Find answers from the community

Updated last month

when i have created an chromaDB with

when i have created an chromaDB with vector indexes, how can i get the filename metadata so i can compare it against incoming docs, to prevent from indexing the same document several times ? anyone ?

3 comments

LLogan M

ideally you keep track of this info outside of chroma (i.e. with a docstore, or some other management layer)

LLogan M

Using the raw api, you could so something like

Plain Text

import chromadb
client = chromadb.Client(...)

coll = client.get_collection("<name of the collection>")
data = coll.get() # Gets all the data

And parse the data from there

hhansson0728

ty, i can work with that

Add a reply