Package com.logicaldoc.ai.embedding
Class EmbeddingTextUtils
java.lang.Object
com.logicaldoc.ai.embedding.EmbeddingTextUtils
Utility class for chunking and sanitizing
- Since:
- 9.2.2
- Author:
- Giuseppe Desiato - LogicalDOC
-
Method Summary
Modifier and TypeMethodDescriptionChunk using a reasonable default policy (used when no per-model Chunking is available).Chunk using a model-specific policy.static StringNormalize and sanitize text before tokenization/embedding.
-
Method Details
-
chunk
Chunk using a model-specific policy. -
chunk
Chunk using a reasonable default policy (used when no per-model Chunking is available). -
sanitize
Normalize and sanitize text before tokenization/embedding.
-