Langchain-Chatchat
Langchain-Chatchat copied to clipboard
chatchat-space
python startup.py -a，程序运行后无法开展对话，无论是LLM还是本地知识库
==============================Langchain-Chatchat Configuration============================== 操作系统：Windows-10-10.0.22631-SP0. python版本：3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)] 项目版本：v0.2.7 langchain版本：0.1.11. fastchat版本：0.2.32
当前使用的分词器：ChineseRecursiveTextSplitter 当前启动的LLM模型：['chatglm2-6b', 'zhipu-api', 'openai-api'] @ cpu {'device': 'cpu', 'host': '127.0.0.1', 'infer_turbo': False, 'model_path': 'E:\models\chatglm2-6b', 'port': 20002} {'api_key': '', 'device': 'auto', 'host': '127.0.0.1', 'infer_turbo': False, 'online_api': True, 'port': 21001, 'provider': 'ChatGLMWorker', 'version': 'chatglm_turbo', 'worker_class': <class 'server.model_workers.zhipu.ChatGLMWorker'>} {'api_base_url': 'https://api.openai.com/v1', 'api_key': '', 'device': 'auto', 'host': '127.0.0.1', 'infer_turbo': False, 'model_name': 'gpt-35-turbo', 'online_api': True, 'openai_proxy': '', 'port': 20002} 当前Embbedings模型： m3e-base @ 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://127.0.0.1:8501 ==============================Langchain-Chatchat Configuration==============================
You can now view your Streamlit app in your browser.
URL: http://127.0.0.1:8501
INFO: 127.0.0.1:55086 - "POST /llm_model/list_config_models HTTP/1.1" 200 OK
2024-03-17 15:08:42,622 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_config_models "HTTP/1.1 200 OK"
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:08:42,720 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55086 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:08:42,721 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
received input message:
{'history': [],
'max_tokens': None,
'model_name': 'chatglm2-6b',
'prompt_name': 'default',
'query': '你是谁',
'stream': True,
'temperature': 0.7}
INFO: 127.0.0.1:55086 - "POST /chat/chat HTTP/1.1" 200 OK
2024-03-17 15:08:42,730 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/chat/chat "HTTP/1.1 200 OK"
D:\Anaconda\envs\langchain\lib\site-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(
D:\Anaconda\envs\langchain\lib\site-packages\langchain_core_api\deprecation.py:117: LangChainDeprecationWarning: The function acall was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use ainvoke instead.
warn_deprecated(
2024-03-17 15:08:43 | INFO | stdout | INFO: 127.0.0.1:55089 - "POST /v1/chat/completions HTTP/1.1" 200 OK
2024-03-17 15:08:43,100 - _client.py[line:1773] - INFO: HTTP Request: POST http://127.0.0.1:20000/v1/chat/completions "HTTP/1.1 200 OK"
2024-03-17 15:08:43 | INFO | httpx | HTTP Request: POST http://127.0.0.1:20002/worker_generate_stream "HTTP/1.1 200 OK"
2024-03-17 15:08:43,561 - utils.py[line:25] - ERROR: TypeError: Caught exception: object of type 'NoneType' has no len()
{'base_url': 'http://127.0.0.1:7861', 'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:08:50,043 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55097 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:08:50,045 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55097 - "POST /llm_model/list_config_models HTTP/1.1" 200 OK
2024-03-17 15:08:50,047 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_config_models "HTTP/1.1 200 OK"
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:08:50,142 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55097 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:08:50,143 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
received input message:
{'history': [{'content': '你是谁', 'role': 'user'},
{'content': '', 'role': 'assistant'}],
'max_tokens': None,
'model_name': 'chatglm2-6b',
'prompt_name': 'default',
'query': '你是谁',
'stream': True,
'temperature': 0.7}
INFO: 127.0.0.1:55097 - "POST /chat/chat HTTP/1.1" 200 OK
2024-03-17 15:08:50,152 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/chat/chat "HTTP/1.1 200 OK"
2024-03-17 15:08:50 | INFO | stdout | INFO: 127.0.0.1:55100 - "POST /v1/chat/completions HTTP/1.1" 200 OK
2024-03-17 15:08:50,382 - _client.py[line:1773] - INFO: HTTP Request: POST http://127.0.0.1:20000/v1/chat/completions "HTTP/1.1 200 OK"
2024-03-17 15:08:50 | INFO | httpx | HTTP Request: POST http://127.0.0.1:20002/worker_generate_stream "HTTP/1.1 200 OK"
2024-03-17 15:08:50,485 - utils.py[line:25] - ERROR: TypeError: Caught exception: object of type 'NoneType' has no len()
2024-03-17 15:08:50.486 Uncaught app exception
Traceback (most recent call last):
File "D:\Anaconda\envs\langchain\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 541, in run_script
exec(code, module.dict)
File "E:\Langchain-Chatchat-0.2.7\webui.py", line 64, in key=''.
To fix this, please make sure that the key argument is unique for each
widget you create.
