Langchain-Chatchat icon indicating copy to clipboard operation
Langchain-Chatchat copied to clipboard

Published 20 hours ago • verified publisher icon chatchat-space

[BUG] 使用api，针对知识库问答时，非openAI在线大模型（qianfan-api和zhipu-api）会报APIConnectionError错误。

Open zzxs opened this issue 1 year ago • 1 comments

问题描述 使用知识库问答时发生如上问题。 上个星期用的时候还是没问题的，这个星期重新搭建了一次就一直报错，依赖库版本可能和上一次不一致。 核心报错信息如下： 2024-04-24 12:44:01,234 - _base_client.py[line:1524] - INFO: Retrying request to /chat/completions in 0.957255 seconds 2024-04-24 12:44:02,192 - _base_client.py[line:1524] - INFO: Retrying request to /chat/completions in 1.747860 seconds 2024-04-24 12:44:03,943 - utils.py[line:38] - ERROR: Connection error 出错代码： /chatchat-space/server/chat/knowledge_base_chat.py的112行 task = asyncio.create_task(wrap_done( chain.acall({"context": context, "question": query}), callback.done), ) 求助。

完整报错信息（隐去key） 操作系统：Linux-5.15.0-92-generic-x86_64-with-glibc2.35. python版本：3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] 项目版本：v0.2.10 langchain版本：0.0.354. fastchat版本：0.2.35

当前使用的分词器：ChineseRecursiveTextSplitter 当前启动的LLM模型：['qianfan-api'] @ cpu {'api_key': '*******************', 'device': 'auto', 'host': '0.0.0.0', 'infer_turbo': False, 'online_api': True, 'port': 21004, 'provider': 'QianFanWorker', 'secret_key': '*****************************', 'version': 'ERNIE-Bot', 'version_url': '', 'worker_class': <class 'server.model_workers.qianfan.QianFanWorker'>} 当前Embbedings模型： m3e-base @ cpu ==============================Langchain-Chatchat Configuration==============================

2024-04-24 12:43:53,612 - startup.py[line:655] - INFO: 正在启动服务： 2024-04-24 12:43:53,612 - startup.py[line:656] - INFO: 如需查看 llm_api 日志，请前往 /home/lxy/chatchat-space/logs INFO: Started server process [17786] INFO: Waiting for application startup.

==============================Langchain-Chatchat Configuration============================== 操作系统：Linux-5.15.0-92-generic-x86_64-with-glibc2.35. INFO: Application startup complete. python版本：3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] 项目版本：v0.2.10 langchain版本：0.0.354. fastchat版本：0.2.35

当前使用的分词器：ChineseRecursiveTextSplitter 当前启动的LLM模型：['qianfan-api'] @ cpu {'api_key': 'mVCljMqBpvJQhXiq2F4lp9Vs', 'device': 'auto', 'host': '0.0.0.0', 'infer_turbo': False, 'online_api': True, 'port': 21004, 'provider': 'QianFanWorker', 'secret_key': 'zCGESU9AUebX3zdzKU8UZodY8KtoURkP', 'version': 'ERNIE-Bot', 'version_url': '', 'worker_class': <class 'server.model_workers.qianfan.QianFanWorker'>} 当前Embbedings模型： m3e-base @ cpu

服务端运行信息： Chatchat API Server: http://127.0.0.1:7861 ==============================Langchain-Chatchat Configuration==============================

INFO: Uvicorn running on http://0.0.0.0:7861 (Press CTRL+C to quit) INFO: 119.39.128.211:51496 - "POST /chat/knowledge_base_chat HTTP/1.1" 200 OK /usr/local/lib/python3.10/dist-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class langchain_community.chat_models.openai.ChatOpenAI was deprecated in langchain-community 0.0.10 and will be removed in 0.2.0. An updated version of the class exists in the langchain-openai package and should be used instead. To use it run pip install -U langchain-openai and import as from langchain_openai import ChatOpenAI. warn_deprecated( 2024-04-24 12:44:00,395 - SentenceTransformer.py[line:66] - INFO: Load pretrained SentenceTransformer: /home/models/moka-ai/m3e-base 2024-04-24 12:44:01,178 - faiss_cache.py[line:92] - INFO: loading vector store in 'samples/vector_store/m3e-base' from disk. 2024-04-24 12:44:01,180 - loader.py[line:54] - INFO: Loading faiss with AVX2 support. 2024-04-24 12:44:01,192 - loader.py[line:56] - INFO: Successfully loaded faiss with AVX2 support. /usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/faiss.py:121: UserWarning: Normalizing L2 is not applicable for metric type: METRIC_INNER_PRODUCT warnings.warn( 2024-04-24 12:44:01,234 - _base_client.py[line:1524] - INFO: Retrying request to /chat/completions in 0.957255 seconds 2024-04-24 12:44:02,192 - _base_client.py[line:1524] - INFO: Retrying request to /chat/completions in 1.747860 seconds 2024-04-24 12:44:03,943 - utils.py[line:38] - ERROR: Connection error. Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/httpx/_transports/default.py", line 67, in map_httpcore_exceptions yield File "/usr/local/lib/python3.10/dist-packages/httpx/_transports/default.py", line 371, in handle_async_request resp = await self._pool.handle_async_request(req) File "/usr/local/lib/python3.10/dist-packages/httpcore/_async/connection_pool.py", line 216, in handle_async_request raise exc from None File "/usr/local/lib/python3.10/dist-packages/httpcore/_async/connection_pool.py", line 196, in handle_async_request response = await connection.handle_async_request( File "/usr/local/lib/python3.10/dist-packages/httpcore/_async/connection.py", line 99, in handle_async_request raise exc File "/usr/local/lib/python3.10/dist-packages/httpcore/_async/connection.py", line 76, in handle_async_request stream = await self._connect(request) File "/usr/local/lib/python3.10/dist-packages/httpcore/_async/connection.py", line 122, in _connect stream = await self._network_backend.connect_tcp(**kwargs) File "/usr/local/lib/python3.10/dist-packages/httpcore/_backends/auto.py", line 30, in connect_tcp return await self._backend.connect_tcp( File "/usr/local/lib/python3.10/dist-packages/httpcore/_backends/anyio.py", line 114, in connect_tcp with map_exceptions(exc_map): File "/usr/lib/python3.10/contextlib.py", line 153, in exit self.gen.throw(typ, value, traceback) File "/usr/local/lib/python3.10/dist-packages/httpcore/_exceptions.py", line 14, in map_exceptions raise to_exc(exc) from exc httpcore.ConnectError: All connection attempts failed

