MetadataModel moved to AbstractEmbeddingModel. #2690
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Embedding models, that didn't have support for a MetadataModel got an additional constructor with MetadataModel as the second argument. I did not include it in all the other constructors since this would break code. AzureOpenAiEmbeddingModel had special handling for empty results, that got lost in the change. Not sure if that is ok. TransformersEmbeddingModel has as default, which differs from the others. Should that be changed to , which seems the most reasonable default to me and is used in the other models?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Embedding models, that didn't have support for a MetadataModel got an additional constructor with MetadataModel as the second argument. I did not include it in all the other constructors since this would break code.
AzureOpenAiEmbeddingModel had special handling for empty results, that got lost in the change. Not sure if that is ok.
TransformersEmbeddingModel has as default, which differs from the others. Should that be changed to , which seems the most reasonable default to me and is used in the other models?
Closes #2579