Running an LLM on the same server as your database is "a read workload that can ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		nkmnz on July 12, 2024 \| parent \| context \| favorite \| on: Korvus: Single-Query RAG with Postgres Running an LLM on the same server as your database is "a read workload that can be easily horizontally scaled"?

CuriouslyC on July 12, 2024 [–]

You can use PL/Python to make API calls outside of the database, you just don't need a separate service to interact with the DB to orchestrate all your ML stuff, only endpoints.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact