rag.core.loaders
================

.. py:module:: rag.core.loaders

.. autoapi-nested-parse::

   Framework-agnostic PDF page loading for ingest backends.



Classes
-------

.. autoapisummary::

   rag.core.loaders.PageDocument


Functions
---------

.. autoapisummary::

   rag.core.loaders.list_pdf_paths
   rag.core.loaders.load_pdf_pages


Module Contents
---------------

.. py:class:: PageDocument

   One extractable PDF page.

   :ivar text: Prose text from the page.
   :vartype text: str
   :ivar metadata: File name, path, and 1-based page fields shared by all backends.

   :vartype metadata: dict


   .. py:attribute:: text
      :type:  str


   .. py:attribute:: metadata
      :type:  dict[str, Any]


.. py:function:: list_pdf_paths(*, papers_dir: pathlib.Path) -> list[pathlib.Path]

   List PDF files under ``papers_dir`` (non-recursive).

   :param papers_dir: Directory containing PDFs.
   :type papers_dir: Path

   :returns: Sorted PDF paths.
   :rtype: list of Path

   :raises FileNotFoundError: If the directory does not exist or contains no PDFs.


.. py:function:: load_pdf_pages(*, pdf_paths: collections.abc.Sequence[pathlib.Path]) -> list[PageDocument]

   Extract per-page prose from PDFs with pypdf.

   Pages that fail ``is_prose_text`` (figures, dedications, glyph salad) are
   skipped.

   :param pdf_paths: PDF files to load.
   :type pdf_paths: sequence of Path

   :returns: One document per extractable page.
   :rtype: list of PageDocument

   :raises FileNotFoundError: If no page yields extractable text.