cuery.tools.flex.generic
========================

.. py:module:: cuery.tools.flex.generic

.. autoapi-nested-parse::

   Tool(s) to iterate over data with a response model defined by json schemas.

   The idea is to first generate a schema with an LLM using the `SchemaGenerator` tool,
   then use that schema process records with the `Generic` tool.



Attributes
----------

.. autoapisummary::

   cuery.tools.flex.generic.GENERIC_PROMPT
   cuery.tools.flex.generic.SCHEMA_CONVERSION_PROMPT


Classes
-------

.. autoapisummary::

   cuery.tools.flex.generic.Generic
   cuery.tools.flex.generic.Auto


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

.. py:data:: GENERIC_PROMPT
   :value: ''


.. py:data:: SCHEMA_CONVERSION_PROMPT
   :value: ''


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

   Bases: :py:obj:`cuery.tools.flex.base.FlexTool`


   Tools that iterates over records with a JSON-schema response model.


   .. py:attribute:: response_schema
      :type:  dict

      JSON schema used as response model.


   .. py:attribute:: instructions
      :type:  str

      Instructions for the tool, describing its purpose and how to use it.


   .. py:property:: prompt
      :type: cuery.Prompt


      Generate a prompt string based on the instructions and current schema.


   .. py:property:: response_model
      :type: cuery.ResponseClass


      Defines the response model for this tool (ClassVar or property).


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

   Bases: :py:obj:`Generic`


   Fully automatic, general-purpose tool for processing data records.

   First auto-generates a response model from the response model instructions,
   then iterates over the records using that model and the provided tools
   instructions.


   .. py:attribute:: response_schema
      :type:  str | dict | None
      :value: None


      Instructions to generate a JSON schema used as response model.


   .. py:attribute:: schema_model
      :type:  str
      :value: None


      Specific model to use to generate the JSON schema.


   .. py:attribute:: _response
      :type:  cuery.ResponseSet | None
      :value: None



   .. py:property:: prompt
      :type: cuery.Prompt


      Generate a prompt string based on the instructions and current schema.


   .. py:method:: response_model()
      :async:


      Defines the response model for this tool (ClassVar or property).



   .. py:method:: task()
      :async:


      Create a Task instance for this tool.



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


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