File size: 4,570 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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e71e720f",
   "metadata": {},
   "source": [
    "# LLM Math\n",
    "\n",
    "This notebook showcases using LLMs and Python REPLs to do complex word math problems."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "44e9ba31",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
      "What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
      "```python\n",
      "import math\n",
      "print(math.pow(13, .3432))\n",
      "```\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\n",
      "\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Answer: 2.4116004626599237\\n'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain import OpenAI, LLMMathChain\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "llm_math = LLMMathChain(llm=llm, verbose=True)\n",
    "\n",
    "llm_math.run(\"What is 13 raised to the .3432 power?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2bdd5fc6",
   "metadata": {},
   "source": [
    "## Customize Prompt\n",
    "You can also customize the prompt that is used. Here is an example prompting it to use numpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "76be17b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts.prompt import PromptTemplate\n",
    "\n",
    "_PROMPT_TEMPLATE = \"\"\"You are GPT-3, and you can't do math.\n",
    "\n",
    "You can do basic math, and your memorization abilities are impressive, but you can't do any complex calculations that a human could not do in their head. You also have an annoying tendency to just make up highly specific, but wrong, answers.\n",
    "\n",
    "So we hooked you up to a Python 3 kernel, and now you can execute code. If you execute code, you must print out the final answer using the print function. You MUST use the python package numpy to answer your question. You must import numpy as np.\n",
    "\n",
    "\n",
    "Question: ${{Question with hard calculation.}}\n",
    "```python\n",
    "${{Code that prints what you need to know}}\n",
    "print(${{code}})\n",
    "```\n",
    "```output\n",
    "${{Output of your code}}\n",
    "```\n",
    "Answer: ${{Answer}}\n",
    "\n",
    "Begin.\n",
    "\n",
    "Question: What is 37593 * 67?\n",
    "\n",
    "```python\n",
    "import numpy as np\n",
    "print(np.multiply(37593, 67))\n",
    "```\n",
    "```output\n",
    "2518731\n",
    "```\n",
    "Answer: 2518731\n",
    "\n",
    "Question: {question}\"\"\"\n",
    "\n",
    "PROMPT = PromptTemplate(input_variables=[\"question\"], template=_PROMPT_TEMPLATE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "0c42faa0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
      "What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
      "\n",
      "```python\n",
      "import numpy as np\n",
      "print(np.power(13, .3432))\n",
      "```\n",
      "\u001b[0m\n",
      "Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\n",
      "\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Answer: 2.4116004626599237\\n'"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "llm_math = LLMMathChain(llm=llm, prompt=PROMPT, verbose=True)\n",
    "\n",
    "llm_math.run(\"What is 13 raised to the .3432 power?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0c62951b",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}