Hi, in "Searching with historical queries" how do you calculate the final embedding? For example, I have these historical queries: 1) phone, 2) laptop, 3) computer. Do you sum up the embeddings of these terms?

In case of https://typesense.org/docs/26.0/api/conversational-search-rag.html#follow-up-questions: https://github.com/typesense/typesense/blob/324bd907b05f70b52a31103b81c5d9a891d56854/include/conversation_model.h#L44

I asked about Searching with historical queries

We average. There is an option to do weighting via the

query_weights

which does weighted average.