Source code for contextgem.public.pipelines

# SPDX-FileCopyrightText: Shcherbak AI AS
# SPDX-License-Identifier: Apache-2.0

"""
Module for handling document processing pipelines.

This module provides the ExtractionPipeline class, which represents a reusable collection
of pre-defined aspects and concepts that can be assigned to documents. Pipelines enable
standardized document analysis by packaging common extraction patterns into reusable units.

Pipelines serve as templates for document processing, allowing consistent application of
the same analysis approach across multiple documents. They encapsulate both the structural
organization (aspects) and the specific information to extract (concepts) in a single,
assignable object.
"""

from __future__ import annotations

from contextgem.internal.base.pipelines import _ExtractionPipeline
from contextgem.internal.decorators import _expose_in_registry




@_expose_in_registry(additional_key=_ExtractionPipeline)
class ExtractionPipeline(_ExtractionPipeline):
    """
    Represents a reusable collection of predefined aspects and concepts for document analysis.

    Extraction pipelines serve as templates that can be assigned to multiple documents,
    ensuring consistent application of the same analysis criteria. They package common
    extraction patterns into reusable units, allowing for standardized document processing.

    :ivar aspects: A list of aspects to extract from documents. Aspects represent structural
                  categories of information. Defaults to an empty list.
    :vartype aspects: list[_Aspect]
    :ivar concepts: A list of concepts to identify within documents. Concepts represent
                   specific information elements to extract. Defaults to an empty list.
    :vartype concepts: list[_Concept]

    Note:
        A pipeline is a reusable configuration of extraction steps. You can use the same pipeline
        to extract data from multiple documents.

    Example:
        .. literalinclude:: ../../../dev/usage_examples/docstrings/pipelines/def_pipeline.py
            :language: python
            :caption: Extraction pipeline definition
    """