Thanks to visit codestin.com
Credit goes to github.com

Skip to content

04-Check Token Usage #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Dec 29, 2024
Merged

04-Check Token Usage #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6364789
[Team] Existing content development teams 3
IHAGI-c Dec 29, 2024
b13ff23
change suggestion
teddylee777 Dec 29, 2024
774af75
Update CheckTokenUsage notebook to enhance token tracking functionality
IHAGI-c Dec 29, 2024
d1c40b4
Merge branch '04-Check-token-usage-by-Haseom' of https://github.com/I…
IHAGI-c Dec 29, 2024
87307c3
Refactor CheckTokenUsage notebook to correct execution counts and upd…
IHAGI-c Dec 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
356 changes: 356 additions & 0 deletions 04-MODEL/04-CheckTokenUsage.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,356 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Check Token Usage\n",
"\n",
"- Author: [Haseom Shin](https://github.com/IHAGI-c)\n",
"- Design: []()\n",
"- Peer Review: []()\n",
"- This is a part of [LangChain Open Tutorial](https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial)\n",
"\n",
"[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain-academy/blob/main/module-4/sub-graph.ipynb) [![Open in LangChain Academy](https://cdn.prod.website-files.com/65b8cd72835ceeacd4449a53/66e9eba12c7b7688aa3dbb5e_LCA-badge-green.svg)](https://academy.langchain.com/courses/take/intro-to-langgraph/lessons/58239937-lesson-2-sub-graphs)\n",
"\n",
"## Overview\n",
"\n",
"This tutorial covers how to track and monitor token usage with `LangChain` and `OpenAI API`.\n",
"\n",
"`Token usage tracking` is crucial for managing API costs and optimizing resource utilization.\n",
"\n",
"In this tutorial, we will create a simple example to measure and monitor token consumption during OpenAI API calls using LangChain's `CallbackHandler`.\n",
"\n",
"![example](./assets/example-flow-token-usage.png)\n",
"\n",
"### Table of Contents\n",
"\n",
"- [Overview](#overview)\n",
"- [Environment Setup](#environment-setup)\n",
"- [Implementing Check Token Usage](#implementing-check-token-usage)\n",
"- [Monitoring Token Usage](#monitoring-token-usage)\n",
"\n",
"### References\n",
"\n",
"- [OpenAI API Pricing](https://openai.com/api/pricing/)\n",
"- [Token Usage Guide](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them)\n",
"- [LangChain Python API Reference](https://python.langchain.com/api_reference/community/callbacks/langchain_community.callbacks.manager.get_openai_callback.html)\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Environment Setup\n",
"\n",
"Set up the environment. You may refer to [Environment Setup](https://wikidocs.net/257836) for more details.\n",
"\n",
"**[Note]**\n",
"- `langchain-opentutorial` is a package that provides a set of easy-to-use environment setup, useful functions and utilities for tutorials. \n",
"- You can checkout the [`langchain-opentutorial`](https://github.com/LangChain-OpenTutorial/langchain-opentutorial-pypi) for more details."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%%capture --no-stderr\n",
"%pip install langchain-opentutorial"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.3.1\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
]
}
],
"source": [
"# Install required packages\n",
"from langchain_opentutorial import package\n",
"\n",
"package.install(\n",
" [\n",
" \"langsmith\",\n",
" \"langchain\",\n",
" \"langchain_openai\",\n",
" \"langchain_community\",\n",
" ],\n",
" verbose=False,\n",
" upgrade=False,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Set environment variables\n",
"from langchain_opentutorial import set_env\n",
"\n",
"set_env(\n",
" {\n",
" \"OPENAI_API_KEY\": \"\",\n",
" \"LANGCHAIN_API_KEY\": \"\",\n",
" \"LANGCHAIN_TRACING_V2\": \"true\",\n",
" \"LANGCHAIN_ENDPOINT\": \"https://api.smith.langchain.com\",\n",
" \"LANGCHAIN_PROJECT\": \"04-CheckTokenUsage\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can alternatively set `OPENAI_API_KEY` in `.env` file and load it. \n",
"\n",
"[Note] This is not necessary if you've already set `OPENAI_API_KEY` in previous steps."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's setup `ChatOpenAI` with `gpt-4o` model."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from langchain_openai import ChatOpenAI\n",
"\n",
"# Load the model\n",
"llm = ChatOpenAI(model_name=\"gpt-4o\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Implementing Check Token Usage\n",
"\n",
