OpenAI Text Embedding 3
Hosted embedding models with configurable output dimensions.
Overview
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.
Technology Graph
How OpenAI Text Embedding 3 connects to the rest of the stack.
Applied to
- RAG technique Techniques OpenAI Text Embedding 3 used for RAG High ✓ source
Tools
Software that implements or integrates with OpenAI Text Embedding 3.
LLM Frameworks
Alternatives
-
BGE
model
An alternative to OpenAI Text Embedding 3 · source
-
Cohere Embed
model
An alternative to OpenAI Text Embedding 3 · source
-
E5
model
An alternative to OpenAI Text Embedding 3 · source
-
GTE
model
An alternative to OpenAI Text Embedding 3 · source
-
Instructor
model
An alternative to OpenAI Text Embedding 3 · source
-
Jina Embeddings
model
An alternative to OpenAI Text Embedding 3 · source
-
Nomic Embed
model
An alternative to OpenAI Text Embedding 3 · source
Comparisons
Side-by-side breakdowns with the alternatives above.