Jeff Huber
Jeff Huber
@schwebke here is the solution: the type out of `InstructorEmbedding` is not compatible with what we expect. Simply cast it to a `list` ``` search_result = collection.query(query_embeddings=list(q_embeddings), n_results=2) ids =...
Hi everyone - we are releasing an update on Monday (with a seamless migration path) that will move from batch to incremental writes. This will massively improve performance for this...
Completed with Chroma `0.4` - we enable incremental writes persisting to disk.
@PeterTF656 if I understand you correctly - you want to use a lambda to read and write to the persisted DB? just a heads up that if you have 2...
@PeterTF656 I see now. You could certainly use the python or JS client inside a lambda to talk to the backend hosted service. That would work fine.
@PeterTF656 we are going to remove `pandas`, - working on the PR right now
@PeterTF656 https://github.com/chroma-core/chroma/pull/729
@kevmok how much data are you trying to load in? can you try insert only a few documents to see if that works? we have an open PR that is...
@kevmok any chance you could share the file with me so I can reproduce this? I would **love** to help! [email protected]
thanks @kevmok - will look into this this afternoon