Paper can be found here: https://www.pinecone.io/research/unveiling-dime-reproducibil...

Multi-vector retrieval as a fast second-stage reranker to improve ranking quality without hurting latency

Thanks sota_pop. I am looking for contributors to help me integrate new features. Please come and join me!

Maxime Caron?

Yes, you can index any content as long as it is parsable. You can easily plug a new PDF parser and start indexing your PDF articles...

We rely on different user intents. Search for "PISA engine" or "PISA search" and you will find this tool and not the city. Being found by the keyword `PISA` on Google is not necessarily our main goal. We are not selling anything, the community is just building a product for IR research. We are willing to gain interest from skilled people in the end. I don't think it really matters if there are `news` about the city, we are not targeting the news anyway.

Also, think about `Windows` or `Go`, there is no way you get confused once these words are in the right context.

Thanks for the feedback!

Good to see you Marko!

Interesting! As long as there is no other OS software with the name PISA it should not be too confusing. Thanks for pointing out.

Not yet