chatchat-space / Langchain-Chatchat

Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
Apache License 2.0
31.45k stars 5.48k forks source link

创建知识库出错: loop of ufunc does not support argument 0 of type NoneType which has no callable conjugate method #2369

Closed Mrzhou1998 closed 9 months ago

Mrzhou1998 commented 9 months ago

一下日志中APISecret,APPID,api_key为手动删除置空

==============================Langchain-Chatchat Configuration============================== 操作系统:Linux-5.10.0-25-amd64-x86_64-with-glibc2.31. python版本:3.9.2 (default, Feb 28 2021, 17:03:44) [GCC 10.2.1 20210110] 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:['xinghuo-api'] @ cpu {'APISecret': '', 'APPID': '', 'api_key': '', 'device': 'cpu', 'host': '0.0.0.0', 'infer_turbo': False, 'online_api': True, 'port': 21003, 'provider': 'XingHuoWorker', 'version': 'v3.0', 'worker_class': <class 'server.model_workers.xinghuo.XingHuoWorker'>} 当前Embbedings模型: qwen-api @ cpu

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 ==============================Langchain-Chatchat Configuration==============================

Collecting usage statistics. To deactivate, set browser.gatherUsageStats to False.

You can now view your Streamlit app in your browser.

URL: http://0.0.0.0:8501

2023-12-13 09:18:58,640 - _client.py[line:1013] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK" INFO: 127.0.0.1:52400 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK 2023-12-13 09:18:58,643 - _client.py[line:1013] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK" 2023-12-13 09:18:58,756 - _client.py[line:1013] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK" INFO: 127.0.0.1:52400 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK 2023-12-13 09:18:58,758 - _client.py[line:1013] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK" INFO: 127.0.0.1:52400 - "POST /llm_model/list_config_models HTTP/1.1" 200 OK 2023-12-13 09:18:58,766 - _client.py[line:1013] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_config_models "HTTP/1.1 200 OK" 2023-12-13 09:19:27,270 - faiss_cache.py[line:80] - INFO: loading vector store in 'fullgoal/vector_store/qwen-api' from disk. 2023-12-13 09:19:27 | ERROR | root | There is no current event loop in thread 'AnyIO worker thread'. 2023-12-13 09:19:27 | ERROR | root | TypeError: 创建知识库出错: loop of ufunc does not support argument 0 of type NoneType which has no callable conjugate method INFO: 127.0.0.1:34828 - "POST /knowledge_base/create_knowledge_base HTTP/1.1" 200 OK 2023-12-13 09:19:27,273 - _client.py[line:1013] - INFO: HTTP Request: POST

realanthonysu commented 9 months ago

使用zhipu-api作为embedding model创建知识库也碰到这个问题,请问是怎么解决的。