File size: 4,268 Bytes
acc4ffe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# BashChain\n",
    "This notebook showcases using LLMs and a bash process to do perform simple filesystem commands."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
      "Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```bash\n",
      "echo \"Hello World\"\n",
      "```\u001b[0m['```bash', 'echo \"Hello World\"', '```']\n",
      "\n",
      "Answer: \u001b[33;1m\u001b[1;3mHello World\n",
      "\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Hello World\\n'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.chains import LLMBashChain\n",
    "from langchain.llms import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "\n",
    "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
    "\n",
    "bash_chain = LLMBashChain(llm=llm, verbose=True)\n",
    "\n",
    "bash_chain.run(text)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Customize Prompt\n",
    "You can also customize the prompt that is used. Here is an example prompting to avoid using the 'echo' utility"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts.prompt import PromptTemplate\n",
    "\n",
    "_PROMPT_TEMPLATE = \"\"\"If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put \"#!/bin/bash\" in your answer. Make sure to reason step by step, using this format:\n",
    "Question: \"copy the files in the directory named 'target' into a new directory at the same level as target called 'myNewDirectory'\"\n",
    "I need to take the following actions:\n",
    "- List all files in the directory\n",
    "- Create a new directory\n",
    "- Copy the files from the first directory into the second directory\n",
    "```bash\n",
    "ls\n",
    "mkdir myNewDirectory\n",
    "cp -r target/* myNewDirectory\n",
    "```\n",
    "\n",
    "Do not use 'echo' when writing the script.\n",
    "\n",
    "That is the format. Begin!\n",
    "Question: {question}\"\"\"\n",
    "\n",
    "PROMPT = PromptTemplate(input_variables=[\"question\"], template=_PROMPT_TEMPLATE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
      "Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```bash\n",
      "printf \"Hello World\\n\"\n",
      "```\u001b[0m['```bash', 'printf \"Hello World\\\\n\"', '```']\n",
      "\n",
      "Answer: \u001b[33;1m\u001b[1;3mHello World\n",
      "\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Hello World\\n'"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bash_chain = LLMBashChain(llm=llm, prompt=PROMPT, verbose=True)\n",
    "\n",
    "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
    "\n",
    "bash_chain.run(text)"
   ]
  }
 ],
 "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}