Results 13 issues of 小海

"llm_chat": { "default": '{{ input }}', "with_history": 'The following is a friendly conversation between a human and an AI. ' 'The AI is talkative and provides lots of specific details...

bug

2024-03-15 11:12:59.932 Uncaught app exception Traceback (most recent call last): File "/home/user/anaconda3/envs/langchai-chat/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 535, in _run_script exec(code, module.__dict__) File "/home/chatglm3/Langchain-Chatchat/webui.py", line 64, in pages[selected_page]["func"](api=api, is_lite=is_lite) File "/home/chatglm3/Langchain-Chatchat/webui_pages/dialogue/dialogue.py", line 325, in...

bug

24-03-13 17:02:32,422 - utils.py[line:38] - ERROR: object of type 'NoneType' has no len() Traceback (most recent call last): File "/home/chatglm3/Langchain-Chatchat/server/utils.py", line 36, in wrap_done await fn File "/home/user/anaconda3/envs/langchai-chat/lib/python3.11/site-packages/langchain/chains/base.py", line 385,...

bug

FSCHAT_MODEL_WORKERS = { # 所有模型共用的默认配置,可在模型专项配置中进行覆盖。 "default": { "host": DEFAULT_BIND_HOST, "port": 20002, "device": LLM_DEVICE, # False,'vllm',使用的推理加速框架,使用vllm如果出现HuggingFace通信问题,参见doc/FAQ # vllm对一些模型支持还不成熟,暂时默认关闭 "infer_turbo": 'vllm', # 开启vllm后必须开启的参数 --start---- "max_parallel_loading_workers":22, "enforce_eager":False, "max_context_len_to_capture":2048, "max_model_len":2048, # ------end----------------------- # model_worker多卡加载需要配置的参数...

bug

Vllm模式启动模型推理能力会下降吗,会出现问问题时回答不完整甚至不返回的现象,server_config.py里面有哪些配置影响上述问题吗?另外load_format':'auto'有哪几个配置项,到哪去查看?

bug

2024-03-13 09:51:31,055 - startup.py[line:655] - INFO: 正在启动服务: 2024-03-13 09:51:31,055 - startup.py[line:656] - INFO: 如需查看 llm_api 日志,请前往 /home/chatglm3/Langchain-Chatchat/logs ==============================Langchain-Chatchat Configuration============================== 操作系统:Linux-3.10.0-1160.108.1.el7.x86_64-x86_64-with-glibc2.17. python版本:3.11.7 (main, Dec 15 2023, 18:12:31) [GCC 11.2.0] 项目版本:v0.2.10 langchain版本:0.0.354....

bug

自定义对话选择agent模式,输入查询北京天气后台不能成功查询,后台打印 > Entering new AgentExecutor chain... Action: ``` {"action": "Final Answer", "action_input": "I will use the weather_check tool to check the weather in Beijing.\n"} ``` > Finished chain. 另外,如何通过api方式调用agent模式?

bug

langchain-chatchat如何自定义工具,像已有的天气查询一样,提供实例并讲述如何调用

bug

使用模型chatglm3-6b,如何在langchain-chatchat交互中调用到chatglm3-6b自定义的工具(function calling),请提供实例

bug

使用模型chatglm3-6b,如何在langchain-chatchat交互中调用到chatglm3-6b自定义的function,请提供实例

bug