L2 openai.api_key VS os.environ['OPENAI_API_KEY']

Short Course Q&A LangChain: Chat with Your Data
1

In the second code cell I commented out the line:

openai.api_key  = os.environ['OPENAI_API_KEY']

and I ran this short example:

from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
template = """Question: {question}
Answer: Let's think step by step."""
prompt = PromptTemplate(template=template, input_variables=["question"])
llm = OpenAI()
llm_chain = LLMChain(prompt=prompt, llm=llm)
question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
llm_chain.run(question)

it still worked.
So if one sets the API key in the .env file for example with “OPENAI_API_KEY” then one does not need to set it in opena9_api_key, correct?
Is there some specific reason that line is used?

George

2

Hi @gkouro

Welcome to the community.

i’m not quite sure if i fully understand your question.

however, the notebooks on the course platform load all the environment variables for you.

But the notebooks also are develop in a way that you can use it locally. That might be a explanation for your question i think.

Best regards

1 Like