Package co.elastic.clients.elasticsearch.ml

Class CommonTokenizationConfig.AbstractBuilder<BuilderT extends CommonTokenizationConfig.AbstractBuilder<BuilderT>>

java.lang.Object
co.elastic.clients.util.ObjectBuilderBase
co.elastic.clients.util.WithJsonObjectBuilderBase<BuilderT>
co.elastic.clients.elasticsearch.ml.CommonTokenizationConfig.AbstractBuilder<BuilderT>
All Implemented Interfaces:
WithJson<BuilderT>
Direct Known Subclasses:
NlpBertTokenizationConfig.Builder, NlpRobertaTokenizationConfig.Builder, XlmRobertaTokenizationConfig.Builder
Enclosing class:
CommonTokenizationConfig
public abstract static class CommonTokenizationConfig.AbstractBuilder<BuilderT extends CommonTokenizationConfig.AbstractBuilder<BuilderT>> extends WithJsonObjectBuilderBase<BuilderT>

  • Constructor Details

    • AbstractBuilder

      public AbstractBuilder()

  • Method Details

    • doLowerCase

      public final BuilderT doLowerCase(@Nullable Boolean value)
      Should the tokenizer lower case the text

      API name: do_lower_case

    • maxSequenceLength

      public final BuilderT maxSequenceLength(@Nullable Integer value)
      Maximum input sequence length for the model

      API name: max_sequence_length

    • span

      public final BuilderT span(@Nullable Integer value)
      Tokenization spanning options. Special value of -1 indicates no spanning takes place

      API name: span

    • truncate

      public final BuilderT truncate(@Nullable TokenizationTruncate value)
      Should tokenization input be automatically truncated before sending to the model for inference

      API name: truncate

    • withSpecialTokens

      public final BuilderT withSpecialTokens(@Nullable Boolean value)
      Is tokenization completed with special tokens

      API name: with_special_tokens

    • self

      protected abstract BuilderT self()
      Specified by:
      self in class WithJsonObjectBuilderBase<BuilderT extends CommonTokenizationConfig.AbstractBuilder<BuilderT>>