"if you want to check token usage, you can use `get_openai_callback` function."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tokens Used: 28\n",
"\tPrompt Tokens: 15\n",
"\t\tPrompt Tokens Cached: 0\n",
"\tCompletion Tokens: 13\n",
"\t\tReasoning Tokens: 0\n",
"Successful Requests: 1\n",
"Total Cost (USD): $0.00016749999999999998\n"
]
}
],
"source": [
"# callback to track it\n",
"from langchain_community.callbacks.manager import get_openai_callback\n",
"\n",
"with get_openai_callback() as cb:\n",
" result = llm.invoke(\"where is the capital of United States?\")\n",
" print(cb)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total tokens used: \t\t28\n",
"Tokens used in prompt: \t\t15\n",
"Tokens used in completion: \t13\n",
"Cost: \t\t\t\t$0.00016749999999999998\n"
]
}
],
"source": [
"# callback to track it\n",
"with get_openai_callback() as cb:\n",
" result = llm.invoke(\"where is the capital of United States?\")\n",
" print(f\"Total tokens used: \\t\\t{cb.total_tokens}\")\n",
" print(f\"Tokens used in prompt: \\t\\t{cb.prompt_tokens}\")\n",
" print(f\"Tokens used in completion: \\t{cb.completion_tokens}\")\n",
" print(f\"Cost: \\t\\t\\t\\t${cb.total_cost}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Monitoring Token Usage\n",
"\n",
"Token usage monitoring is crucial for managing costs and resources when using the OpenAI API. LangChain provides an easy way to track this through `get_openai_callback()`.\n",
"\n",
"In this section, we'll explore token usage monitoring through three key scenarios:\n",
"\n",
"1. **Single Query Monitoring**: \n",
" - Track token usage for individual API calls\n",
" - Distinguish between prompt and completion tokens\n",
" - Calculate costs\n",
"\n",
"2. **Multiple Queries Monitoring**:\n",
" - Track cumulative token usage across multiple API calls\n",
" - Analyze total costs\n",
"\n",
"> **Note**: Token usage monitoring is currently only supported for OpenAI API."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1. Single Query Monitoring\n",
"----------------------------------------\n",
"Response: The capital of France is Paris.\n",
"----------------------------------------\n",
"Token Usage Statistics:\n",
"Prompt Tokens: \t\t14\n",
"Completion Tokens: \t8\n",
"Total Tokens: \t\t22\n",
"Cost: \t\t\t$0.0001\n",
"\n"
]
}
],
"source": [
"# 1. Single Query Monitoring\n",
"print(\"1. Single Query Monitoring\")\n",
"print(\"-\" * 40)\n",
"\n",
"with get_openai_callback() as cb:\n",
" response = llm.invoke(\"What is the capital of France?\")\n",
" print(f\"Response: {response.content}\")\n",
" print(\"-\" * 40)\n",
" print(f\"Token Usage Statistics:\")\n",
" print(f\"Prompt Tokens: \\t\\t{cb.prompt_tokens}\")\n",
" print(f\"Completion Tokens: \\t{cb.completion_tokens}\")\n",
" print(f\"Total Tokens: \\t\\t{cb.total_tokens}\")\n",
" print(f\"Cost: \\t\\t\\t${cb.total_cost:.4f}\\n\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2. Multiple Queries Monitoring\n",
"----------------------------------------\n",
"Response 1: Python is a high-level, interpreted programming language known for its readability, simplicity, and ...\n",
"----------------------------------------\n",
"Response 2: JavaScript is a high-level, dynamic, untyped, and interpreted programming language that is widely us...\n",
"----------------------------------------\n",
"Cumulative Statistics:\n",
"Total Prompt Tokens: \t\t23\n",
"Total Completion Tokens: \t596\n",
"Total Tokens: \t\t\t619\n",
"Total Cost: \t\t\t$0.0060\n",
"\n"
]
}
],
"source": [
"# 2. Multiple Queries Monitoring\n",
"print(\"2. Multiple Queries Monitoring\")\n",
"print(\"-\" * 40)\n",
"\n",
"with get_openai_callback() as cb:\n",
" # First query\n",
" response1 = llm.invoke(\"What is Python?\")\n",
" # Second query\n",
" response2 = llm.invoke(\"What is JavaScript?\")\n",
"\n",
" print(f\"Response 1: {response1.content[:100]}...\")\n",
" print(\"-\" * 40)\n",
" print(f\"Response 2: {response2.content[:100]}...\")\n",
" print(\"-\" * 40)\n",
" print(\"Cumulative Statistics:\")\n",
" print(f\"Total Prompt Tokens: \\t\\t{cb.prompt_tokens}\")\n",
" print(f\"Total Completion Tokens: \\t{cb.completion_tokens}\")\n",
" print(f\"Total Tokens: \\t\\t\\t{cb.total_tokens}\")\n",
" print(f\"Total Cost: \\t\\t\\t${cb.total_cost:.4f}\\n\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "langchain-opentutorial-BXw0bE1H-py3.11",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Binary file added 04-MODEL/assets/example-flow-token-usage.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.