File size: 5,491 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
188
189
190
191
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e5715368",
   "metadata": {},
   "source": [
    "# How to track token usage\n",
    "\n",
    "This notebook goes over how to track your token usage for specific calls. It is currently only implemented for the OpenAI API.\n",
    "\n",
    "Let's first look at an extremely simple example of tracking token usage for a single LLM call."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9455db35",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import OpenAI\n",
    "from langchain.callbacks import get_openai_callback"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d1c55cc9",
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(model_name=\"text-davinci-002\", n=2, best_of=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "31667d54",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tokens Used: 42\n",
      "\tPrompt Tokens: 4\n",
      "\tCompletion Tokens: 38\n",
      "Successful Requests: 1\n",
      "Total Cost (USD): $0.00084\n"
     ]
    }
   ],
   "source": [
    "with get_openai_callback() as cb:\n",
    "    result = llm(\"Tell me a joke\")\n",
    "    print(cb)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c0ab6d27",
   "metadata": {},
   "source": [
    "Anything inside the context manager will get tracked. Here's an example of using it to track multiple calls in sequence."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e09420f4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "91\n"
     ]
    }
   ],
   "source": [
    "with get_openai_callback() as cb:\n",
    "    result = llm(\"Tell me a joke\")\n",
    "    result2 = llm(\"Tell me a joke\")\n",
    "    print(cb.total_tokens)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8186e7b",
   "metadata": {},
   "source": [
    "If a chain or agent with multiple steps in it is used, it will track all those steps."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5d1125c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import load_tools\n",
    "from langchain.agents import initialize_agent\n",
    "from langchain.agents import AgentType\n",
    "from langchain.llms import OpenAI\n",
    "\n",
    "llm = OpenAI(temperature=0)\n",
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2f98c536",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
      "\u001B[32;1m\u001B[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
      "Action: Search\n",
      "Action Input: \"Olivia Wilde boyfriend\"\u001B[0m\n",
      "Observation: \u001B[36;1m\u001B[1;3mSudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling.\u001B[0m\n",
      "Thought:\u001B[32;1m\u001B[1;3m I need to find out Harry Styles' age.\n",
      "Action: Search\n",
      "Action Input: \"Harry Styles age\"\u001B[0m\n",
      "Observation: \u001B[36;1m\u001B[1;3m29 years\u001B[0m\n",
      "Thought:\u001B[32;1m\u001B[1;3m I need to calculate 29 raised to the 0.23 power.\n",
      "Action: Calculator\n",
      "Action Input: 29^0.23\u001B[0m\n",
      "Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.169459462491557\n",
      "\u001B[0m\n",
      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
      "Final Answer: Harry Styles, Olivia Wilde's boyfriend, is 29 years old and his age raised to the 0.23 power is 2.169459462491557.\u001B[0m\n",
      "\n",
      "\u001B[1m> Finished chain.\u001B[0m\n",
      "Total Tokens: 1506\n",
      "Prompt Tokens: 1350\n",
      "Completion Tokens: 156\n",
      "Total Cost (USD): $0.03012\n"
     ]
    }
   ],
   "source": [
    "with get_openai_callback() as cb:\n",
    "    response = agent.run(\"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\")\n",
    "    print(f\"Total Tokens: {cb.total_tokens}\")\n",
    "    print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
    "    print(f\"Completion Tokens: {cb.completion_tokens}\")\n",
    "    print(f\"Total Cost (USD): ${cb.total_cost}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "80ca77a3",
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}