Indexing Time for ColBERTv2 on Wikipedia for LongFact Evaluation

[LuckyyySTA]

Hello,

Thank you for your work! I noticed in your paper that you used ColBERTv2 with the 33M Wikipedia-dec-2021 dataset for retrieval when evaluating LongFact. In my experience, the indexing process has been quite time-consuming. Could you please share how long the indexing took in your case? I’m using the official code from ColBERT’s GitHub repository for indexing.

Thank you very much for your help!