What is the recommended way to access the simpleQA dataset?

[ZhangYiqun018]

Hi,

I'm encountering an "Access Failure" error (ResourceNotFound) when trying to read the simple_qa_test_set.csv file from the Azure path az://openaipublic/simple-evals/simple_qa_test_set.csv using pandas and blobfile.

Is the simple-evals container publicly accessible? If not, how can I obtain the necessary credentials? Also, what is the recommended way to access the simpleQA dataset?

thanks.

[ZhangYiqun018]

I found a solution to access the simpleQA dataset. Instead of using blobfile with the az:// path, you can directly use pandas to read the CSV file from the HTTPS URL:

import pandas
df = pandas.read_csv(
    "https://openaipublic.blob.core.windows.net/simple-evals/simple_qa_test_set.csv"
)

The key is to use the HTTPS URL format (https://openaipublic.blob.core.windows.net/...) rather than the Azure blob storage path (az://...). This approach works without requiring any authentication credentials.

Hope this helps anyone facing a similar issue!