Specialized queries

OpenSearch supports the following specialized queries:

• agentic: Uses natural language questions that are automatically planned and executed by an agent with a large language model.

• distance_feature: Calculates document scores based on the dynamically calculated distance between the origin and a document’s date, date_nanos, or geo_point fields. This query can skip non-competitive hits.

• knn: Used for searching raw vectors during vector search.

• more_like_this: Finds documents similar to the provided text, document, or collection of documents.

• neural: Used for searching by text or image in vector search.

• neural_sparse: Used for vector field search in sparse neural search.

• percolate: Finds queries (stored as documents) that match the provided document.

• rank_feature: Calculates scores based on the values of numeric features. This query can skip non-competitive hits.

• script: Uses a script as a filter.

• script_score: Calculates a custom score for matching documents using a script.

• template: Allows you to use Mustache templating in queries.

• wrapper: Accepts other queries as JSON or YAML strings.