model.py

import os
from dotenv import load_dotenv, find_dotenv
from langchain.callbacks.streaming_stdout_final_only import (
    FinalStreamingStdOutCallbackHandler,
)

_ = load_dotenv(find_dotenv())  # read local .env file

openaiAPIVersion = os.getenv("OPENAI_API_VERSION")  # "2023-05-15"
gpt4Model = os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME_GPT4")
gpt35Model = os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME_GPT35")
print(openaiAPIVersion, gpt4Model, gpt35Model)

from langchain.chat_models import AzureChatOpenAI

llm = AzureChatOpenAI(
    temperature=0,
    deployment_name=gpt35Model,
    openai_api_version=openaiAPIVersion,
)

llm4 = AzureChatOpenAI(
    temperature=0,
    deployment_name=gpt4Model,
    openai_api_version=openaiAPIVersion,
    streaming=True,
)