Jeff Huber

@DylanAlloy can you share any code to reproduce this? One issue with notebooks is their GC is not always reliable - and it's a good idea to manually call `client.persist()`....

We changed away from `del` to `atExit` which will help here. Closing this for now, but happy to re-open.

This is stale. Closing this issue for now. Happy to re-open.

Note to self: pull down and check out notebook locally

@GentBinaku I think I might need to create the Docker accounts? Would love some help. Can you DM me on discord?

im jeffreyhuber#3239 in https://discord.gg/MMeYNTmh3x

@mausamsion did you figure this out? closing for now, but happy to re-open

@junwang-wish you will get *far* better performance loading batches of 100k+ vectors into chroma. Can you run your benchmark with that?

@dk-crazydiv these are good questions - we are working on a performance section of our docs - the issue is here https://github.com/chroma-core/docs/issues/52

@sytelus For your use case I would suggest embedding outside of Chroma and then passing the embeddings in the code is really quite minimal - https://github.com/chroma-core/chroma/blob/main/chromadb/utils/embedding_functions.py