ie_schema
=========

.. py:module:: ie_schema


Classes
-------

.. autoapisummary::

   ie_schema.ClassificationTask
   ie_schema.EntityExtractionTask
   ie_schema.IESchema
   ie_schema.JSONStructureTask
   ie_schema.RelationExtractionTask
   ie_schema.StructureChild
   ie_schema.Task


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

.. py:class:: ClassificationTask

   Bases: :py:obj:`Task`


   Classification task definition with labels and threshold metadata.


   .. py:property:: labels
      :type: list[str]


      Ordered list of class labels.



   .. py:property:: multi_label
      :type: bool


      Whether multiple labels may be assigned.



   .. py:property:: task
      :type: str


      Classification task name.



   .. py:property:: threshold
      :type: Optional[float]


      Optional confidence threshold for the classification.



.. py:class:: EntityExtractionTask

   Bases: :py:obj:`Task`


   Entity extraction task definition.


   .. py:property:: entities
      :type: list[str]


      Entity labels that should be extracted.



.. py:class:: IESchema

   Information-extraction schema loaded from JSON (or from a dataclass / Pydantic model type).

   Build an `IESchema` from a JSON string with `loads()` (IE ingest JSON or a root JSON Schema
   object), from a path with `load()`, or from a stdlib dataclass / Pydantic v2 `BaseModel` by
   passing the class (or an instance) to `loads()`. Iterating over the object yields task instances
   in schema order.

   Example:
   >>> import ie_schema
   >>> _j = '{"json_structures":[{"name":"Business","business_name":{"dtype":"str"}}]}'
   >>> schema = ie_schema.IESchema.loads(_j)
   >>> isinstance(schema, ie_schema.IESchema)
   True
   >>> len(list(schema))
   1


   .. py:method:: load(path: str) -> IESchema
      :classmethod:


      Parse an `IESchema` from a JSON file path.



   .. py:method:: loads(input: Any) -> IESchema
      :classmethod:


      Parse an `IESchema` from a JSON string or from a dataclass / Pydantic v2 `BaseModel` type.

      String input must be either IE ingest JSON (top-level keys such as `json_structures`,
      `entities`, …) or a root JSON Schema object (`type`, `properties`, …). Unknown top-level
      keys are rejected for the IE shape so JSON Schema is not misread as an empty ingest.

      For a dataclass or `BaseModel` type (or instance), Pydantic v2 builds JSON Schema
      (`TypeAdapter` for dataclasses, `model_json_schema()` for `BaseModel` subclasses), which is
      then parsed like JSON Schema string input.

      Example:
      >>> import ie_schema
      >>> schema = ie_schema.IESchema.loads('{"json_structures":[{"name":"Business","business_name":{"dtype":"str"}}]}')
      >>> len(list(schema))
      1



   .. py:method:: prompt() -> str

      Render the generated extraction prompt as a debug string.

      Example:
      >>> import ie_schema
      >>> schema = ie_schema.IESchema.loads('{"json_structures":[{"name":"Business","business_name":{"dtype":"str"}}]}')
      >>> s = schema.prompt()
      >>> ("[P]" in s) and ("business_name" in s)
      True



.. py:class:: JSONStructureTask

   Bases: :py:obj:`Task`


   Structured JSON extraction task with named children.


   .. py:property:: children
      :type: list[StructureChild]


      Child fields that belong to this structure.



   .. py:property:: name
      :type: str


      Structure name.



.. py:class:: RelationExtractionTask

   Bases: :py:obj:`Task`


   Relation extraction task between head and tail entity types.


   .. py:property:: description
      :type: Optional[str]


      Optional human-readable relation description.



   .. py:property:: head
      :type: str


      Head entity type.



   .. py:property:: name
      :type: str


      Relation name.



   .. py:property:: tail
      :type: str


      Tail entity type.



.. py:class:: StructureChild

   Child field in a `JSONStructureTask`.


   .. py:property:: choices
      :type: list[str]


      Allowed string choices for this property.



   .. py:property:: description
      :type: Optional[str]


      Optional child-field description.



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


      Property name for this child field.



.. py:class:: Task

   Base class for all extraction tasks yielded by `IESchema`.