pipelines.extractor.models

Pydantic models for structured information extraction

EntityCollection

def EntityCollection(
    **data:Any
)->None:

Collection of entities extracted from a document.

source

Entity

def Entity(
    **data:Any
)->None:

A named entity extracted from text.

source

DocumentMetadata

def DocumentMetadata(
    **data:Any
)->None:

High-level metadata about a document.

source

KPPCollection

def KPPCollection(
    **data:Any
)->None:

Collection of Key Performance Parameters from acquisition documents.

source

KPPValue

def KPPValue(
    **data:Any
)->None:

A Key Performance Parameter with threshold and objective values.

source

ParamCollection

def ParamCollection(
    **data:Any
)->None:

!!! abstract “Usage Documentation” Models

A base class for creating Pydantic models.

Attributes: class_vars: The names of the class variables defined on the model. private_attributes: Metadata about the private attributes of the model. signature: The synthesized __init__ [Signature][inspect.Signature] of the model.

__pydantic_complete__: Whether model building is completed, or if there are still undefined fields.
__pydantic_core_schema__: The core schema of the model.
__pydantic_custom_init__: Whether the model has a custom `__init__` function.
__pydantic_decorators__: Metadata containing the decorators defined on the model.
    This replaces `Model.__validators__` and `Model.__root_validators__` from Pydantic V1.
__pydantic_generic_metadata__: A dictionary containing metadata about generic Pydantic models.
    The `origin` and `args` items map to the [`__origin__`][genericalias.__origin__]
    and [`__args__`][genericalias.__args__] attributes of [generic aliases][types-genericalias],
    and the `parameter` item maps to the `__parameter__` attribute of generic classes.
__pydantic_parent_namespace__: Parent namespace of the model, used for automatic rebuilding of models.
__pydantic_post_init__: The name of the post-init method for the model, if defined.
__pydantic_root_model__: Whether the model is a [`RootModel`][pydantic.root_model.RootModel].
__pydantic_serializer__: The `pydantic-core` `SchemaSerializer` used to dump instances of the model.
__pydantic_validator__: The `pydantic-core` `SchemaValidator` used to validate instances of the model.

__pydantic_fields__: A dictionary of field names and their corresponding [`FieldInfo`][pydantic.fields.FieldInfo] objects.
__pydantic_computed_fields__: A dictionary of computed field names and their corresponding [`ComputedFieldInfo`][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__: A dictionary containing extra values, if [`extra`][pydantic.config.ConfigDict.extra]
    is set to `'allow'`.
__pydantic_fields_set__: The names of fields explicitly set during instantiation.
__pydantic_private__: Values of private attributes set on the model instance.

source

SystemParameter

def SystemParameter(
    **data:Any
)->None:

!!! abstract “Usage Documentation” Models

A base class for creating Pydantic models.

__pydantic_complete__: Whether model building is completed, or if there are still undefined fields.
__pydantic_core_schema__: The core schema of the model.
__pydantic_custom_init__: Whether the model has a custom `__init__` function.
__pydantic_decorators__: Metadata containing the decorators defined on the model.
    This replaces `Model.__validators__` and `Model.__root_validators__` from Pydantic V1.
__pydantic_generic_metadata__: A dictionary containing metadata about generic Pydantic models.
    The `origin` and `args` items map to the [`__origin__`][genericalias.__origin__]
    and [`__args__`][genericalias.__args__] attributes of [generic aliases][types-genericalias],
    and the `parameter` item maps to the `__parameter__` attribute of generic classes.
__pydantic_parent_namespace__: Parent namespace of the model, used for automatic rebuilding of models.
__pydantic_post_init__: The name of the post-init method for the model, if defined.
__pydantic_root_model__: Whether the model is a [`RootModel`][pydantic.root_model.RootModel].
__pydantic_serializer__: The `pydantic-core` `SchemaSerializer` used to dump instances of the model.
__pydantic_validator__: The `pydantic-core` `SchemaValidator` used to validate instances of the model.

__pydantic_fields__: A dictionary of field names and their corresponding [`FieldInfo`][pydantic.fields.FieldInfo] objects.
__pydantic_computed_fields__: A dictionary of computed field names and their corresponding [`ComputedFieldInfo`][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_extra__: A dictionary containing extra values, if [`extra`][pydantic.config.ConfigDict.extra]
    is set to `'allow'`.
__pydantic_fields_set__: The names of fields explicitly set during instantiation.
__pydantic_private__: Values of private attributes set on the model instance.

# # | notest

# from onprem import LLM
# from onprem.pipelines import Extractor

# # |  notest

# llm = LLM("anthropic/claude-sonnet-4-5", max_tokens=32000, mute_stream=True)

# # | notest


# # Initialize
# extractor = Extractor(llm)

# # Test document
# content = """
#  Aircraft Specifications:
#  - Maximum Speed: 500 mph
#  - Cruise Speed (avg): 350 knots
#  - Operational Range: 2000 nm
#  - Payload Capacity: 5000 lbs
#  - Power Output: 1500 W
#  - Total Weight: 25000 kg
# """

# # Extract with whitelist filtering
# whitelist = {'range', 'cruise speed', 'weight', 'power'}

# result = extractor.extract_parameters(
#      content=content,
#      parameter_whitelist=whitelist,
# )

# # Display results
# print(f"Extracted {len(result['params'])} matching parameters:\n")
# for p in result['params']:
#     print(f"  {p['name']}: {p['value']} {p['unit']}")


# # cruise speed: 350 knots -> matches "cruise speed"
# # range: 2000 nm          -> matches "operational range"
# # power: 1500 W           -> matches "power output"
# # weight: 25000 kg        -> matches "total weight"

  Whitelist filtered params: 6 → 4 items
Extracted 4 matching parameters:

  cruise speed: 350 knots
  range: 2000 nm
  power: 1500 W
  weight: 25000 kg