cuery.tools.flex.base
=====================

.. py:module:: cuery.tools.flex.base


Classes
-------

.. autoapisummary::

   cuery.tools.flex.base.FlexTool


Functions
---------

.. autoapisummary::

   cuery.tools.flex.base.preprocess_records


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

.. py:function:: preprocess_records(records, attrs = None, max_samples = None)

   Sample and filter attributes/columns in records.


.. py:class:: FlexTool(/, **data)

   Bases: :py:obj:`cuery.Tool`


   Base class for tools iterating over data records with arbitrary attributes.


   .. py:attribute:: model_config

      Needed to allow DataFrame and other non-Pydantic types.


   .. py:attribute:: records
      :type:  pandas.DataFrame | list[dict]

      Data records to iterate over.


   .. py:attribute:: attrs
      :type:  list[str] | None
      :value: None


      List of record attributes to use. If None, all attributes are used.


   .. py:attribute:: record_format
      :type:  Literal['json', 'md', 'text']
      :value: 'text'


      Format of the record in the prompt.


   .. py:property:: template
      :type: str


      Get the name of the record template for the prompt.

      Each record/row will be formatted into the prompt using this template.


   .. py:property:: context
      :type: list[dict]


      For each input record, returns an object with a single "record" key.

      Jinja templates can then iterate over the "record" object's attributes


   .. py:method:: __call__(**kwargs)
      :async:


      Normalize the nested input records back into individual columns in output.