[ENH] Update Jina Embedding Function to support v3 with new parameters

[moltrus]

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:

• Upgraded the default Jina model from jina-embeddings-v2-base-en to jina-embeddings-v3.
• Added new parameters to enhance flexibility:
  • 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 as float, binary (for faster retrieval), or base64 (for efficient transmission)
• Updated docstrings to reflect the new parameters and functionality.