The advantage of pg_vector is that you don't need a second, specialised database and you also don't need to synchronise data.
It makes much more operational sense to use pg_vector if your use case can be implemented tha way.
It makes much more operational sense to use pg_vector if your use case can be implemented tha way.
You're going to spend a bunch of time writing integrations that already exist for actual search engines, and you're going to be stuck and need to back out when search becomes a necessity rather than an afterthought.
From my vantage point, you’re both right in the appropriate context.
If you have two systems, then you have two (unique) answers for HA,DR,Shard,Replica,Backup - the PG set and the Vespa.
That's more complicated, from an operational perspective.
PG FTS is quite good, and there are in-pg methods that can improve it.
And, from experience, when it's item to upscale to Solr/ES/etc it's not a very heavy lift.