{'base_url': 'http://127.0.0.1:7861', 'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:13:05,657 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55168 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:13:05,658 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55168 - "POST /llm_model/list_config_models HTTP/1.1" 200 OK
2024-03-17 15:13:05,660 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_config_models "HTTP/1.1 200 OK"
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:13:05,757 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55168 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:13:05,759 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55168 - "GET /knowledge_base/list_knowledge_bases HTTP/1.1" 200 OK
2024-03-17 15:13:05,763 - _client.py[line:1026] - INFO: HTTP Request: GET http://127.0.0.1:7861/knowledge_base/list_knowledge_bases "HTTP/1.1 200 OK"
2024-03-17 15:13:05.767 Uncaught app exception
Traceback (most recent call last):
File "D:\Anaconda\envs\langchain\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 541, in run_script
exec(code, module.dict)
File "E:\Langchain-Chatchat-0.2.7\webui.py", line 64, in key=''.
To fix this, please make sure that the key argument is unique for each
widget you create.
{'base_url': 'http://127.0.0.1:7861', 'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:13:19,996 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55174 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:13:19,997 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55174 - "POST /llm_model/list_config_models HTTP/1.1" 200 OK
2024-03-17 15:13:19,999 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_config_models "HTTP/1.1 200 OK"
{'timeout': 300.0, 'proxies': {'all://127.0.0.1': None, 'all://localhost': None, 'http://127.0.0.1': None, 'http://': None, 'https://': None, 'all://': None, 'http://localhost': None}}
2024-03-17 15:13:20,096 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:20001/list_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55174 - "POST /llm_model/list_running_models HTTP/1.1" 200 OK
2024-03-17 15:13:20,097 - _client.py[line:1026] - INFO: HTTP Request: POST http://127.0.0.1:7861/llm_model/list_running_models "HTTP/1.1 200 OK"
INFO: 127.0.0.1:55174 - "GET /knowledge_base/list_knowledge_bases HTTP/1.1" 200 OK
2024-03-17 15:13:20,101 - _client.py[line:1026] - INFO: HTTP Request: GET http://127.0.0.1:7861/knowledge_base/list_knowledge_bases "HTTP/1.1 200 OK"
2024-03-17 15:13:20.105 Uncaught app exception
Traceback (most recent call last):
File "D:\Anaconda\envs\langchain\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 541, in run_script
exec(code, module.dict)
File "E:\Langchain-Chatchat-0.2.7\webui.py", line 64, in key=''.
To fix this, please make sure that the key argument is unique for each
widget you create.
嘿，@winer3086！很高兴再次看到你在这里提问。希望你最近一切都好！
根据您提供的信息，您在使用 python startup.py -a 命令启动对话时遇到了 TypeError 和 streamlit.errors.DuplicateWidgetID 错误。这可能是由于以下几个原因：
-
TypeError：这种错误可能是由于您的代码中某个参数或变量的预期类型不匹配。但是，如果没有具体的回溯指向您的
server/api.py文件中TypeError发生的位置，就很难确定确切的原因。提供的代码并没有直接与 Streamlit 交互，也没有显示出与命令执行相关的TypeError的明显原因。 -
DuplicateWidgetID 错误：
streamlit.errors.DuplicateWidgetID错误表明在单个应用程序会话中创建了具有相同键的 Streamlit 小部件。如果您在循环或条件中动态生成小部件，而没有为每个小部件实例确保唯一的键，就可能发生这种情况。然而，提供的代码并没有直接包含任何 Streamlit 小部件的定义或使用。这个错误可能与您的应用程序的另一部分有关，该部分没有包含在上下文中。Streamlit 在提供的server/api.py文件中并没有直接引用，这表明问题可能源于使用 Streamlit 进行前端交互的另一个文件。
鉴于提供的上下文，重要的是要检查以下几点：
- 确保任何 Streamlit 小部件（例如，
st.text_input，st.button）在动态或条件创建时都有一个唯一的键。 - 查看
TypeError的完整错误回溯，以确定导致问题的确切行和操作。这将有助于理解它是否与您的 FastAPI 端点中传递的数据类型不正确或您的应用程序的其他部分有关。
没有具体的错误消息或回溯，而且提供的代码并没有直接引用 Streamlit 小部件的创建或可能导致与命令执行相关的 TypeError 的操作，所以很难提供更精确的解决方案。
如果您能提供更详细的错误信息，例如 TypeError 和 streamlit.errors.DuplicateWidgetID 错误的完整回溯，以及可能涉及的任何其他代码文件，我可能会更好地帮助您解决这个问题。
另外，您正在使用的 Langchain-Chatchat 的版本是 v0.2.7，而最新的版本是 v0.2.10。在这两个版本之间可能已经修复了一些错误，因此建议您尝试更新到最新版本，看看问题是否仍然存在。
参考资料：
Sources
- WebUI无法访问
- python startup.py -a 之后，出现报错
- 启动失败
- [BUG] Langchain-chatchat 一键启动项目 python startup.py -a 报错
- python startup.py -a执行报错卡住
- 启动时报错（python startup.py -a），如下，是硬件不够吗？
- server/api.py
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.
If you want to continue the conversation, start your reply with @dosu-bot.
![dosubot[bot] avatar](https://avatars.githubusercontent.com/in/324583?v=4 "Published by a pub.dev verified publisher"){kind=small}
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}