AI 助理
备案控制台
开发者社区 阿里云百炼 正文

最近调接口总是 timeout

最近调阿里云百炼的 LLM API 总是报错，代码如下

llm = OpenAI(
                api_key=self.__api_key__,
                base_url=self.__api_base__,
                **kwargs
            )
llm.chat.completions.create(
        model=ctx.obj['model'],
        messages=[
            {'role': 'system', 'content': 'You are a helpful assistant.'},
            {'role': 'user', 'content': '请解释国债收益率和价格的关系？'}],
        )

不报错时输出：

2025-04-15 22:03:11,850 - httpx - INFO - HTTP Request: POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions "HTTP/1.1 200 OK"

Result: {"id":"chatcmpl-ec8a999f-d3ab-9f2c-947f-db706bab3794","choices":[{"finish_reason":"stop","index":0,"logprobs":null,"message":{"content":"我是通义千问，阿里巴巴集团旗下的超大规模语言模型。我能够回答问题、创作文字，如写故事、公文、技术文档等，还能进行逻辑推理、表达观点、玩游戏等。如果你有任何问题或需要帮助，欢迎随时告诉我！","refusal":null,"role":"assistant","annotations":null,"audio":null,"function_call":null,"tool_calls":null}}],"created":1744725792,"model":"qwen-turbo","object":"chat.completion","service_tier":null,"system_fingerprint":null,"usage":{"completion_tokens":55,"prompt_tokens":22,"total_tokens":77,"completion_tokens_details":null,"prompt_tokens_details":null}}

报错时输出：

2025-04-15 22:04:01,815 - openai._base_client - INFO - Retrying request to /chat/completions in 0.416089 seconds
2025-04-15 22:04:07,242 - openai._base_client - INFO - Retrying request to /chat/completions in 0.796980 seconds
Traceback (most recent call last):
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_transports/default.py", line 101, in map_httpcore_exceptions
    yield
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_transports/default.py", line 250, in handle_request
    resp = self._pool.handle_request(req)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpcore/_sync/connection_pool.py", line 256, in handle_request
    raise exc from None
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpcore/_sync/connection_pool.py", line 236, in handle_request
    response = connection.handle_request(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpcore/_sync/http_proxy.py", line 316, in handle_request
    stream = stream.start_tls(**kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpcore/_sync/http11.py", line 376, in start_tls
    return self._stream.start_tls(ssl_context, server_hostname, timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpcore/_backends/sync.py", line 154, in start_tls
    with map_exceptions(exc_map):
         ^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/python@3.12/3.12.8/Frameworks/Python.framework/Versions/3.12/lib/python3.12/contextlib.py", line 158, in __exit__
    self.gen.throw(value)
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpcore/_exceptions.py", line 14, in map_exceptions
    raise to_exc(exc) from exc
httpcore.ConnectTimeout: _ssl.c:983: The handshake operation timed out

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 955, in _request
    response = self._client.send(
               ^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_client.py", line 914, in send
    response = self._send_handling_auth(
               ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_client.py", line 942, in _send_handling_auth
    response = self._send_handling_redirects(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_client.py", line 979, in _send_handling_redirects
    response = self._send_single_request(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_client.py", line 1014, in _send_single_request
    response = transport.handle_request(request)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_transports/default.py", line 249, in handle_request
    with map_httpcore_exceptions():
         ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/python@3.12/3.12.8/Frameworks/Python.framework/Versions/3.12/lib/python3.12/contextlib.py", line 158, in __exit__
    self.gen.throw(value)
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/httpx/_transports/default.py", line 118, in map_httpcore_exceptions
    raise mapped_exc(message) from exc
httpx.ConnectTimeout: _ssl.c:983: The handshake operation timed out

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/tzhu/work/lab/caspian/analyze.py", line 306, in <module>
    llm_analysis()
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/click/core.py", line 1161, in __call__
    return self.main(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/click/core.py", line 1082, in main
    rv = self.invoke(ctx)
         ^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/click/core.py", line 1697, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/click/core.py", line 1443, in invoke
    return ctx.invoke(self.callback, **ctx.params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/click/core.py", line 788, in invoke
    return __callback(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context(), *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/analyze.py", line 285, in test
    completion = llm.chat.completions.create(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 279, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 914, in create
    return self._post(
           ^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1242, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 919, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 964, in _request
    return self._retry_request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1057, in _retry_request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 964, in _request
    return self._retry_request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1057, in _retry_request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/tzhu/work/lab/caspian/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 974, in _request
    raise APITimeoutError(request=request) from err
openai.APITimeoutError: Request timed out.

