E5
Text embedding model family trained on weakly supervised pairs.
Resumen
E5 is an embedding model family trained on large collections of weakly supervised text pairs, with the task described in the input so one model serves queries, passages and classification. It solves the problem that an embedding model trained on one kind of pair transfers poorly to another. It exists because describing the task in the text is a cheap way to make one model cover several retrieval settings.
Grafo de tecnologías
Cómo se conecta E5 con el resto del stack.
Alternativas
-
BGE
model
Una alternativa a E5 · source
-
Cohere Embed
model
Una alternativa a E5 · source
-
GTE
model
Una alternativa a E5 · source
-
Instructor
model
Una alternativa a E5 · source
-
Jina Embeddings
model
Una alternativa a E5 · source
-
Nomic Embed
model
Una alternativa a E5 · source
-
OpenAI Text Embedding 3
model
Una alternativa a E5 · source
Comparativas
Comparativas detalladas con las alternativas anteriores.