langchain/docs/modules/models/llms/examples/token_usage_tracking.ipynb

{
 "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": 1,
   "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": 5,
   "id": "31667d54",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total Tokens: 42\n",
      "Prompt Tokens: 4\n",
      "Completion Tokens: 38\n"
     ]
    }
   ],
   "source": [
    "with get_openai_callback() as cb:\n",
    "    result = llm(\"Tell me a joke\")\n",
    "    print(f\"Total Tokens: {cb.total_tokens}\")\n",
    "    print(f\"Prompt Tokens: {cb.prompt_tokens}\")\n",
    "    print(f\"Completion Tokens: {cb.completion_tokens}\")"
   ]
  },
  {
   "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": 6,
   "id": "e09420f4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "83\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": 7,
   "id": "5d1125c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import load_tools\n",
    "from langchain.agents import initialize_agent\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=\"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;3mJason Sudeikis\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
      "Action: Search\n",
      "Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m47 years\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 47 raised to the 0.23 power\n",
      "Action: Calculator\n",
      "Action Input: 47^0.23\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "1465\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(cb.total_tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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
}