenAI 的 BUG
表现
描述 BUG 的表现情况
同样的配置，在Mirai版本，API是正常使用，在Go-cqhttp下连接不上"api.openai.com"
运行环境:
- 操作系统：CentOS
- Docker： ？
- 项目版本：？
复现步骤
描述你是如何触发这个 BUG 的
- Go to '...'
- Click on '....'
- Scroll down to '....'
- See error
预期行为
描述你认为正常情况下应该看见的情况
截图
Warning: running as root
2023-03-11 17:18:14,706 Warning: cannot enable SSH socket upgrades
2023-03-11 17:18:14,706 No module named 'paramiko'
2023-03-11 17:18:14,706 created tcp socket '0.0.0.0:14500'
2023-03-11 17:18:14,708 no uinput module (not usually needed)
2023-03-11 17:18:16,165 pointer device emulation using XTest
2023-03-11 17:18:16,214 serving html content from '/usr/share/xpra/www'
2023-03-11 17:18:16,216 wrote pid 8 to '/tmp/0/server.pid'
2023-03-11 17:18:16,234 Warning: socket directory '/tmp/0'
2023-03-11 17:18:16,234 expected permissions 700 but found 750
2023-03-11 17:18:16,234 Warning: some of the sockets are in an unknown state:
2023-03-11 17:18:16,234 /run/user/1000/xpra/VM-4-13-centos-0
2023-03-11 17:18:16,235 /tmp/0/socket
2023-03-11 17:18:16,235 please wait as we allow the socket probing to timeout
2023-03-11 17:18:22,244 created unix domain socket '/run/user/1000/xpra/VM-4-13-centos-0'
2023-03-11 17:18:22,244 created unix domain socket '/tmp/0/socket'
2023-03-11 17:18:22,244 xvfb pid=12
2023-03-11 17:18:22,301 Warning: cannot watch for application menu changes without pyinotify:
2023-03-11 17:18:22,302 No module named 'pyinotify'
2023-03-11 17:18:22,309 Warning: cannot load menu data
2023-03-11 17:18:22,309 No module named 'xdg'
2023-03-11 17:18:22,318 Warning: webcam forwarding is disabled
2023-03-11 17:18:22,318 the virtual video directory '/sys/devices/virtual/video4linux' was not found
2023-03-11 17:18:22,318 make sure that the 'v4l2loopback' kernel module is installed and loaded
2023-03-11 17:18:22,318 or use the 'webcam=no' option
2023-03-11 17:18:22,318 found 0 virtual video devices for webcam forwarding
2023-03-11 17:18:22,321 started command `xterm -e python bot.py 2>&1 | tee /tmp/log.txt` with pid 54
2023-03-11 17:18:22,428 7.5GB of system memory
2023-03-11 17:18:22,541 waiting for initialization thread to complete
2023-03-11 17:18:22,542 xpra is ready.
2023-03-11 17:18:22,542 xpra X11 seamless version 4.4.3-r0 64-bit
2023-03-11 17:18:22,543 uid=0 (root), gid=0 (root)
2023-03-11 17:18:22,543 running with pid 8 on Linux Debian 11 bullseye
2023-03-11 17:18:22,552 connected to X11 display :0 with 24 bit colors
2023-03-11 17:18:22,979 OpenGL is supported on display ':0'
2023-03-11 17:18:22,979 using 'llvmpipe (LLVM 11.0.1, 256 bits)' renderer
2023-03-11 17:18:23.590 | ERROR | config:scan_presets:264 - 检查预设：正常 <==> presets/default.txt [失败：文件不存在]
2023-03-11 17:18:23.590 | SUCCESS | config:scan_presets:262 - 检查预设：猫娘 <==> presets/catgirl.txt [成功]
2023-03-11 17:18:23.591 | SUCCESS | config:scan_presets:275 - 注册预设：catgirl <==> ./presets/catgirl.txt [成功]
2023-03-11 17:18:23.591 | SUCCESS | config:scan_presets:275 - 注册预设：预设模板 <==> ./presets/预设模板.txt [成功]
2023-03-11 17:18:23.591 | INFO | __main__::10 - 检测到 Onebot 配置，将以 Onebot 模式启动……
2023-03-11 17:18:23.961 | INFO | manager.bot:login_openai:107 - 正在登录第 1 个 OpenAI 账号
2023-03-11 17:18:23.961 | INFO | manager.bot:__login_openai_apikey:247 - 尝试使用 api_key 登录中...
