| | |
- gen_ai_hub.orchestration.models.base.JSONSerializable(abc.ABC)
-
- OrchestrationConfig
class OrchestrationConfig(gen_ai_hub.orchestration.models.base.JSONSerializable) |
| |
OrchestrationConfig(template: Union[gen_ai_hub.orchestration.models.template.Template, gen_ai_hub.orchestration.models.template_ref.TemplateRef], llm: gen_ai_hub.orchestration.models.llm.LLM, filtering: Optional[gen_ai_hub.orchestration.models.content_filtering.ContentFiltering] = None, data_masking: Optional[gen_ai_hub.orchestration.models.data_masking.DataMasking] = None, grounding: Optional[gen_ai_hub.orchestration.models.document_grounding.GroundingModule] = None, stream_options: Optional[dict] = None, translation: Optional[gen_ai_hub.orchestration.models.translation.translation.Translation] = None)
Configuration for the Orchestration Service's content generation process.
Defines modules for a harmonized API that combines LLM-based content generation
with additional processing functionalities.
The orchestration service allows for advanced content generation by processing inputs through a series of steps:
template rendering, text generation via LLMs, and optional input/output transformations such as data masking
or filtering.
|
| |
- Method resolution order:
- OrchestrationConfig
- gen_ai_hub.orchestration.models.base.JSONSerializable
- abc.ABC
- builtins.object
Methods defined here:
- __init__(self, template: Union[gen_ai_hub.orchestration.models.template.Template, gen_ai_hub.orchestration.models.template_ref.TemplateRef], llm: gen_ai_hub.orchestration.models.llm.LLM, filtering: Optional[gen_ai_hub.orchestration.models.content_filtering.ContentFiltering] = None, data_masking: Optional[gen_ai_hub.orchestration.models.data_masking.DataMasking] = None, grounding: Optional[gen_ai_hub.orchestration.models.document_grounding.GroundingModule] = None, stream_options: Optional[dict] = None, translation: Optional[gen_ai_hub.orchestration.models.translation.translation.Translation] = None)
- Initializes the OrchestrationConfig with specified modules.
:param template: template for rendering input prompts
:type template: Union[Template, TemplateRef]
:param llm: language model for text generation
:type llm: LLM
:param filtering: content filtering module, defaults to None
:type filtering: Optional[ContentFiltering], optional
:param data_masking: data masking module, defaults to None
:type data_masking: Optional[DataMasking], optional
:param grounding: document grounding module, defaults to None
:type grounding: Optional[GroundingModule], optional
:param stream_options: global streaming options, defaults to None
:type stream_options: Optional[dict], optional
:param translation: translation module, defaults to None
:type translation: Optional[Translation], optional
- to_dict(self)
- Converts the orchestration configuration to a dictionary format.
:return: dictionary representation of the orchestration configuration.
:rtype: dict
Data and other attributes defined here:
- __abstractmethods__ = frozenset()
- __annotations__ = {}
Data descriptors inherited from gen_ai_hub.orchestration.models.base.JSONSerializable:
- __dict__
- dictionary for instance variables (if defined)
- __weakref__
- list of weak references to the object (if defined)
| |