llmp.components.generator.simple.Generator

class llmp.components.generator.simple.Generator(job: JobRecord, job_settings: dict = None, **kwargs)

Basic generator that runs a job once.

This generator is used to run a job once and return the parsed output according job’s output_model.

Initialize the generator with a job and job settings.

Parameters

• job (JobRecord) – the job to be executed

• job_settings (dict) – the job settings to be used

• **kwargs – any - passed to load_engine_from_job

Attributes

verification_type

Return the validation type for the generator.

Methods

__init__(job[, job_settings])	Initialize the generator with a job and job settings.
generate(input_data, **kwargs)	Generate an output based on the job and input data.
log_generation(input_object, ...)	Log the generation result.

__init__(job: JobRecord, job_settings: dict = None, **kwargs)

Initialize the generator with a job and job settings.

Parameters

• job (JobRecord) – the job to be executed

• job_settings (dict) – the job settings to be used

• **kwargs – any - passed to load_engine_from_job

generate(input_data: dict, **kwargs) → Tuple[dict, dict]

Generate an output based on the job and input data.

loads the engine from the job and runs it with the input data.

Parameters

• input_data (dict) – Input data for the job. With prompt placeholder as keys

• **kwargs – any - passed to engine.run() method

log_generation(input_object: dict, generated_object: dict, run_metrics: dict, **kwargs) → Optional[Event]

Log the generation result.

Parameters

• input_object (dict) – the input object

• generated_object (dict) – the generated object

• run_metrics (dict) – the run metrics

• **kwargs – any - passed to JobRecord.log_generation