Optionalfilter?: objectThe filter to apply. You can use vector metadata to limit your search.
Optionalid?: stringThe unique ID of the vector to be used as a query vector.
Optionalinputs?: objectThe query text to search with. Searching with text is supported only for indexes with integrated embedding.
OptionalmatchTerms?: SearchMatchTermsSpecifies which terms must be present in the text of each search hit based on the specified strategy. The match is performed against the text field specified in the integrated index fieldMap configuration. Terms are normalized and tokenized into single tokens before matching, and order does not matter. Expected format: {strategy: "all", terms: ["term1", "term2", "term3"]} Currently, only "all" strategy is supported, which means all specified terms must be present.
Limitations: matchTerms is only supported for sparse indexes with integrated embedding configured to use the pinecone-sparse-english-v0 model.
The number of similar records to return.
Optionalvector?: SearchRecordsVectorThe SearchRecordsVector to search with, if provided.
The query object used with a SearchRecordsOptions request.