OptionalmodelThe name of a hosted sparse embedding model. Defaults to pinecone-sparse-english-v0. A dense model is rejected; declare it under embed instead.
Refer to the model guide for available models.
OptionalreadModel-specific parameters applied when embedding search query text, such as truncate. Validated against the model; omitted parameters take the model's defaults. The resolved parameters are returned when the index is described.
OptionalwriteModel-specific parameters applied when embedding document text, such as truncate. Validated against the model; omitted parameters take the model's defaults. The resolved parameters are returned when the index is described.
Learned-sparse embedding configuration for a
stringfield. Pinecone embeds the field's text with a hosted sparse embedding model when documents are upserted or updated, and embeds the query text with the same model when a search scores the field with asparse_embedscoring method.Every key is optional;
{}selects the default model. Sparse embeddings have no dimension or metric, anddimensionormetricis rejected here. The resolved configuration is returned when the index is described. The configuration is fixed at creation and cannot be changed afterwards.A
sparse_embedfield occupies the index's single sparse vector slot, so it cannot be combined with asparse_vectorfield or withsparse_embedon another field.Export
CreateSparseEmbedConfig