Package com.ibm.watson.discovery.v2.model

Class QueryLargePassages

java.lang.Object
com.ibm.cloud.sdk.core.service.model.GenericModel
com.ibm.watson.discovery.v2.model.QueryLargePassages
All Implemented Interfaces:
com.ibm.cloud.sdk.core.service.model.ObjectModel
public class QueryLargePassages
extends com.ibm.cloud.sdk.core.service.model.GenericModel
Configuration for passage retrieval.

  • Method Details

    • newBuilder

      public QueryLargePassages.Builder newBuilder()
      New builder.
      Returns:
      a QueryLargePassages builder

    • enabled

      public Boolean enabled()
      Gets the enabled.

      A passages query that returns the most relevant passages from the results.

      Returns:
      the enabled

    • perDocument

      public Boolean perDocument()
      Gets the perDocument.

      When `true`, passages will be returned within their respective result.

      Returns:
      the perDocument

    • maxPerDocument

      public Long maxPerDocument()
      Gets the maxPerDocument.

      Maximum number of passages to return per result.

      Returns:
      the maxPerDocument

    • fields

      public List<String> fields()
      Gets the fields.

      A list of fields that passages are drawn from. If this parameter not specified, then all top-level fields are included.

      Returns:
      the fields

    • count

      public Long count()
      Gets the count.

      The maximum number of passages to return. The search returns fewer passages if the requested total is not found. The maximum is `100`.

      Returns:
      the count

    • characters

      public Long characters()
      Gets the characters.

      The approximate number of characters that any one passage will have.

      Returns:
      the characters

    • findAnswers

      public Boolean findAnswers()
      Gets the findAnswers.

      When true, `answer` objects are returned as part of each passage in the query results. The primary difference between an `answer` and a `passage` is that the length of a passage is defined by the query, where the length of an `answer` is calculated by Discovery based on how much text is needed to answer the question./n/nThis parameter is ignored if passages are not enabled for the query, or no **natural_language_query** is specified./n/nIf the **find_answers** parameter is set to `true` and **per_document** parameter is also set to `true`, then the document search results and the passage search results within each document are reordered using the answer confidences. The goal of this reordering is to do as much as possible to make sure that the first answer of the first passage of the first document is the best answer. Similarly, if the **find_answers** parameter is set to `true` and **per_document** parameter is set to `false`, then the passage search results are reordered in decreasing order of the highest confidence answer for each document and passage./n/nThe **find_answers** parameter is **beta** functionality available only on managed instances and should not be used in a production environment. This parameter is not available on installed instances of Discovery.

      Returns:
      the findAnswers

    • maxAnswersPerPassage

      public Long maxAnswersPerPassage()
      Gets the maxAnswersPerPassage.

      The number of `answer` objects to return per passage if the **find_answers** parmeter is specified as `true`.

      Returns:
      the maxAnswersPerPassage