OptionalfieldThe one-field form of fields.
OptionalfieldsThe fields to score against. Provide fields or field (not both) for every type except query_string, which takes neither.
text accepts one or more fields; the other types accept exactly one.
OptionalparametersModel parameters for embedding the query of an embed clause in this search, such as
{ task_type: 'fact_verification' }. They override the field's readParameters. Today only task_type can be
set; pc.inference.listModels() lists the models that accept it. The API validates the keys and values, and
rejects parameters on every other clause type, sparse_embed included.
OptionalqueryThe text query for text, query_string, embed, and sparse_embed. For embed and sparse_embed, Pinecone embeds
this text with the named field's model. Leading and trailing whitespace is trimmed, and an empty query is rejected.
OptionalsparseThe sparse query vector for sparse_vector.
The scoring method: dense_vector, sparse_vector, text, query_string, embed, or sparse_embed.
OptionalvaluesThe dense query vector for dense_vector. Its length must match the field's dimension.
A scoring method that defines how documents are scored against a query.
typeselects the method and which other fields apply:dense_vector:fieldorfieldsnaming one field, andvalues.sparse_vector:fieldorfieldsnaming one field, andsparseValues.text:fieldorfieldsnaming one or more fields, andquery.query_string:queryonly. Use field qualifiers (field:(clause)) in the query to target a field.embed/sparse_embed:fieldorfieldsnaming onestringfield that declaresembed/sparse_embed, andquery. Anembedclause also acceptsparameters.