2023-03-11 17:18:23.962 | INFO | manager.bot:__check_proxy:169 - 正在检查代理配置：http://127.0.0.1:10809
2023-03-11 17:18:25.579 | SUCCESS | manager.bot:login_openai:122 - 登录成功！
2023-03-11 17:18:25.579 | SUCCESS | manager.bot:login_openai:139 - 成功登录 1/1 个 OpenAI 账号！
2023-03-11 17:18:25.579 | INFO | manager.bot:login:78 - AI 类型：chatgpt-web - 可用账号： 0 个
2023-03-11 17:18:25.580 | INFO | manager.bot:login:78 - AI 类型：openai-api - 可用账号： 1 个
2023-03-11 17:18:25.580 | INFO | manager.bot:login:78 - AI 类型：bing-cookie - 可用账号： 0 个
[2023-03-11 17:18:25 +0000] [63] [INFO] Running on http://0.0.0.0:8554 (CTRL + C to quit)
2023-03-11 17:18:25,582 - hypercorn.error - INFO - info - Running on http://0.0.0.0:8554 (CTRL + C to quit)
* Serving Quart app ''
* Environment: production
* Please use an ASGI server (e.g. Hypercorn) directly in production
* Debug mode: False
* Running on http://0.0.0.0:8554 (CTRL + C to quit)
[2023-03-11 17:20:38 +0000] [63] [INFO] 127.0.0.1:11426 GET /ws 1.1 101 - 993
2023-03-11 17:20:58.783 | DEBUG | middlewares.concurrentlock:handle_request:40 - [Concurrent] 排队中，前面还有 0 个人！
2023-03-11 17:20:58.784 | DEBUG | middlewares.concurrentlock:handle_request:42 - [Concurrent] 排到了！
2023-03-11 17:20:58.788 | DEBUG | middlewares.timeout:create_timeout_task:12 - [Timeout] 开始计时……
2023-03-11 17:21:04.957 | ERROR | universal:request:147 - HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by ConnectTimeoutError(, 'Connection to api.openai.com timed out. (connect timeout=None)'))
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/urllib3/connection.py", line 174, in _new_conn
conn = connection.create_connection(
│ └
└
File "/usr/local/lib/python3.11/site-packages/urllib3/util/connection.py", line 95, in create_connection
raise err
└ TimeoutError(110, 'Connection timed out')
File "/usr/local/lib/python3.11/site-packages/urllib3/util/connection.py", line 85, in create_connection
sock.connect(sa)
│ └ ('2001::adfc:4a0c', 443, 0, 0)
└ None
TimeoutError: [Errno 110] Connection timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
│ └
└
File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 386, in _make_request
self._validate_conn(conn)
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 1042, in _validate_conn
conn.connect()
│ └
└
File "/usr/local/lib/python3.11/site-packages/urllib3/connection.py", line 363, in connect
self.sock = conn = self._new_conn()
│ │ │ └
│ │ └
│ └ None
└
File "/usr/local/lib/python3.11/site-packages/urllib3/connection.py", line 179, in _new_conn
raise ConnectTimeoutError(
└
urllib3.exceptions.ConnectTimeoutError: (, 'Connection to api.openai.com timed out. (connect timeout=None)')
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.11/site-packages/requests/adapters.py", line 489, in send
resp = conn.urlopen(
│ └
└
File "/usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py", line 787, in urlopen
retries = retries.increment(
│ └
└ Retry(total=0, connect=None, read=False, redirect=None, status=None)
File "/usr/local/lib/python3.11/site-packages/urllib3/util/retry.py", line 592, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
│ │ │ │ │ └ 'unknown'
│ │ │ │ └
│ │ │ └ ConnectTimeoutError(, 'Connection to api.openai.com timed out. (...
