Navneet Verma

Hi @austintlee Lets it over the call. I will setup a call.

@heemin32 > implementing some very basic ingest pipeline inside ml-commons for integ test purpose. My comment was mainly around this.

> It is good that this topic is brought up publicly. I remember that I and @martin-gaievski have discussed about this exact limitation of current hybrid search before but wasn't...

@HenryL27 thanks for sharing the gist, it is very helpful. Based on my understanding of OpenSearch and this hybrid query the contention point in implementing such thing is getting more...

For both of the queries number of documents that enter the normalization is ‘size’ if there are enough documents. @SeyedAlirezaFatemi

@SeyedAlirezaFatemi > the default min_score can be of help here `min_score` feature is in radar, its just its not being priortised as of now. > when we have normalization, do...

since there is no activity on the GH issue. Resolving the issue

@martin-gaievski can you please provide the reference for the integration tests that has been added. I am able to find this: https://github.com/opensearch-project/neural-search/blob/main/src/test/java/org/opensearch/neuralsearch/query/HybridQueryIT.java#L32

> @navneet1v this one test hybrid but for some reason when I run it in my IDE to debug I can't see the normalization processor being triggered. Could also be...

> Don't the weights need to sum to 1? Yes the weights need to sum up to 1. We didn't add this check at start. This needs to be added....