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

Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1435, in _request response = await self._client.send( File "/usr/local/lib/python3.10/dist-packages/httpx/_client.py", line 1646, in send response = await self._send_handling_auth( File "/usr/local/lib/python3.10/dist-packages/httpx/_client.py", line 1674, in _send_handling_auth response = await self._send_handling_redirects( File "/usr/local/lib/python3.10/dist-packages/httpx/_client.py", line 1711, in _send_handling_redirects response = await self._send_single_request(request) File "/usr/local/lib/python3.10/dist-packages/httpx/_client.py", line 1748, in _send_single_request response = await transport.handle_async_request(request) File "/usr/local/lib/python3.10/dist-packages/httpx/_transports/default.py", line 370, in handle_async_request with map_httpcore_exceptions(): File "/usr/lib/python3.10/contextlib.py", line 153, in exit self.gen.throw(typ, value, traceback) File "/usr/local/lib/python3.10/dist-packages/httpx/_transports/default.py", line 84, in map_httpcore_exceptions raise mapped_exc(message) from exc httpx.ConnectError: All connection attempts failed

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

Traceback (most recent call last): File "/home/lxy/chatchat-space/server/utils.py", line 36, in wrap_done await fn File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 385, in acall raise e File "/usr/local/lib/python3.10/dist-packages/langchain/chains/base.py", line 379, in acall await self._acall(inputs, run_manager=run_manager) File "/usr/local/lib/python3.10/dist-packages/langchain/chains/llm.py", line 275, in _acall response = await self.agenerate([inputs], run_manager=run_manager) File "/usr/local/lib/python3.10/dist-packages/langchain/chains/llm.py", line 142, in agenerate return await self.llm.agenerate_prompt( File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 554, in agenerate_prompt return await self.agenerate( File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 514, in agenerate raise exceptions[0] File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 617, in _agenerate_with_cache return await self._agenerate( File "/usr/local/lib/python3.10/dist-packages/langchain_community/chat_models/openai.py", line 522, in _agenerate return await agenerate_from_stream(stream_iter) File "/usr/local/lib/python3.10/dist-packages/langchain_core/language_models/chat_models.py", line 87, in agenerate_from_stream async for chunk in stream: File "/usr/local/lib/python3.10/dist-packages/langchain_community/chat_models/openai.py", line 488, in _astream async for chunk in await acompletion_with_retry( File "/usr/local/lib/python3.10/dist-packages/langchain_community/chat_models/openai.py", line 105, in acompletion_with_retry return await llm.async_client.create(**kwargs) File "/usr/local/lib/python3.10/dist-packages/openai/resources/chat/completions.py", line 1300, in create return await self._post( File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1703, in post return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls) File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1406, in request return await self._request( File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1459, in _request return await self._retry_request( File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1528, in _retry_request return await self._request( File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1459, in _request return await self._retry_request( File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1528, in _retry_request return await self._request( File "/usr/local/lib/python3.10/dist-packages/openai/_base_client.py", line 1469, in _request raise APIConnectionError(request=request) from err openai.APIConnectionError: Connection error. 2024-04-24 12:44:03,944 - utils.py[line:40] - ERROR: APIConnectionError: Caught exception: Connection error.

zzxs avatar Apr 24 '24 05:04 zzxs

The APIConnectionError you're encountering with the qianfan-api and zhipu-api could be due to several factors. Here's a focused approach to troubleshoot and potentially resolve the issue:

  1. API Key and Secret Key Verification: Double-check that the API key and secret key are correct. Incorrect credentials can prevent successful API requests.

  2. Network Connectivity: Ensure the server has a stable connection to https://aip.baidubce.com. Connection issues can lead to the errors you're seeing.

  3. Baidu Service Status: Check for any service disruptions or maintenance on Baidu's end that might affect API availability.

  4. Dependencies Update: Make sure all dependencies, especially httpx, are up to date to avoid compatibility issues.

  5. Enhanced Error Handling: Improve error handling and logging for the API call sections to capture more detailed error information.

  6. Rate Limits: Consider if you're hitting API rate limits and implement retry mechanisms with exponential backoff if necessary.

  7. API Support: If the issue persists, reaching out to the support teams for qianfan-api and zhipu-api could provide more insights.

Additionally, review your server_config.py for configurations like HTTPX_DEFAULT_TIMEOUT, DEFAULT_BIND_HOST, and the API_SERVER setup to ensure they align with your network and service requirements. Adjusting these settings or ensuring they're correctly configured might help resolve the connection issues you're experiencing.

Details

Sources


About Dosu 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.

To continue the conversation, mention @dosu.

dosubot[bot] avatar Apr 24 '24 05:04 dosubot[bot]

超过token上线了吧，4096上限默认

zRzRzRzRzRzRzR avatar May 05 '24 04:05 zRzRzRzRzRzRzR