How to specify a proxy in transformers pipeline

user_3232272 0
Viewed 3804

I am using sentiment-analysis pipeline as described here.

from transformers import pipeline
classifier = pipeline('sentiment-analysis')

It's failing with a connection error message

ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.

Is there a way to specify a proxy within the pipeline method so that it's able to connect to the internet and download the files needed?

bert-language-model huggingface-transformers python
1 Answers

It should be proxy problem. You can try add this code snippet to go through proxies.

import os
os.environ['HTTP_PROXY'] = 'http://xxx:xxx@xxx:xxx'
os.environ['HTTPS_PROXY'] = 'http://xxx:xxx@xxx:xxx'

from transformers import pipeline
classifier = pipeline('sentiment-analysis')

Note: Remember to use http instead of https for the proxy value.

user_76611580
Related