[Python] Why can't (langchain) AzureOpenAI find a model that AzureChatOpenAI can?

Invoking a request using AzureChatOpenAI returns response as expected:

import os
from dotenv import load_dotenv
from langchain_openai import AzureChatOpenAI

load_dotenv()

llm = AzureChatOpenAI(
azure_endpoint=os.getenv("AZURE_ENDPOINT"),
api_key=os.getenv("TOOL_KEY"),
api_version=os.getenv("API_VERSION"),
model="gpt-4o-2024-08-06"
)

response = llm.invoke("what is 2+3?")
print(response.content)


Returns:

2 + 3 equals 5.


But using the same config doesn't work with AzureOpenAI:

import os
from dotenv import load_dotenv
from langchain_openai import AzureOpenAI

load_dotenv()

llm = AzureOpenAI(
azure_endpoint=os.getenv("AZURE_ENDPOINT"),
api_key=os.getenv("TOOL_KEY"),
api_version=os.getenv("API_VERSION"),
model="gpt-4o-2024-08-06"
)

response = llm.invoke("what is 2+3?")
print(response.content)


Returns error:

openai.NotFoundError: Error code: 404 - {'detail': 'Not Found'}


What am I missing here?

Continue reading...