Class JtokkitTextSplitter
java.lang.Object
com.github.hakenadu.javalangchains.chains.qa.split.MaxLengthBasedTextSplitter
com.github.hakenadu.javalangchains.chains.qa.split.JtokkitTextSplitter
- All Implemented Interfaces:
TextSplitter
public final class JtokkitTextSplitter extends MaxLengthBasedTextSplitter
This
TextSplitter splits documents based on their token count. For
that purpose jtokkit is
utilized.-
Constructor Summary
Constructors Constructor Description JtokkitTextSplitter(com.knuddels.jtokkit.api.Encoding encoding, int maxTokens)creates an instance ofJtokkitTextSplitterwith sentence based text streamingJtokkitTextSplitter(com.knuddels.jtokkit.api.Encoding encoding, int maxTokens, TextStreamer textStreamer)creates an instance ofJtokkitTextSplitter -
Method Summary
Methods inherited from class com.github.hakenadu.javalangchains.chains.qa.split.MaxLengthBasedTextSplitter
split
-
Constructor Details
-
JtokkitTextSplitter
public JtokkitTextSplitter(com.knuddels.jtokkit.api.Encoding encoding, int maxTokens, TextStreamer textStreamer)creates an instance ofJtokkitTextSplitter- Parameters:
encoding-encodingmaxTokens- max amount of tokens for each chunktextStreamer- theTextStreamerused for streaming the base text
-
JtokkitTextSplitter
public JtokkitTextSplitter(com.knuddels.jtokkit.api.Encoding encoding, int maxTokens)creates an instance ofJtokkitTextSplitterwith sentence based text streaming- Parameters:
encoding-encodingmaxTokens- max amount of tokens for each chunk
-
-
Method Details
-
getLength
Description copied from class:MaxLengthBasedTextSplitterprovide the length value for a text part- Specified by:
getLengthin classMaxLengthBasedTextSplitter- Parameters:
textPart- the text part which needs to be measured- Returns:
- the length for the passed textPart
-