Nomic Embed
Open embedding model with an auditable training set and long context.
Resumen
Nomic Embed is an open embedding model released with an open training dataset and reproducible training run, as well as long-context support. It solves two problems at once: most open embedding models publish weights but not the data they were trained on, which makes their behaviour hard to reason about, and most cap inputs short of a document. It exists because an embedding model whose training data is inspectable can be evaluated for the biases that come from that data.
Grafo de tecnologías
Cómo se conecta Nomic Embed con el resto del stack.
Aplicado a
- RAG technique Techniques Nomic Embed used for RAG High ✓ source
Alternativas
-
BGE
model
Una alternativa a Nomic Embed · source
-
Cohere Embed
model
Una alternativa a Nomic Embed · source
-
E5
model
Una alternativa a Nomic Embed · source
-
GTE
model
Una alternativa a Nomic Embed · source
-
Instructor
model
Una alternativa a Nomic Embed · source
-
Jina Embeddings
model
Una alternativa a Nomic Embed · source
-
OpenAI Text Embedding 3
model
Una alternativa a Nomic Embed · source
Comparativas
Comparativas detalladas con las alternativas anteriores.