选择最佳随机策略#

class langchain_experimental.rl_chain.pick_best_chain.PickBestRandomPolicy(feature_embedder: Embedder, **kwargs: Any)[源代码]#

PickBest链的随机策略。

方法

__init__(feature_embedder, **kwargs)

learn(event)

log(event)

predict(event)

save()

Parameters:
__init__(feature_embedder: Embedder, **kwargs: Any)[来源]#
Parameters:

  • feature_embedder (Embedder)

  • kwargs (Any)

learn(event: PickBestEvent) → None[来源]#
Parameters:

事件 (PickBestEvent)

Return type:

无

log(event: PickBestEvent) → None[source]#
Parameters:

事件 (PickBestEvent)

Return type:

无

predict(event: PickBestEvent) → List[Tuple[int, float]][来源]#
Parameters:

事件 (PickBestEvent)

Return type:

列表[元组[int, float]]

save() → None#
Return type:

无