Cohere Embed
Hosted multilingual embedding model with separate query and document modes.
Aperçu
Cohere Embed is a hosted embedding model that distinguishes the query from the document being indexed, and supports a hundred languages in one model. It solves the asymmetry problem explicitly: a question and a passage are not the same kind of text, and encoding them with the same mode is a compromise. It exists because multilingual retrieval otherwise means either a separate model per language or one model doing all of them badly.
Graphe des technologies
Comment Cohere Embed se rattache au reste de la pile.
Appliqué à
- AI Search application Applications Cohere Embed used for AI Search High ✓ source
- RAG technique Techniques Cohere Embed used for RAG High ✓ source
Outils
Logiciels qui implémentent Cohere Embed ou s'y intègrent.
LLM Frameworks
Alternatives
-
BGE
model
Une alternative à Cohere Embed · source
-
E5
model
Une alternative à Cohere Embed · source
-
GTE
model
Une alternative à Cohere Embed · source
-
Instructor
model
Une alternative à Cohere Embed · source
-
Jina Embeddings
model
Une alternative à Cohere Embed · source
-
Nomic Embed
model
Une alternative à Cohere Embed · source
-
OpenAI Text Embedding 3
model
Une alternative à Cohere Embed · source
Comparaisons
Comparaisons détaillées avec les alternatives ci-dessus.