Making default behavior saving to disk instead of clearing it about chroma

[jeffchuber]

Hi @Shomvel - Chroma is used by people creating persistant apps, but also people who just want an "in-memory" database to run some quick computation, for example inside a Jupyter notebook.

Making persistence the default would break the idempotency of using chroma in that case (you can run the same script twice and get the same result).

That all being said..... I do agree the docs are confusing in that place! And we also want to clean up the ergonomics around how someone would instantiate a persistent client, persist, load, and generally query it. One idea we had was instead of

import chromadb
client = chromadb.Client() // in-memory
client = chromadb.PersistentClient() //in-memory with persistence

What do you think about this?

cc @wpnbos

[Shomvel]

I think it's better to centralize client settings. What about making it an option and making it clear in doc that default behavior is in-memory w/o persistence?

If persist=True, make impl='duckdb+parquet' or you can also specify impl.

import chromadb
chromadb.Client() // w/o persistence
chromadb.Client(persistence=True) // persists, impl=duckdb+parquet
chromadb.Client(persistence=True, impl='clickhouse') // impl=clickhouse

[atroyn]

Persistence requires the user to pass in the persistence_directory which I think functions fine as a flag. I agree that the impl is mostly redundant unless the user wants to use Clickhouse specifically