GTE
Embedding model family from Alibaba, trained for retrieval and ranking.
Overview
GTE is a family of text embedding models trained for retrieval, with variants covering English and multilingual use and long inputs. It solves the same problem as the other retrieval-focused embedding families: a general-purpose encoder is not optimised for the asymmetric comparison of a short query against a long document. It exists because retrieval quality is decided at the embedding step, and a family that scores well on public retrieval benchmarks is the cheapest way to improve everything downstream.
Technology Graph
How GTE connects to the rest of the stack.
Alternatives
-
BGE
model
An alternative to GTE · source
-
Cohere Embed
model
An alternative to GTE · source
-
E5
model
An alternative to GTE · source
-
Instructor
model
An alternative to GTE · source
-
Jina Embeddings
model
An alternative to GTE · source
-
Nomic Embed
model
An alternative to GTE · source
-
OpenAI Text Embedding 3
model
An alternative to GTE · source
Comparisons
Side-by-side breakdowns with the alternatives above.