dosubot[bot]
commented
8 months ago 🤖
你好，@weipeng008005！我是Dosu，一个可以帮助你解决 bugs，回答问题以及成为贡献者的机器人。在等待人类维护者的同时，我会尽我所能帮助你。让我们一起解决问题吧！
根据您提供的错误日志，这个问题可能是由于在处理API请求时发生了异常。具体来说，这个错误通常表示服务器在发送完整的响应之前关闭了连接。在Langchain-Chatchat v0.2.8的上下文中，这可能是由于以下几个原因：
-
OpenAI API密钥或基础URL不正确：
openai.api_key和openai.api_base是从config字典中设置的。如果这些值不正确，对openai.ChatCompletion.acreate(**data)的API调用可能会失败。 -
OpenAI API服务器正在关闭连接：这可能是由于各种原因，如速率限制、服务器端错误或网络问题。
-
在API调用期间抛出了异常：
openai.ChatCompletion.acreate(**data)调用被包装在一个try-except块中。如果在此调用期间抛出异常，它将被记录并关闭连接。
要调试此问题，您可以：
- 检查OpenAI API密钥和基础URL：确保这些值正确，并且服务器可以访问。
- 检查日志：如果在API调用期间抛出异常，应该会被记录。检查日志中的任何错误消息。
- 检查网络：确保没有网络问题可能导致连接过早关闭。
没有更多的信息，很难确切地说为什么会出现这个错误。然而，这些步骤应该可以帮助您开始调试问题。
另外，我在Langchain-Chatchat的问题库中找到了一些类似的已解决问题，可能对您有所帮助：
希望这些信息对您有所帮助。如果您有任何其他问题或需要进一步的帮助，请随时告诉我。
Sources
- [BUG] 简洁阐述问题 / Concis我安装后，LLM问答没问题，知识库不能问答，也不能上传文件，API通信遇到错误：peer closed connection without sending complete message body (incomplete chunked read)e description of the issue，请教如何查找服务器端口，做映射
- [BUG] API通信遇到错误：peer closed connection without sending complete message body (incomplete chunked read)
- [BUG]
dev v0.2.8API通信遇到错误 - server/chat/openai_chat.py
- server/chat/knowledge_base_chat.py
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.
Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.
If you want to continue the conversation, start your reply with @dosu-bot.
weipeng008005
CaffeineOddity
zRzRzRzRzRzRzR
问题描述 / Problem Description 用简洁明了的语言描述这个问题 / Describe the problem in a clear and concise manner.
复现问题的步骤 / Steps to Reproduce
预期的结果 / Expected Result 描述应该出现的结果 / Describe the expected result.
实际结果 / Actual Result 描述实际发生的结果 / Describe the actual result.
环境信息 / Environment Information
附加信息 / Additional Information 添加与问题相关的任何其他信息 / Add any other information related to the issue.
python startup.py -a LLM对话可以正常使用，知识库对话会报API通信错误
运行信息：
操作系统：Linux-5.4.0-150-generic-x86_64-with-glibc2.27.
python版本：3.11.7 | packaged by conda-forge | (main, Dec 23 2023, 14:43:09) [GCC 12.3.0]
项目版本：v0.2.8
langchain版本：0.0.344. fastchat版本：0.2.34
当前使用的分词器：ChineseRecursiveTextSplitter
当前启动的LLM模型：['Qwen-14B-Chat'] @ cuda
{'device': 'cuda',
'gpus': '0',
'host': '0.0.0.0',
'infer_turbo': False,
'model_path': '/home/gpu/ai/projects/Qwen/models/qwen-14b-chat',
'model_path_exists': True,
'num_gpus': 1,
'port': 20003}
当前Embbedings模型： nlp_gte_sentence-embedding_chinese-large @ cuda
服务端运行信息：
OpenAI API Server: http://127.0.0.1:20000/v1
Chatchat API Server: http://127.0.0.1:7861
Chatchat WEBUI Server: http://0.0.0.0:8501
bug信息： 2023-12-28 09:16:02,440 - _client.py[line:1027] - INFO: HTTP Request: POST http://127.0.0.1:7861/chat/knowledge_base_chat "HTTP/1.1 200 OK"
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/uvicorn/protocols/http/httptools_impl.py", line 426, in run_asgi result = await app( # type: ignore[func-returns-value]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in call
return await self.app(scope, receive, send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in call
await super().call(scope, receive, send)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/applications.py", line 122, in call
await self.middleware_stack(scope, receive, send)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/middleware/errors.py", line 184, in call
raise exc
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/middleware/errors.py", line 162, in call await self.app(scope, receive, _send)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 79, in call
raise exc
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 68, in call await self.app(scope, receive, sender)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/routing.py", line 718, in call
await route.handle(scope, receive, send)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/routing.py", line 276, in handle
await self.app(scope, receive, send)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/routing.py", line 69, in app
await response(scope, receive, send)
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/responses.py", line 270, in call
async with anyio.create_task_group() as task_group:
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 597, in aexit
raise exceptions[0]
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/responses.py", line 273, in wrap
await func()
File "/home/gpu/ai/anaconda3/envs/langchain/lib/python3.11/site-packages/starlette/responses.py", line 262, in stream_response
async for chunk in self.body_iterator:
File "/home/gpu/ai/projects/Langchain-Chatchat/server/chat/knowledge_base_chat.py", line 81, in knowledge_base_chat_iterator
input_msg = History(role="user", content=prompt_template).to_msg_template(False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "pydantic/main.py", line 341, in pydantic.main.BaseModel.init
pydantic.error_wrappers.ValidationError: 1 validation error for History
content
none is not an allowed value (type=type_error.none.not_allowed)
2023-12-28 09:16:02,450 - utils.py[line:188] - ERROR: RemoteProtocolError: API通信遇到错误：peer closed connection without sending complete mess age body (incomplete chunked read)