Should LLM be tightly coupled to SQLite?

[simonw]

Might need some kind of abstraction in LLM core for persistent storage, which will soon also need to be both sync and async capable.

It probably shouldn't be 100% reliant on SQLite either, since I want LLM as a library to be useful in other contexts, eg for people who are integrating it with PostgreSQL or even a system with NoSQL storage of some kind.

Originally posted by @simonw in simonw/llm-gemini#19 (comment)

This question is mainly relevant to LLM's usage as a Python library. I'm fine with the CLI expression of the tool depending on SQLite.

Related to this too:

• Ability to execute prompts against an asyncio (non-blocking) API #507