Hi
I just created a Lucene vector search index with Lucene-9.0.0-SNAPSHOT
based on train-v2.0.json of SQuAD
(https://rajpurkar.github.io/SQuAD-explorer/), which are 86'831 QnAs
(for the embedding I used SentenceBERT).
It took a couple of hours on my Mac laptop, but it worked in the end and
I can search successfully :-)
I tried to open the index with Luke, but receive an error, that the
index might be corrupt.
Does Luke already support analyzing a vector search index? If not, are
there any plans to support vector search?
Thanks
Michael
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
