rag.core.passage
================

.. py:module:: rag.core.passage

.. autoapi-nested-parse::

   Passage selection helpers shared by RAG backends.



Attributes
----------

.. autoapisummary::

   rag.core.passage.AUTHOR_QUESTION_CUES
   rag.core.passage.ACKNOWLEDGEMENT_CUES
   rag.core.passage.PROCEEDINGS_BOILERPLATE_CUES
   rag.core.passage.QA_GROUNDING_RULES


Functions
---------

.. autoapisummary::

   rag.core.passage.is_author_question
   rag.core.passage.is_acknowledgement_text
   rag.core.passage.is_proceedings_boilerplate_text
   rag.core.passage.page_from_mapping


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

.. py:data:: AUTHOR_QUESTION_CUES
   :type:  Final
   :value: ('who wrote', 'who is the writer', 'who is the author', 'who are the authors', 'who is the main...


.. py:data:: ACKNOWLEDGEMENT_CUES
   :type:  Final
   :value: ('acknowledg', 'thanks to', 'thank ', 'grateful to', 'careful revision', 'revising the...


.. py:data:: PROCEEDINGS_BOILERPLATE_CUES
   :type:  Final
   :value: ('edited by', 'proc. of spie', 'ccc code', 'spiedigitallibrary', 'terms of use')


.. py:data:: QA_GROUNDING_RULES
   :type:  Final
   :value: "People thanked for revising a manuscript are not authors. SPIE 'edited by' names are volume...


.. py:function:: is_author_question(*, question: str) -> bool

   Return True when the question is asking who wrote a paper.

   :param question: User question.
   :type question: str

   :returns: True when authorship cues are present.
   :rtype: bool


.. py:function:: is_acknowledgement_text(*, text: str) -> bool

   Return True when text looks like thanks / manuscript revision notes.

   :param text: Chunk or page text.
   :type text: str

   :returns: True when acknowledgement phrasing dominates authorship lists.
   :rtype: bool


.. py:function:: is_proceedings_boilerplate_text(*, text: str) -> bool

   Return True when text is SPIE copyright / volume-editor footer.

   :param text: Chunk or page text.
   :type text: str

   :returns: True when proceedings chrome is present.
   :rtype: bool


.. py:function:: page_from_mapping(*, metadata: dict[str, Any]) -> int | None

   Read a 1-based page number from chunk metadata.

   :param metadata: Loader metadata.
   :type metadata: dict

   :returns: Page number when parseable.
   :rtype: int or None