Shell工具
让代理能够访问shell是一种很强大的方法（在沙箱环境之外有风险)。
LLM可以使用它来执行任何Shell命令。这种情况的常见用例是让LLM与本地文件系统进行交互。
from langchain.tools import ShellTool
shell_tool = ShellTool()
print(shell_tool.run({"commands": ["echo 'Hello World!'", "time"]}))
Hello World!
real 0m0.000s
user 0m0.000s
sys 0m0.000s
/Users/wfh/code/lc/lckg/langchain/tools/shell/tool.py:34: UserWarning: The shell tool has no safeguards by default. Use at your own risk.
warnings.warn(
与代理一起使用
与所有工具一样，可以将其提供给代理以完成更复杂的任务。让代理从网页中获取一些链接。
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent
from langchain.agents import AgentType
llm = ChatOpenAI(temperature=0)
shell_tool.description = shell_tool.description + f"args {shell_tool.args}".replace("{", "{{").replace("}", "}}")
self_ask_with_search = initialize_agent([shell_tool], llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
self_ask_with_search.run("Download the langchain.com webpage and grep for all urls. Return only a sorted list of them. Be sure to use double quotes.")
> Entering new AgentExecutor chain...
Question: What is the task?
Thought: We need to download the langchain.com webpage and extract all the URLs from it. Then we need to sort the URLs and return them.
Action:
``` python
```python
{
"action": "shell",
"action_input": {
"commands": [
"curl -s https://langchain.com | grep -o 'http[s]*://[^\" ]*' | sort"
]
}
}
``` python
```python
/Users/wfh/code/lc/lckg/langchain/tools/shell/tool.py:34: UserWarning:
The shell tool has no safeguards by default. Use at your own risk.
Observation: https://blog.langchain.dev/
https://discord.gg/6adMQxSpJS
https://docs.langchain.com/docs/
https://github.com/hwchase17/chat-langchain
https://github.com/hwchase17/langchain
https://github.com/hwchase17/langchainjs
https://github.com/sullivan-sean/chat-langchainjs
https://js.langchain.com/docs/
https://python.langchain.com/en/latest/
https://twitter.com/langchainai
Thought:The URLs have been successfully extracted and sorted. We can return the list of URLs as the final answer.
Final Answer: ["https://blog.langchain.dev/",
"https://discord.gg/6adMQxSpJS",
"https://docs.langchain.com/docs/",
"https://github.com/hwchase17/chat-langchain",
"https://github.com/hwchase17/langchain",
"https://github.com/hwchase17/langchainjs",
"https://github.com/sullivan-sean/chat-langchainjs",
"https://js.langchain.com/docs/",
"https://python.langchain.com/en/latest/",
"https://twitter.com/langchainai"]
> Finished chain.
'["https://blog.langchain.dev/",
"https://discord.gg/6adMQxSpJS",
"https://docs.langchain.com/docs/",
"https://github.com/hwchase17/chat-langchain",
"https://github.com/hwchase17/langchain",
"https://github.com/hwchase17/langchainjs",
"https://github.com/sullivan-sean/chat-langchainjs",
"https://js.langchain.com/docs/",
"https://python.langchain.com/en/latest/",
"https://twitter.com/langchainai"]'