search

koaning / bulk

A Simple Bulk Labelling Tool
MIT License
536 stars 45 forks source link

Help creating pipeline #42

Closed phgoddard closed 1 year ago

phgoddard commented 1 year ago

Thanks for the great tool. I'm just getting started and got stuck making the pipeline. I've installed embetter.text and imported SentenceEncoder. I've also installed sentence-transformers. Running into error 'pip install embetter[sbert] though I'm able to create a model using: model = SentenceTransformer('all-MiniLM-L6-v2') screen shot attached:

2022-12-04_20-43-12

Can you help me - thanks.

koaning commented 1 year ago

I think this is a mistake on the embetter side. Could you try: 

python -m pip install "embetter[text]"

It should also be fixed via: 

python -m pip install sentence-transformers

You will likely need to restart your Python env to get this to work though.

koaning commented 1 year ago

I did find the bad error message that mentions sbert instead of text. Will push a new version with a fix in a bit.

phgoddard commented 1 year ago

thank you - past the error now.