The ``splitter.py`` module
==========================

.. py:module:: src.allie.flowkit.endpoints.splitter


Summary
-------








.. py:currentmodule:: splitter
.. tab-set::







    .. tab-item:: Functions

        .. list-table::
          :header-rows: 0
          :widths: auto


          * - :py:obj:`~split_ppt`
            - Endpoint for splitting text in a PowerPoint document into chunks.


          * - :py:obj:`~split_py`
            - Endpoint for splitting Python code into chunks.


          * - :py:obj:`~split_pdf`
            - Endpoint for splitting text in a PDF document into chunks.


          * - :py:obj:`~process_ppt`
            - Process a PowerPoint document to split text into chunks.


          * - :py:obj:`~process_python_code`
            - Process Python code to split text into chunks.


          * - :py:obj:`~process_pdf`
            - Process a PDF document to split text into chunks.


          * - :py:obj:`~validate_request`
            - Validate the splitter request and API key.



    .. tab-item:: Attributes

        .. list-table::
          :header-rows: 0
          :widths: auto


          * - :py:obj:`~router`
            - 



    .. tab-item:: Constants

        .. list-table::
          :header-rows: 0
          :widths: auto


          * - :py:obj:`~TOKEN_TO_CHARACTER_MULTIPLIER`
            - 















Description
-----------

Module for splitting text into chunks.

..
    !! processed by numpydoc !!






Module detail
-------------

.. py:function:: split_ppt(request: allie.flowkit.models.splitter.SplitterRequest, api_key: str = Header(...)) -> allie.flowkit.models.splitter.SplitterResponse
   :async:


   
   Endpoint for splitting text in a PowerPoint document into chunks.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'

       **api_key** : :class:`python:str`
           The API key for authentication.














   ..
       !! processed by numpydoc !!

.. py:function:: split_py(request: allie.flowkit.models.splitter.SplitterRequest, api_key: str = Header(...)) -> allie.flowkit.models.splitter.SplitterResponse
   :async:


   
   Endpoint for splitting Python code into chunks.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'

       **api_key** : :class:`python:str`
           The API key for authentication.



   :Returns:

       :obj:`SplitterResponse`
           An object containing a list of text chunks.











   ..
       !! processed by numpydoc !!

.. py:function:: split_pdf(request: allie.flowkit.models.splitter.SplitterRequest, api_key: str = Header(...)) -> allie.flowkit.models.splitter.SplitterResponse
   :async:


   
   Endpoint for splitting text in a PDF document into chunks.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'.

       **api_key** : :class:`python:str`
           The API key for authentication.



   :Returns:

       :obj:`SplitterResponse`
           An object containing a list of text chunks.











   ..
       !! processed by numpydoc !!

.. py:function:: process_ppt(request: allie.flowkit.models.splitter.SplitterRequest) -> allie.flowkit.models.splitter.SplitterResponse

   
   Process a PowerPoint document to split text into chunks.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'



   :Returns:

       :obj:`SplitterResponse`
           An object containing a list of text chunks.











   ..
       !! processed by numpydoc !!

.. py:function:: process_python_code(request: allie.flowkit.models.splitter.SplitterRequest) -> allie.flowkit.models.splitter.SplitterResponse

   
   Process Python code to split text into chunks.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'



   :Returns:

       :obj:`SplitterResponse`
           An object containing a list of text chunks.











   ..
       !! processed by numpydoc !!

.. py:function:: process_pdf(request: allie.flowkit.models.splitter.SplitterRequest) -> allie.flowkit.models.splitter.SplitterResponse

   
   Process a PDF document to split text into chunks.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'



   :Returns:

       :obj:`SplitterResponse`
           An object containing a list of text chunks.











   ..
       !! processed by numpydoc !!

.. py:function:: validate_request(request: allie.flowkit.models.splitter.SplitterRequest, api_key: str)

   
   Validate the splitter request and API key.


   :Parameters:

       **request** : :obj:`SplitterRequest`
           An object containing 'document_content' in Base64,
           'chunk_size', and 'chunk_overlap'

       **api_key** : :class:`python:str`
           The API key for authentication.







   :Raises:

       :obj:`HTTPException`
           If the API key is invalid or if any of the request parameters are invalid.







   ..
       !! processed by numpydoc !!

.. py:data:: TOKEN_TO_CHARACTER_MULTIPLIER
   :value: 4


.. py:data:: router