Class InferenceConfig

java.lang.Object
org.apache.tika.inference.InferenceConfig
All Implemented Interfaces:
Serializable
Direct Known Subclasses:
InferenceConfig.RuntimeConfig

public class InferenceConfig extends Object implements Serializable
Configuration for the inference metadata filters.

Controls both the chunking behaviour (how text is split before inference) and the remote endpoint settings (URL, model, auth, timeout).

See Also:
  • Constructor Details

    • InferenceConfig

      public InferenceConfig()
  • Method Details

    • getBaseUrl

      public String getBaseUrl()
    • setBaseUrl

      public void setBaseUrl(String baseUrl) throws TikaConfigException
      Throws:
      TikaConfigException
    • getModel

      public String getModel()
    • setModel

      public void setModel(String model)
    • getApiKey

      public String getApiKey()
    • setApiKey

      public void setApiKey(String apiKey) throws TikaConfigException
      Throws:
      TikaConfigException
    • getTimeoutSeconds

      public int getTimeoutSeconds()
    • setTimeoutSeconds

      public void setTimeoutSeconds(int timeoutSeconds)
    • getMaxChunkChars

      public int getMaxChunkChars()
    • setMaxChunkChars

      public void setMaxChunkChars(int maxChunkChars)
    • getOverlapChars

      public int getOverlapChars()
    • setOverlapChars

      public void setOverlapChars(int overlapChars)
    • getContentField

      public String getContentField()
    • setContentField

      public void setContentField(String contentField)
    • getOutputField

      public String getOutputField()
    • setOutputField

      public void setOutputField(String outputField)
    • isSkipEmbedding

      public boolean isSkipEmbedding()
    • setSkipEmbedding

      public void setSkipEmbedding(boolean skipEmbedding)
    • isClearContentAfterChunking

      public boolean isClearContentAfterChunking()
    • setClearContentAfterChunking

      public void setClearContentAfterChunking(boolean clearContentAfterChunking)
    • getMaxBatchSize

      public int getMaxBatchSize()
    • setMaxBatchSize

      public void setMaxBatchSize(int maxBatchSize)
      Set the maximum number of chunks per embeddings API request. Must be at least 1.
    • getMaxChunks

      public int getMaxChunks()
    • setMaxChunks

      public void setMaxChunks(int maxChunks)
      Set the maximum number of chunks per document. Set to -1 for no limit. Must be -1 or at least 1.