search

stanford-futuredata / ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
MIT License
2.67k stars 355 forks source link

Set batch size when indexing #300

Closed Diegi97 closed 4 months ago

Diegi97 commented 5 months ago

I see that you set a fixed batch size of 64 when indexing in this line: https://github.com/stanford-futuredata/ColBERT/blob/0bb135845c2b237a0b5f11b8f9a20a838924d395/colbert/indexer.py#L64

Is there a way to set a different batch size? I would like to add it to RAGatouille.

okhat commented 4 months ago

Happy to take a PR to make this a config

okhat commented 4 months ago

cc @bclavie if this is interesting to you

Diegi97 commented 4 months ago

PR submitted #303