OpenAI Text Embedding 3
Hosted embedding models with configurable output dimensions.
Aperçu
Text Embedding 3 is OpenAI's hosted embedding family, notable for letting the caller choose a shorter output vector than the model natively produces. It solves the storage problem directly: embedding indexes are sized by dimensions times vectors, so trimming 3072 dimensions to 512 or 256 shrinks the index substantially at a small quality cost. It exists because that trade is one the caller is better placed to make than the model author, and it removes the need to retrain to change it.
Graphe des technologies
Comment OpenAI Text Embedding 3 se rattache au reste de la pile.
Appliqué à
- RAG technique Techniques OpenAI Text Embedding 3 used for RAG High ✓ source
Outils
Logiciels qui implémentent OpenAI Text Embedding 3 ou s'y intègrent.
LLM Frameworks
Alternatives
-
BGE
model
Une alternative à OpenAI Text Embedding 3 · source
-
Cohere Embed
model
Une alternative à OpenAI Text Embedding 3 · source
-
E5
model
Une alternative à OpenAI Text Embedding 3 · source
-
GTE
model
Une alternative à OpenAI Text Embedding 3 · source
-
Instructor
model
Une alternative à OpenAI Text Embedding 3 · source
-
Jina Embeddings
model
Une alternative à OpenAI Text Embedding 3 · source
-
Nomic Embed
model
Une alternative à OpenAI Text Embedding 3 · source
Comparaisons
Comparaisons détaillées avec les alternatives ci-dessus.