trinity.common.workflows.agentscope_workflow module

trinity.common.workflows.agentscope_workflow module#

class trinity.common.workflows.agentscope_workflow.AgentScopeWorkflowAdapter(*, task: Task, model: ModelWrapper, auxiliary_models: List[ModelWrapper] | None = None)[源代码]#

基类：Workflow

Adapter to wrap a agentscope trainable workflow function into a Trinity Workflow.

is_async: bool = True#
__init__(*, task: Task, model: ModelWrapper, auxiliary_models: List[ModelWrapper] | None = None)[源代码]#

Initialize the adapter with the task and model.

construct_experiences(reward: float) → List[Experience][源代码]#

Construct experiences from the agent's interaction history.

参数:

reward (float) -- The reward value to assign to each experience.

返回:

A list of Experience objects.

返回类型:

List

async run_async() → List[Experience][源代码]#

Run the workflow asynchronously and return experiences.

class trinity.common.workflows.agentscope_workflow.AgentScopeWorkflowAdapterV1(*, task: Task, model: ModelWrapper, auxiliary_models: List[ModelWrapper] | None = None)[源代码]#

基类：Workflow

A more general adapter to wrap agentscope trainable workflow and judge functions into a Trinity Workflow.

is_async: bool = True#
__init__(*, task: Task, model: ModelWrapper, auxiliary_models: List[ModelWrapper] | None = None)[源代码]#

Initialize the adapter with the task and model.

construct_experiences(reward: float, metrics: Dict) → List[Experience][源代码]#

Construct experiences from the agent's interaction history.

参数:

  • reward (float) -- The reward value to assign to each experience.

  • metrics (Dict) -- A dictionary of metrics to be attached to the last experience.

返回:

A list of Experience objects.

返回类型:

List

async run_async() → List[Experience][源代码]#

Run the workflow asynchronously and return experiences.

目录