parsing_docling

Parse documents using Docling for robust text extraction from complex documents

Parse the data provided by the loader using Docling.

Docling is a more robust and thorough document parsing library that:

• Uses OCR capabilities to extract text from images
• Can parse complex documents with tables and multi-column layouts
• Supports Office formats (DOCX, XLSX, etc.)
• Preserves document structure better than other parsers
• Converts documents to markdown format

Note that docling uses ML models for improved parsing, which makes it slower than simpler parsers like pymupdf.

Samples

SELECT ai.create_vectorizer(
    'my_table'::regclass,
    parsing => ai.parsing_docling(),
    -- other parameters...
);

Arguments

This function takes no arguments.

Returns

A JSON configuration object that you can use in ai.create_vectorizer.