[djupblue]

>For example, to build shared threads like OpenAI’s, you might end up creating a new collection, a caching layer, or an index just to connect messages that logically belong together.

Which messages belongs together depends on the context and when you discover that the fancy thread store you built your app around can't return a list of MY messages without a full sequential scan of every single thread you'll wish you could solve it with an index.

[hasante]

Hi - dont know how to answer you directly - but yes the store has an index already, at a timed sequence for example. And a key called thread:thread_meta.

This statement is in no way saying you dont need an index, its simply saying, this is the variety of ways people might end up choosing.

Which is just 1 example of the type of work - a thread model & compatible store can fix and fix more efficiently.

In no way fancy too - this is just redis with a disc and some steps imo.