Jina CLIP v2 is a state-of-the-art multilingual and multimodal (text-image) embedding model, It excels in both cross-modal (text-to-image, image-to-text) and unimodal (text-to-text) retrieval tasks within a single vector space. It supports 100 languages with a focus on 30 (including English, Spanish, Chinese, Arabic, and more), it supports flexible embedding generation through Matryoshka Representation Learning (MRL) and allows for shortened vector lengths via the dimensions parameter.
from pinecone import Pinecone, ServerlessSpecpc = Pinecone(api_key="API_KEY")JINA_API_KEY = "" # Replace with your Jina API keydimension = 1024 # Specify the desired embedding dimensionindex_name = "jina-clip-v2"if not pc.has_index(index_name): pc.create_index( name=index_name, dimension=dimension, metric="cosine", spec=ServerlessSpec( cloud='aws', region='us-east-1' # Replace with your preferred region ) )index = pc.Index(index_name)