Fix: ChromaVectorStore can attempt to add in excess of chromadb batch… #8019
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
… size
Description
Changed
ChromaVectorStore.add
to batch inputs at one less than chromadb's max to avoid the oversize error. Adds a class method to do chunking.Fixes #7648
Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
I have passing unit tests on my branch but have not included them. The unit test to add a large number of nodes takes ~5 secs to run. If that's acceptable, I can submit the unit tests for
add
I noticed tests were missing for all of the llama_index.vector_stores.chroma.py. So I also implemented tests for several other methods.
Let me know if you want all the unit tests, all the tests excluding
add
, or none of them.Suggested Checklist:
make format; make lint
to appease the lint gods