04. Check token usage

Check token usage

# API KEY A configuration file for managing environment variables
from dotenv import load_dotenv

# API KEY load information
load_dotenv()

True

# LangSmith set up tracking. https://smith.langchain.com
# !pip install langchain-teddynote
from langchain_teddynote import logging

# Enter a project name.
logging.langsmith("CH04-Models")

 Start tracking LangSmith. 
[Project name] 
CH04-Models 

Describes how to track the use of tokens for specific calls.

This feature is currently only implemented in the OpenAI API.

First, let's look at a very simple example of tracking the token usage for a single Chat model call.

from langchain.callbacks import get_openai_callback
from langchain_openai import ChatOpenAI

# load the model.
llm = ChatOpenAI(model_name="gpt-4o")

with get_openai_callback() All token usage/rates running in syntax are tracked.

# callback track using.
with get_openai_callback() as cb:
    result = llm.invoke("What is the capital of South Korea?")
    print(cb)

Tokens Used: 55 
    Prompt Tokens: 15 
    Completion Tokens: 40 
Successful Requests: 1 
Total Cost (USD): $0.000674999999999999 

# callback track using.
with get_openai_callback() as cb:
    result = llm.invoke("What is the capital of South Korea?")
    result = llm.invoke("What is the capital of South Korea?")
    print(f"Total number of tokens used: \t\t{cb.total_tokens}")
    print(f"Number of tokens used in the prompt: \t{cb.prompt_tokens}")
    print(f"Number of tokens used in the answer: \t{cb.completion_tokens}")
    print(f"Amount charged for the call(USD): \t${cb.total_cost}")

Total number of tokens used: 98 
Number of tokens used for prompt: 30 
Tokens used in the answer: 68 
Amount charged for the call (USD): $0.00117