kagisearch / vectordb

A minimal Python package for storing and retrieving text using chunking, embeddings, and vector search.

Home Page:https://vectordb.com

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Memory file broken, no metadata

AWAS666 opened this issue · comments

Ever since the change that split the metadata from the embeddings, it can't be loaded from disk anymore, as only the embeddings get saved an not the metadata.

This makes everything work just fine when using it from Ram, but completely breaks as soon as you try to load from storage.

Not sure what is a clean solution here, as saving two files would also be a hassle...

We could make a single dictionary outa the two of them when saving and splitting again once loaded?

I see what you mean. Splitting them made a lot of sense from resource usage/performance standpoint but this was overlooked.

Two dicts make sense, want to give it a shot?

I see what you mean. Splitting them made a lot of sense from resource usage/performance standpoint but this was overlooked.

Two dicts make sense, want to give it a shot?

ye sure if that works out for you.