lagent

lagent copied to clipboard

fanqiNO1

小小修改了下demo， from lagent.actions import ActionExecutor, ArxivSearch, IPythonInterpreter, PythonInterpreter,IPythonInteractive action_list = [ IPythonInterpreter(), PythonInterpreter(), IPythonInteractive(), ] 然后进入demo，勾选插件让运行编辑器，写代码，做些简单任务，都只能模型本身正常回答问题，无法调用对应的插件？ 系统windows10，用的是windows里部署的lmdeploy挂载的internlm2-chat-7b模型，然后lagent部署在wsl2里，是wsl2兼容性问题么？ 现在有点迷惑，actions正常的调用方法是什么？

thsun6

Update base_llm.py

3

Increase code flexibility and backward compatibility

seanxuu

fanqiNO1

为什么部署成功了internlm2_agent_web_demo.py，但是模型回答不调用工具呢？

1

hheyang

liujiangning30

自定义了一个天气查询的工具，模型没有调用我的工具，而是瞎掰了一个： ``` 用户：北京市今天天气怎么样 InternLm2：/home/ybZhang/miniconda3/envs/lagent/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:410: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.1` -- this flag is only used in sample-based generation modes. You should set `do_sample=True`...

v-yunbin

liujiangning30

 ` ValueError: not enough values to unpack (expected 2, got 1) message 好的，我会帮你处理这个 CSV 文件。 2024-02-23 13:12:51.844 Uncaught app exception Traceback (most recent call last): File "C:\Users\a9092\.conda\envs\my-env\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 535,...

909254

May I know once I want to make a LLM by `BaseAPIModel`, where could I input the url_base?

6

I cannot find where can I input my url of my LLM on cloud. I should make one just like you do in `GPTAPI`, shoudn't I? So why this `class`...

ZhaoCake