File size: 6,660 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "8f210ec3",
      "metadata": {},
      "source": [
        "# Shell Tool\n",
        "\n",
        "Giving agents access to the shell is powerful (though risky outside a sandboxed environment).\n",
        "\n",
        "The LLM can use it to execute any shell commands. A common use case for this is letting the LLM interact with your local file system."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "id": "f7b3767b",
      "metadata": {
        "tags": []
      },
      "outputs": [],
      "source": [
        "from langchain.tools import ShellTool\n",
        "\n",
        "shell_tool = ShellTool()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "id": "c92ac832-556b-4f66-baa4-b78f965dfba0",
      "metadata": {
        "tags": []
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Hello World!\n",
            "\n",
            "real\t0m0.000s\n",
            "user\t0m0.000s\n",
            "sys\t0m0.000s\n",
            "\n"
          ]
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/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.\n",
            "  warnings.warn(\n"
          ]
        }
      ],
      "source": [
        "print(shell_tool.run({\"commands\": [\"echo 'Hello World!'\", \"time\"]}))"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "2fa952fc",
      "metadata": {},
      "source": [
        "### Use with Agents\n",
        "\n",
        "As with all tools, these can be given to an agent to accomplish more complex tasks. Let's have the agent fetch some links from a web page."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "851fee9f",
      "metadata": {
        "tags": []
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mQuestion: What is the task?\n",
            "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.\n",
            "Action:\n",
            "```\n",
            "{\n",
            "  \"action\": \"shell\",\n",
            "  \"action_input\": {\n",
            "    \"commands\": [\n",
            "      \"curl -s https://langchain.com | grep -o 'http[s]*://[^\\\" ]*' | sort\"\n",
            "    ]\n",
            "  }\n",
            "}\n",
            "```\n",
            "\u001b[0m"
          ]
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/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.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\n",
            "Observation: \u001b[36;1m\u001b[1;3mhttps://blog.langchain.dev/\n",
            "https://discord.gg/6adMQxSpJS\n",
            "https://docs.langchain.com/docs/\n",
            "https://github.com/hwchase17/chat-langchain\n",
            "https://github.com/hwchase17/langchain\n",
            "https://github.com/hwchase17/langchainjs\n",
            "https://github.com/sullivan-sean/chat-langchainjs\n",
            "https://js.langchain.com/docs/\n",
            "https://python.langchain.com/en/latest/\n",
            "https://twitter.com/langchainai\n",
            "\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3mThe URLs have been successfully extracted and sorted. We can return the list of URLs as the final answer.\n",
            "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\"]\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "'[\"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\"]'"
            ]
          },
          "execution_count": 3,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "from langchain.chat_models import ChatOpenAI\n",
        "from langchain.agents import initialize_agent\n",
        "from langchain.agents import AgentType\n",
        "\n",
        "llm = ChatOpenAI(temperature=0)\n",
        "\n",
        "shell_tool.description = shell_tool.description + f\"args {shell_tool.args}\".replace(\"{\", \"{{\").replace(\"}\", \"}}\")\n",
        "self_ask_with_search = initialize_agent([shell_tool], llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n",
        "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.\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "8d0ea3ac-0890-4e39-9cec-74bd80b4b8b8",
      "metadata": {},
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.16"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}