OpenAI Text Embedding 3
Hosted embedding models with configurable output dimensions.
Überblick
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.
Technologiegraph
Wie OpenAI Text Embedding 3 mit dem übrigen Stack zusammenhängt.
Angewendet auf
- RAG technique Techniques OpenAI Text Embedding 3 used for RAG High ✓ source
Werkzeuge
Software, die OpenAI Text Embedding 3 implementiert oder integriert.
LLM Frameworks
Alternativen
-
BGE
model
Eine Alternative zu OpenAI Text Embedding 3 · source
-
Cohere Embed
model
Eine Alternative zu OpenAI Text Embedding 3 · source
-
E5
model
Eine Alternative zu OpenAI Text Embedding 3 · source
-
GTE
model
Eine Alternative zu OpenAI Text Embedding 3 · source
-
Instructor
model
Eine Alternative zu OpenAI Text Embedding 3 · source
-
Jina Embeddings
model
Eine Alternative zu OpenAI Text Embedding 3 · source
-
Nomic Embed
model
Eine Alternative zu OpenAI Text Embedding 3 · source
Vergleiche
Detaillierte Gegenüberstellungen mit den Alternativen oben.