Yuri Victorovich
9 lines
478 B
Plaintext
9 lines
478 B
Plaintext
Docling is a document conversion SDK and CLI that parses PDF, DOCX, PPTX,
|
|
XLSX, HTML, images, and other formats into a unified document representation
|
|
suitable for powering downstream workflows such as retrieval-augmented
|
|
generation (RAG) and gen AI applications.
|
|
|
|
This is the user-facing meta-package that depends on docling-slim with the
|
|
standard extras enabled, providing the full Docling feature set including
|
|
OCR, table structure recognition, and document layout analysis.
|