Instructor
Embedding model that takes a task instruction alongside the text.
Overview
Instructor embeds text together with an instruction describing what the embedding is for, so one model serves retrieval, clustering and classification without fine-tuning for each. It solves the problem that a single fixed embedding cannot be optimal for several different tasks, and fine-tuning a copy per task is expensive and easy to get wrong. It exists because telling the model what kind of similarity you want is a cheap substitute for training it to want that.
Technology Graph
How Instructor connects to the rest of the stack.
Alternatives
-
BGE
model
An alternative to Instructor · source
-
Cohere Embed
model
An alternative to Instructor · source
-
E5
model
An alternative to Instructor · source
-
GTE
model
An alternative to Instructor · source
-
Jina Embeddings
model
An alternative to Instructor · source
-
Nomic Embed
model
An alternative to Instructor · source
-
OpenAI Text Embedding 3
model
An alternative to Instructor · source
Comparisons
Side-by-side breakdowns with the alternatives above.