Package sk.iway.iwcm.rag.indexing
Interface ContentExtractor<T>
- All Known Implementing Classes:
DocDetailsContentExtractor
public interface ContentExtractor<T>
Interface for extracting plain text from an entity for embedding.
-
Method Summary
Modifier and TypeMethodDescriptionextractText(T entity) Extract text content from the given entity, suitable for embedding.Returns the entity type identifier (e.g., "document").
-
Method Details
-
extractText
Extract text content from the given entity, suitable for embedding.- Parameters:
entity- the source entity- Returns:
- extracted plain text (HTML stripped, includes rendered)
-
getEntityType
RagEntityType getEntityType()Returns the entity type identifier (e.g., "document").
-