State-of-the-art embedding model from Mistral AI that generates 1024-dimensional vectors for text, supporting semantic search, clustering, and retrieval-augmented generation applications.
mistral-embed is Mistral AI's general-purpose embedding model that transforms text into 1024-dimensional vector representations, capturing semantic meaning for various NLP tasks.
Mistral also offers codestral-embed for code-specific use cases:
Due to norm 1 normalization, all these metrics are equivalent:
Available through Mistral AI's Embeddings API with support for:
Loading more......