You are trying to use a chat model. This way of initializing it is no longer supported.

[tancs711]

The following serpapi code works. But I got this message.

/usr/local/lib/python3.10/dist-packages/langchain/llms/openai.py:171: UserWarning: You are trying to use a chat model. This way of initializing it is no longer supported. Instead, please use: from langchain.chat_models import ChatOpenAI
warnings.warn(

What should I change?

## Token usage and cost
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.llms import OpenAI
from langchain.callbacks import get_openai_callback
import json

llm_model_name="gpt-3.5-turbo"
llm = OpenAI(model_name=llm_model_name)
toolkit = load_tools(["serpapi"], llm=llm, serpapi_api_key=SERPAPI_API_KEY)
agent = initialize_agent(toolkit, llm, agent="zero-shot-react-description", verbose=True, return_intermediate_steps=True)

query="Get Microsoft share price from the www.bloomberg.com and include the url where you got this information."

with get_openai_callback() as cb:
    response = agent({"input":query})
    print(f"Total Tokens: {cb.total_tokens}")
    print(f"Prompt Tokens: {cb.prompt_tokens}")
    print(f"Completion Tokens: {cb.completion_tokens}")
    print(f"Total Cost (USD): ${cb.total_cost}")

I dont get an error when llm

llm = OpenAI(temperature=0) 

[talhaanwarch]

do this way

from langchain.chat_models import ChatOpenAI
llm = ChatOpenAI(model_name='gpt-3.5-turbo')

[sherwinwater]

thanks

[tancs711]

@talhaanwarch, thanks that works!

[tancs711]

@talhaanwarch , do you know which model is use by default if model name is not supplied?

[shawnesquivel]

Printing OpenAI(), you can see the default parameters, and that it is the davinci model

params: {'model_name': 'text-davinci-003', 'temperature': 0.7, 'max_tokens': 256, 'top_p': 1, 'frequency_penalty': 0, 'presence_penalty': 0, 'n': 1, 'request_timeout': None, 'logit_bias': {}}