File size: 7,308 Bytes
ed4d993
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bash chain\n",
    "This notebook showcases using LLMs and a bash process to 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\n",
      "Code: \u001b[33;1m\u001b[1;3m['echo \"Hello World\"']\u001b[0m\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_experimental.llm_bash.base import LLMBashChain\n",
    "from langchain_openai 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.from_llm(llm, verbose=True)\n",
    "\n",
    "bash_chain.invoke(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": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts.prompt import PromptTemplate\n",
    "from langchain_experimental.llm_bash.prompt import BashOutputParser\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(\n",
    "    input_variables=[\"question\"],\n",
    "    template=_PROMPT_TEMPLATE,\n",
    "    output_parser=BashOutputParser(),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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\n",
      "Code: \u001b[33;1m\u001b[1;3m['printf \"Hello World\\\\n\"']\u001b[0m\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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bash_chain = LLMBashChain.from_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.invoke(text)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Persistent Terminal\n",
    "\n",
    "By default, the chain will run in a separate subprocess each time it is called. This behavior can be changed by instantiating with a persistent bash process."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
      "List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```bash\n",
      "ls\n",
      "cd ..\n",
      "```\u001b[0m\n",
      "Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3mcpal.ipynb  llm_bash.ipynb  llm_symbolic_math.ipynb\n",
      "index.mdx   llm_math.ipynb  pal.ipynb\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'cpal.ipynb  llm_bash.ipynb  llm_symbolic_math.ipynb\\r\\nindex.mdx   llm_math.ipynb  pal.ipynb'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain_experimental.llm_bash.bash import BashProcess\n",
    "\n",
    "persistent_process = BashProcess(persistent=True)\n",
    "bash_chain = LLMBashChain.from_llm(llm, bash_process=persistent_process, verbose=True)\n",
    "\n",
    "text = \"List the current directory then move up a level.\"\n",
    "\n",
    "bash_chain.invoke(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
      "List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```bash\n",
      "ls\n",
      "cd ..\n",
      "```\u001b[0m\n",
      "Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m_category_.yml\tdata_generation.ipynb\t\t   self_check\n",
      "agents\t\tgraph\n",
      "code_writing\tlearned_prompt_optimization.ipynb\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'_category_.yml\\tdata_generation.ipynb\\t\\t   self_check\\r\\nagents\\t\\tgraph\\r\\ncode_writing\\tlearned_prompt_optimization.ipynb'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Run the same command again and see that the state is maintained between calls\n",
    "bash_chain.invoke(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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}