python run_server.py --model_server dashscope不成功 about qwen-agent HOT 11 CLOSED

请问具体报错是怎么样的呢？

from qwen-agent.

File "/Users/weiguoliao/exgit/Qwen-Agent/qwen_server/app.py", line 334, in bot
for chunk in response:
File "/Users/weiguoliao/exgit/Qwen-Agent/qwen_agent/llm/base.py", line 80, in chat_dashscope_stream
for trunk in response:
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/dashscope/aigc/generation.py", line 113, in
return (GenerationResponse.from_api_response(rsp)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/dashscope/api_entities/http_request.py", line 77, in
return (item for item in response)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/dashscope/api_entities/http_request.py", line 225, in _handle_request
raise e
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/dashscope/api_entities/http_request.py", line 208, in _handle_request
response = session.post(url=self.url,
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/requests/sessions.py", line 637, in post
return self.request("POST", url, data=data, json=json, **kwargs)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
resp = self.send(prep, **send_kwargs)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
r = adapter.send(request, **kwargs)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/requests/adapters.py", line 486, in send
resp = conn.urlopen(
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/urllib3/connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/urllib3/connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/urllib3/connection.py", line 244, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "/Users/weiguoliao/miniconda3/lib/python3.10/http/client.py", line 1282, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/Users/weiguoliao/miniconda3/lib/python3.10/http/client.py", line 1323, in _send_request
self.putheader(hdr, value)
File "/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/urllib3/connection.py", line 224, in putheader
_HTTPConnection.putheader(self, header, *values)
File "/Users/weiguoliao/miniconda3/lib/python3.10/http/client.py", line 1255, in putheader
values[i] = one_value.encode('latin-1')
UnicodeEncodeError: 'latin-1' codec can't encode character '\u201c' in position 7: ordinal not in range(256)
/Users/weiguoliao/miniconda3/lib/python3.10/site-packages/gradio/helpers.py:818: UserWarning: Using the update method is deprecated. Simply return a new object instead, e.g. return gr.Textbox(...) instead of return gr.update(...) warnings.warn( /Users/weiguoliao/miniconda3/lib/python3.10/site-packages/gradio/components/textbox.py:163: UserWarning: Using the update method is deprecated. Simply return a new object instead, e.g. return gr.Textbox(...)instead ofreturn gr.Textbox.update(...)`.
warnings.warn(

from qwen-agent.

agent跑Mac上，跟平台应该没关系

from qwen-agent.

我曾经见过类似的报错（ https://stackoverflow.com/a/76278687 ），当时的情况是用户配置API_KEY的时候误输入了中文的双引号导致的。请确保您指定DASHSCOPE_API_KEY没有输入中文字符（实际上，英文双引号可能也是不需要的）。

比如，请写成：

export DASHSCOPE_API_KEY=sk-this-is-a-fake-api-12345

不要写成（含中文的双引号）：

export DASHSCOPE_API_KEY=“sk-this-is-a-fake-api-12345”

如果还不能解决，请尝试升级dashscope版本：

pip install "dashscope>=1.11.0"

from qwen-agent.

谢谢，APIKEY的问题解决了，但是，出现下面问题

Loading model from cache /var/folders/x0/pbvvtc5n4s1gq1jh0hfpz02h0000gn/T/jieba.cache
Loading model cost 0.312 seconds.
Prefix dict has been built successfully.
wordlist: ['你好']
wordlist: ['你好']
2
2
Now using dashscope api
Error code: DataInspectionFailed, error message: Input data may contain inappropriate content.
错误码: 数据检查失败，错误信息: 输入数据可能包含不适当的内容。

版本是最新的

pip list|grep dash
dashscope 1.11.0

from qwen-agent.

谢谢，APIKEY的问题解决了，但是，出现下面问题

Loading model from cache /var/folders/x0/pbvvtc5n4s1gq1jh0hfpz02h0000gn/T/jieba.cache Loading model cost 0.312 seconds. Prefix dict has been built successfully. wordlist: ['你好'] wordlist: ['你好'] 2 2 Now using dashscope api Error code: DataInspectionFailed, error message: Input data may contain inappropriate content. 错误码: 数据检查失败，错误信息: 输入数据可能包含不适当的内容。

版本是最新的

pip list|grep dash dashscope 1.11.0

这个应该是被平台的安全合规算法拦截了。产品初期比较谨慎，该算法可能较严，我正在反馈给相关同事。

from qwen-agent.

常见的被拦截的原因可能是因为网页、PDF的内容命中了一些特殊的关键词。我们还在看这部分体验怎么优化。

from qwen-agent.

可以了

from qwen-agent.

谢谢，APIKEY的问题解决了，但是，出现下面问题
Loading model from cache /var/folders/x0/pbvvtc5n4s1gq1jh0hfpz02h0000gn/T/jieba.cache Loading model cost 0.312 seconds. Prefix dict has been built successfully. wordlist: ['你好'] wordlist: ['你好'] 2 2 Now using dashscope api Error code: DataInspectionFailed, error message: Input data may contain inappropriate content. 错误码: 数据检查失败，错误信息: 输入数据可能包含不适当的内容。
版本是最新的
pip list|grep dash dashscope 1.11.0

这个应该是被平台的安全合规算法拦截了。产品初期比较谨慎，该算法可能较严，我正在反馈给相关同事。

那请问被拦截了该怎么解决呢？

from qwen-agent.

可以了

你好请问你是怎么解决这个问题的呀？我的也一直敏感

from qwen-agent.

有什么避开敏感词的方法吗，或者敏感词不输出，但是程序不断开？

from qwen-agent.