SentenceChunkingConfiguration Configuration
SentenceChunkingConfiguration Configuration documentation for Java SDK
SentenceChunkingConfiguration
Sentence-based chunking strategy with language detection support
Properties
| Name | Type | Description | Notes |
|---|---|---|---|
| maxChunkSize | Integer | Maximum size of a chunk | |
| minChunkSize | Integer | Minimum size before creating a new chunk | |
| enableLanguageDetection | Boolean | Whether to detect language for better segmentation | [optional] |
| lengthMeasurement | LengthMeasurement | How to measure chunk length |
Usage Example
import ai.pairsys.goodmem.client.model.*;
SentenceChunkingConfiguration config = new SentenceChunkingConfiguration()
.maxChunkSize(1024)
.minChunkSize(100)
.enableLanguageDetection(true)
.lengthMeasurement(LengthMeasurement.CHARACTER_COUNT);