Maurício Maia

From an independent developer's point of view, I'd say the more the better 😄

Thanks for the review @isafulf! I addressed your comments and will run an end-to-end test of the plugin soon.

Supabase is just one of the hosted PostgreSQL options that supports `pgvector`. There are options listed [here](https://github.com/pgvector/pgvector/issues/54). A user of this project could also choose to use their own PostgreSQL...

@egor-romanov sorry that I overlooked it. As I see, this implementation ends up using postgREST and a PostgreSQL connection ([`init_db`](https://github.com/egor-romanov/chatgpt-retrieval-plugin/blob/supabase-datastore-provider/datastore/providers/supabase_datastore.py#L179)). Which requires more configuration from the user. The other implementations...

There are two other PRs addressing `pgvector` support: - https://github.com/openai/chatgpt-retrieval-plugin/pull/45 - https://github.com/openai/chatgpt-retrieval-plugin/pull/53

> I agree we need one Postgres implementation but I'm not sure about calling the datastore `pgvector`. Agreed! I was not sure about it either because pgvector is not very...

Thanks @hwchase17! I fixed the lint error

I'm pretty new to this, so would probably take some time before getting it to work 😬 I may give it a try next week, if nobody does it.

[Render](https://render.com/) added support to their PostgreSQL service. https://twitter.com/render/status/1646249514045702144

> anyone has setup `pg_vector` on Railway? Didn't found anything about installing extensions there :/ @NicolasLopes7 It's not possible yet. You can vote and comment on these feature requests: -...