Project: datalens
81 entity types
Matrix/Architecture/text chunk storage
LayerArchitecture

text chunk storage

Text chunk storage persists extracted text chunks including DOCX and PPTX chunks into the DuckDB database's doc_text_chunks table.

Attributes
labelsEntity,Layer
responsibilitiesManage storage of text chunks extracted from documents, including their metadata and structure for efficient retrieval and processing.
interface patternJSON format with text_content, section_heading, hierarchy, chunk_index, char_count, and optional metadata fields.
allowed dependenciesDepends on document extraction modules and database/storage layers.
Relationships1 connections
Loading graph...