│ │ └ '/v1/chat/completions'
│ └
└
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by ConnectTimeoutError(, 'Connection to api.openai.com timed out. (connect timeout=None)'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/bot.py", line 11, in
import onebot_bot
File "", line 1178, in _find_and_load
File "", line 1149, in _find_and_load_unlocked
File "", line 690, in _load_unlocked
File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "/app/onebot_bot.py", line 177, in
bot.run(host=config.onebot.reverse_ws_host, port=config.onebot.reverse_ws_port)
│ │ │ │ │ │ │ └ 8554
│ │ │ │ │ │ └ Onebot(qq=, manager_qq=, reverse_ws_host='0.0.0.0', reverse_ws_port=8554)
│ │ │ │ │ └
│ │ │ │ └ '0.0.0.0'
│ │ │ └ Onebot(qq=, manager_qq=, reverse_ws_host='0.0.0.0', reverse_ws_port=8554)
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/aiocqhttp/__init__.py", line 222, in run
self._server_app.run(host=host, port=port, *args, **kwargs)
│ │ │ │ │ │ └ {'use_reloader': False}
│ │ │ │ │ └ ()
│ │ │ │ └ 8554
│ │ │ └ '0.0.0.0'
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/quart/app.py", line 1423, in run
loop.run_until_complete(asyncio.gather(*tasks))
│ │ │ │ └ [
│ │ └
│ └
└ <_UnixSelectorEventLoop running=True closed=False debug=False>
File "/usr/local/lib/python3.11/asyncio/base_events.py", line 640, in run_until_complete
self.run_forever()
│ └
└ <_UnixSelectorEventLoop running=True closed=False debug=False>
File "/usr/local/lib/python3.11/asyncio/base_events.py", line 607, in run_forever
self._run_once()
│ └
└ <_UnixSelectorEventLoop running=True closed=False debug=False>
File "/usr/local/lib/python3.11/asyncio/base_events.py", line 1922, in _run_once
handle._run()
│ └
└ )>
File "/usr/local/lib/python3.11/asyncio/events.py", line 80, in _run
self._context.run(self._callback, *self._args)
│ │ │ │ │ └
│ │ │ │ └ )>
│ │ │ └
│ │ └ )>
│ └
└ )>
File "/app/onebot_bot.py", line 91, in _
await handle_message(response, f"friend-{event.user_id}", msg.display, chain)
│ │ │ │ └ MessageChain([Plain(text='test')])
│ │ │ └
│ │ └ MessageChain([Plain(text='test')])
│ └ .response at 0x7f7b6f6a5620>
└
File "/app/universal.py", line 155, in handle_message
await action(session_id, message.strip(), conversation_context, respond)
│ │ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ │ └ None
│ │ │ └
│ │ └ 'test'
│ └ 'friend-'
└ .wrap_request..call at 0x7f7b6f6a6200>
File "/app/universal.py", line 47, in call
await m.handle_request(session_id, message, respond, conversation_context, n)
│ │ │ │ │ │ └ .wrap_request..call at 0x7f7b6f6a6160>
│ │ │ │ │ └ None
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ 'test'
│ │ └ 'friend-'
│ └
└
File "/app/middlewares/concurrentlock.py", line 43, in handle_request
await action(session_id, prompt, conversation_context, respond)
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ None
│ │ └ 'test'
│ └ 'friend-'
└ .wrap_request..call at 0x7f7b6f6a6160>
File "/app/universal.py", line 47, in call
await m.handle_request(session_id, message, respond, conversation_context, n)
│ │ │ │ │ │ └ .wrap_request..call at 0x7f7b6f6a60c0>
│ │ │ │ │ └ None
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ 'test'
│ │ └ 'friend-'
│ └
└
File "/app/middlewares/middleware.py", line 9, in handle_request
await action(session_id, prompt, conversation_context, respond)
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ None
│ │ └ 'test'
│ └ 'friend-'
└ .wrap_request..call at 0x7f7b6f6a60c0>
File "/app/universal.py", line 47, in call
await m.handle_request(session_id, message, respond, conversation_context, n)
│ │ │ │ │ │ └ .wrap_request..call at 0x7f7b6f6a6020>
│ │ │ │ │ └ None
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ 'test'
│ │ └ 'friend-'
│ └
└
File "/app/middlewares/ratelimit.py", line 25, in handle_request
await action(session_id, prompt, conversation_context, respond)
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ None
│ │ └ 'test'
│ └ 'friend-'
└ .wrap_request..call at 0x7f7b6f6a6020>
File "/app/universal.py", line 47, in call
await m.handle_request(session_id, message, respond, conversation_context, n)
│ │ │ │ │ │ └ .request at 0x7f7b6f6a5f80>
│ │ │ │ │ └ None
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ 'test'
│ │ └ 'friend-'
│ └
└
File "/app/middlewares/timeout.py", line 30, in handle_request
await action(session_id, prompt, conversation_context, respond)
│ │ │ │ └ .respond at 0x7f7b6f6a5ee0>
│ │ │ └ None
│ │ └ 'test'
│ └ 'friend-'
└ .request at 0x7f7b6f6a5f80>
> File "/app/universal.py", line 114, in request
async for rendered in task:
└
File "/app/conversation.py", line 85, in ask
async for item in self.adapter.ask(prompt):
│ │ │ └ 'test'
│ │ └
│ └
└
File "/app/adapter/chatgpt/api.py", line 66, in ask
raise resp
└ ConnectTimeout(MaxRetryError("HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/c...
