[ENH] Update Jina Embedding Function to support v3 with new parameters #4078
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Outdated suggestions cannot be applied.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.
Description of Changes
Upgraded the default embedding model from jina-embeddings-v2-base-en to jina-embeddings-v3, incorporating new API parameters. The updated version provides better performance, multilingual support (89 languages), and MRL embeddings.
Key Changes:
jina-embeddings-v2-base-entojina-embeddings-v3.task: Allows selection of LoRA adapters for specific downstream tasks.late_chunking: Supports token embedding, chunking, and pooling for improved context awareness.dimensions: Enables setting a custom dimensionality to optimize storage and performance.embedding_type: Supports output asfloat,binary(for faster retrieval), orbase64(for efficient transmission)