Langchain-experiments classroom exercise

I just can't get openAI to send me a response. I had a look at the new https://python.langchain.com/docs/get_started/quickstart site and updated the folder code as the original doesn't work anymore.

I ended with the following:

import os

from dotenv import find_dotenv, load_dotenv

from langchain_openai import ChatOpenAI

load_dotenv(find_dotenv())

my_key = os.getenv("OPENAI_API_KEY")

my_prompt = "Write a poem about python and AI"

my_model = "gpt-3.5-turbo-0125"

llm = ChatOpenAI(openai_api_key=my_key, model_name=my_model)

response = llm.invoke(my_prompt)

print(response)

Here i'm getting "You exceeded your current quota..." but my API key is saying that my last used was "Never". This suggests that my call wasn't fully configured. I tried most models on the openAI website.

The llm variable information: (API key is hidden🙂)

llm: client=<openai.resources.chat.completions.Completions object at 0x0000026DA9AC75F0> async_client= <...> -turbo-0125' openai_api_key='sk-...nGVq' openai_proxy=''

Any hints what to look at to resolve this?

5 comments