File "/app/adapter/chatgpt/api.py", line 49, in ask_sync
for resp in self.bot.ask_stream(prompt, role=self.hashed_user_id):
│ │ │ │ │ └ 'user-878b7bbebc9cde9b'
│ │ │ │ └
│ │ │ └ 'test'
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/revChatGPT/V3.py", line 81, in ask_stream
response = self.session.post(
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 635, in post
return self.request("POST", url, data=data, json=json, **kwargs)
│ │ │ │ │ └ {'headers': {'Authorization': 'Bearer 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'}, 'stream': True}
│ │ │ │ └ {'model': 'gpt-3.5-turbo', 'messages': [{'role': 'system', 'content': 'You are ChatGPT, a large language model trained by Ope...
│ │ │ └ None
│ │ └ 'https://api.openai.com/v1/chat/completions'
│ └
└
File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
│ │ │ └ {'timeout': None, 'allow_redirects': True, 'proxies': OrderedDict(), 'stream': True, 'verify': True, 'cert': None}
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
│ │ │ └ {'timeout': None, 'proxies': OrderedDict(), 'stream': True, 'verify': True, 'cert': None}
│ │ └
│ └
└
File "/usr/local/lib/python3.11/site-packages/requests/adapters.py", line 553, in send
raise ConnectTimeout(e, request=request)
│ └
└
requests.exceptions.ConnectTimeout: HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by ConnectTimeoutError(, 'Connection to api.openai.com timed out. (connect timeout=None)'))
其他内容
Mirai版的可以正常使用，Go-cqhttp版本连接超时
@lss233 您看这段：
2023-03-11 17:18:23.961 | INFO | manager.bot:login_openai:107 - 正在登录第 1 个 OpenAI 账号
2023-03-11 17:18:23.961 | INFO | manager.bot:__login_openai_apikey:247 - 尝试使用 api_key 登录中...
2023-03-11 17:18:23.962 | INFO | manager.bot:__check_proxy:169 - 正在检查代理配置：http://127.0.0.1:10809
2023-03-11 17:18:25.579 | SUCCESS | manager.bot:login_openai:122 - 登录成功！
2023-03-11 17:18:25.579 | SUCCESS | manager.bot:login_openai:139 - 成功登录 1/1 个 OpenAI 账号！
我认为我的网络环境是OK的，我还试过access_token了，Mirai版本下我可以登录ChatGPT账号，在Go-cqhttp版本连接不上，配置文件上，我只是把[Mirai]改成了[onebot]，补充了一下反向代理的东西，其他的没动，我感觉是Go-cqhttp版本版本没有获取到系统代理
@lss233 大大，我研究了一下，从我v2ray的访问记录来看，目前的API key方法好像不会走系统代理，导致国内机器没办法用，我用以下方法创建docker就成功了:
docker run --name mirai-chatgpt-bot -e XPRA_PASSWORD=1 -e HTTP_PROXY="http://127.0.0.1:10809" -e HTTPS_PROXY="http://127.0.0.1:10809" -v /usr/local/config.cfg:/app/config.cfg --network host lss233/chatgpt-mirai-qq-bot:browser-version
你在容器里 IP 是隔离的，不能用 127.0.0.1 这个地址。
他这个设置确实有问题，不过确实是不走代理的，同样环境下，web可以走代理，但是api不走代理，那个api的代理配置文件，只有验证的时候走一下，用的时候不走代理
