Embedding model family that ranks well on retrieval benchmarks.
| Critère | BGE | Nomic Embed |
|---|---|---|
| Dimensions | 1024 | 768 |
| License | MIT | Apache-2.0 |
| Max tokens | 512 | 8192 |
| Open weights | Yes | Yes |
| Provider | BAAI | Nomic AI |
Les lignes grisées sont identiques pour les deux ; ce sont les lignes qui diffèrent qui motivent la recommandation ci-dessous.
Généré à partir des différences ci-dessus par des règles structurées, et non par un modèle.
Choose BGE if…
Aucun des attributs enregistrés ne le distingue à son avantage.
Choose Nomic Embed if…
Aucun des attributs enregistrés ne le distingue à son avantage.
model · Embedding Models
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.
model · Embedding Models
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.
