olaf.pipeline.pipeline_component.axiom_extraction package

Submodules

olaf.pipeline.pipeline_component.axiom_extraction.llm_based_axiom_extraction module

class olaf.pipeline.pipeline_component.axiom_extraction.llm_based_axiom_extraction.LLMBasedOWLAxiomExtraction(prompt_template: Callable[[str], List[Dict[str, str]]] | None = None, llm_generator: LLMGenerator | None = None, namespace: str | None = None)

Bases: PipelineComponent

LLM based OWL axiom extraction.

Attributes

prompt_template: Callable[[str], List[Dict[str, str]]]

Prompt template used to give instructions and context to the LLM.

llm_generator: LLMGenerator

The LLM model used to generate axioms.

namespace: str

The name space used for axiom generation, by default “http://www.ms2.org/o/example#”.

check_resources() → None

Method to check that the component has access to all its required resources.

get_performance_report() → Dict[str, Any]

A getter for the pipeline component performance report. If the component has been optimised, it only returns the best performance. Otherwise, it returns the results obtained with the set parameters.

Returns

Dict[str, Any]

The pipeline component performance report.

optimise(validation_terms: Set[str], option_values_map: Set[float]) → None

A method to optimise the pipeline component by tuning the configuration.

run(pipeline: Pipeline) → None

Method that is responsible for the execution of the component. Axioms are created based on the knowledge representation. The RDF graph is set on the knowledge representation.

Parameters

pipeline: Pipeline

The pipeline to run the component with.

olaf.pipeline.pipeline_component.axiom_extraction.owl_axiom_extraction module

class olaf.pipeline.pipeline_component.axiom_extraction.owl_axiom_extraction.OWLAxiomExtraction(owl_axiom_generators: Set[Callable[[KnowledgeRepresentation, URIRef], Graph]], base_uri: str | URIRef | None = None, reasoner: str | None = 'ELK')

Bases: PipelineComponent

The OWL axiom extraction component inductively construct OWL axioms from the knowledge representation based on some OWL ontology modeling patterns.

The component generates the OWL ontology based on the provided patterns, test its semantic consistence with an OWL reasoner and remove axioms until the ontology is consistent.

This component requires the environment variables: - “JAVA_EXE” - “ROBOT_JAR”

Attributes

owl_axiom_generatorsSet[Callable[[KnowledgeRepresentation, URIRef], Graph]]

The function to generate the OWL axioms.

base_uriUnion[str, URIRef], optional

The base URI to use when creating the concepts and relations URIs, by default “http://www.ms2.org/o/example#”.

reasonerstr, optional

The reasoner to use, by default “ELK”. Reasoning is performed using the ROBOT CLI: <https://robot.obolibrary.org/reason>. Hence, possible values are: “hermit”, “jfact”, “whelk”, “emr”, “structural”

java_exe: str

Environment variable path to the Java executable.

robot_jar: str

Environment variable path to the ROBOT CLI .jar file.

graph_to_test_temp_file: PathLike

Temporary file path to store intermediate RDF graphs for consistency check.

tested_graph_temp_file: PathLike

Temporary file path for the inferred triples.

_pattern_nb_classes: str

Regex pattern to match the number of unsatisfiable classes in the ROBOT CLI error message.

_pattern_unsatisfiable_classes: str

Regex pattern to match the unsatisfiable classes URIs in the ROBOT CLI error message.

individuals_axiom_generators: Set[Set[Callable[[KnowledgeRepresentation, URIRef], Graph]]]

A set of the possible OWL axiom generators creating OWL named individuals.

build_full_graph(kr: KnowledgeRepresentation) → Graph

Build the complete RDF graph based on the provided OWL axiom generators.

Parameters

krKnowledgeRepresentation

The knowledge representation to use when build the graph.

Returns

Graph

The constructed RDF graph.

build_graph_without_owl_instances(kr: KnowledgeRepresentation) → Graph

Build the RDF graph based on the provided OWL axiom generators omitting the ones creating OWL named instances.

Parameters

krKnowledgeRepresentation

_description_

Returns

Graph

_description_

check_resources() → None

Method to check that the component has access to all its required resources.

The OWL axiom extraction component requires the environment variables: - “JAVA_EXE” - “ROBOT_JAR”

get_performance_report() → Dict[str, Any]

A getter for the pipeline component performance report.

If the component has been optimised, it only returns the best performance. Otherwise, it returns the results obtained with the set parameters.

Returns

Dict[str, Any]

The pipeline component performance report.

optimise(validation_terms: Set[str], option_values_map: Set[float]) → None

A method to optimise the pipeline component by tuning the options.

run(pipeline: Pipeline) → None

Create the OWL file containing the valid axiomatised Knowledge Representation instance.

Module contents