On: Creating a search engine with PostgreSQL

[endisneigh]

For something like this I'd use FoundationDB to store the entries redundantly and consistently with high availability and TypeSense for searching through the records and regenerating the index as necessary from FDB.

[esafak → endisneigh]

Does Typesense work with external vector databases?

[jabo → esafak]

Typesense has a vector store / search built-in: https://typesense.org/docs/0.24.1/api/vector-search.html

In the upcoming version, we've also added the ability to automatically generate embeddings from within Typesense either using OpenAI, PaLM API or a built-in model like s-bert or E5. So you only have to send json and pick a model, Typesense will then do a hybrid vector+keyword search for queries.

[esafak → jabo]

I see you run hnswlib but do you (plan to) support external vector databases, so users can upgrade?

[jabo → esafak]

We don't plan to support external vector databases, since we want to build Typesense as a vector + keyword search datastore by itself.

[esafak → jabo]

I see. Do you plan to replace hnswlib with your own technology?