SOTA text embedding model with variable dimensionality — outperforms OpenAI text-embedding-ada-002 and text-embedding-3-small models.
texts
the strings to embed.task_type
the task to optimize the embedding for. Can be search_document
(default), search_query
, clustering
, or classification
.dimensionality
the size of each output vector, any integer between 64
and 768
(default).