BGE
Embedding model family that ranks well on retrieval benchmarks.
Resumen
BGE is a family of embedding models trained specifically for retrieval, available in sizes small enough to run locally. It solves the problem that a general-purpose embedding model is not optimised for the asymmetric comparison a search query and a document require. It exists because retrieval quality is set at the embedding step, so a model trained for it improves everything downstream without changing anything else.
Grafo de tecnologías
Cómo se conecta BGE con el resto del stack.
Herramientas
Software que implementa o se integra con BGE.
Benchmarks
LLM Frameworks
Alternativas
-
Cohere Embed
model
Una alternativa a BGE · source
-
E5
model
Una alternativa a BGE · source
-
GTE
model
Una alternativa a BGE · source
-
Instructor
model
Una alternativa a BGE · source
-
Jina Embeddings
model
Una alternativa a BGE · source
-
Nomic Embed
model
Una alternativa a BGE · source
-
OpenAI Text Embedding 3
model
Una alternativa a BGE · source
Comparativas
Comparativas detalladas con las alternativas anteriores.