以上错误不定期出现，出错概率在 80%以上

试过以下的所有模型：

    DEEPSEEK_R1 = 'deepseek-r1'
    DEEPSEEK_V3 = 'deepseek-v3'
    QWEN_MAX_LATEST = 'qwen-max-latest'
    QWEN_MAX = 'qwen-max'
    QWEN_OMNI_TURBO = 'qwen-omni-turbo-latest'
    QWEN_OMNI_TURBO_2025_01_19 = 'qwen-omni-turbo-2025-01-19'
    QWEN_MAX_2025_01_25 = 'qwen-max-2025-01-25'
    QWEN_PLUS = 'qwen-plus'
    QWEN_PLUS_LATEST = 'qwen-plus-latest'
    QWEN_PLUS_2025_01_25 = 'qwen-plus-2025-01-25'
    QWQ_PLUS = 'qwq-plus'
    QWEN_TURBO = 'qwen-turbo'
    QWEN2_5_VL_72B_INSTRUCT = 'qwen2.5-vl-72b-instruct'
    QWEN2_5_14B_INSTRUCT_1M = 'qwen2.5-14b-instruct-1m'

展开
收起
1907705034155180 2025-04-15 22:14:12 57 分享 版权

版权声明：本文内容由阿里云实名注册用户自发贡献，版权归原作者所有，阿里云开发者社区不拥有其著作权，亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容，填写侵权投诉表单进行举报，一经查实，本社区将立刻删除涉嫌侵权内容。

0 条回答
写回答
取消 提交回答
问答分类：
API 大模型服务平台百炼
问答地址：
开发者社区 > 阿里云百炼 > 问答
相关问答
OSS的endpoint如何查看
33389
5
0
如果购买了域名，一定要备案才能用吗
41626
38
0
this xml file does not appear to have any style in
40973
10
0
配置了安全组规则，端口还是无法访问
29798
23
0
阿里云服务器如何重置系统？
22919
4
0
请问nacos/nacos错误，nacos 2.0.3的默认密码是什么呢？
4707
11
0
短信发送失败：内容关键字(GB:0010)
17987
2
0
com/action/joingroup?code=v1是什么意思
212538
21
0
支付宝H5 下载的时候，提示 【请确保该下载文件来源安全,如需浏览,请长按网址复制后使用浏览器访问】
245207
10
0
企业邮箱免费版
10498
5
0

阿里云百炼

基于通义系列大模型和开源大模型的一站式大模型服务平台，提供「生成式大模型的全流程应用工具」和「企业大模型的全链路训练工具」。为大模型，也为小应用。 阿里云百炼官网网址：https://www.aliyun.com/product/bailian

我要提问

相关文章

  • RunnerGo API 性能测试实战：从问题到解决的全链路剖析
  • A2A与MCP：理解它们的区别以及何时使用
  • AI 搜索开放平台重磅发布：Qwen3 模型上线啦
  • 一文掌握 1688 商品详情 API 接口：从入门到实战
  • JMeter、Apipost 与 Postman 的 API 测试对比：为什么 APIPost 是更聪明的选择

    • 热门讨论

    热门文章

  • MCP Agent是如何加速AI应用或工作流的开发？
  • 零代码搭建 DeepSeek 版个人知识库，你想试试吗？
  • AI陪练 VS 真人教学，你更喜欢哪一个？
  • 在dify中添加qwen，rerank和tts时都增加不上，什么原因
  • 在api调用夸克搜索时，遇到权限不足问题
  • 我在Java里使用langchain4j，搭建本地的RAG。
  • DeepSeek API 调用没反应，超时后报错 500， 这是啥意思，按照对接文档调用的啊
  • 阿里云百炼的 计费和部署计费 是分开的么？
  • 为什么同样的输入文档，通义千问官网个人版的回答质量比百炼平台的通义千问大模型高很多。
  • deepseek v3新版本提升很大，阿里云什么时候更新版本？
    • 展开全部
  • 阿里云百炼 MCP服务使用教程合集
  • 【MCP教程系列】阿里云百炼xChatPPT，5分钟轻松搞定PPT
  • 【MCP教程系列】在阿里云百炼，实现超级简单的MCP服务部署
  • 通用文本向量模型全新升级至V3，开通百炼速来体验~~
  • 精铸智刃·“百炼”成钢——深度探索阿里云百炼大模型开发平台
  • 通义千问API入门教程
  • Bolt.diy 测评：从零部署到创意实践的全流程体验
  • 【MCP教程系列】如何自己打包MCP服务并部署到阿里云百炼上
  • 阿里云百炼上线Qwen2.5-Turbo模型，可支持100万超长上下文
  • 新用户100万token免费额度！阿里云上线DeepSeek-R1满血版
    • 展开全部
    还有其他疑问?
    咨询AI助理