Refactor ChromadbRM to use collection's default embedding function #449
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Outdated suggestions cannot be applied.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.
The previous PR #400 opened by @animtel set
chromadb.utils.embedding_functions.DefaultEmbeddingFunction
as the default query embedding function. This callsONNXMiniLM_L6_V2
, which usesall-MiniLM-L6-v2
as the base embedding model.This introduced unintended behavior where queries could be embedded using a different model than documents unless the embedding function was explicitly provided. If a model other than
all-MiniLM-L6-v2
embeds queries, and the embedding function is not specified, the query and document embeddings will use different models. While this may be desired in some cases, this should not be the default behavior.This PR changes the default query embedding method to use the collection's embedding function, accessed via the class. Users can still provide a custom embedding model.