multimodal/ Multimodal.ipynb example doesn't include vital details

[pleabargain]

There are a number of libs | imports not included
e.g. # ! pip install sentencepiece
#! pip install transformers

! pip install gpt_index

And the code insists on openai_api_key
but no matter how I try to set this VAR, the code complains that the openai_api_key doesn't exist.

reciept reader code complains for a long time:
Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration.

I tried with
OPENAI_API_KEY="sk-XXX"
and
openai_api_key="sk-XXX"
both failed with

Did not find openai_api_key, please add an environment variable OPENAI_API_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)

[Disiok]

How do you currently set your API key? Do other notebook examples work?

[logan-markewich]

Going to close this issue, as being stale

For reference, there are several ways to set the key

in a bash terminal
export OPENAI_API_KEY="my key"

Directly in code
import os
os.environ['OPENAI_API_KEY'] = "my key"

Directly in LLM
llm_predictor = LLMPredictor(llm=OpenAI(model_name='text-davinci-003', temperature=0, openai_api_key="my key"))