OpenAI Text Embedding 3
Hosted embedding models with configurable output dimensions.
Resumen
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.
Grafo de tecnologías
Cómo se conecta OpenAI Text Embedding 3 con el resto del stack.
Aplicado a
- RAG technique Techniques OpenAI Text Embedding 3 used for RAG High ✓ source
Herramientas
Software que implementa o se integra con OpenAI Text Embedding 3.
LLM Frameworks
Alternativas
-
BGE
model
Una alternativa a OpenAI Text Embedding 3 · source
-
Cohere Embed
model
Una alternativa a OpenAI Text Embedding 3 · source
-
E5
model
Una alternativa a OpenAI Text Embedding 3 · source
-
GTE
model
Una alternativa a OpenAI Text Embedding 3 · source
-
Instructor
model
Una alternativa a OpenAI Text Embedding 3 · source
-
Jina Embeddings
model
Una alternativa a OpenAI Text Embedding 3 · source
-
Nomic Embed
model
Una alternativa a OpenAI Text Embedding 3 · source
Comparativas
Comparativas detalladas con las alternativas anteriores.