langchain_experimental.rl_chain.pick_best_chain.PickBestRandomPolicy

class langchain_experimental.rl_chain.pick_best_chain.PickBestRandomPolicy(feature_embedder: Embedder, **kwargs: Any)

随机策略用于选择最佳链。

方法

__init__(feature_embedder, **kwargs)
learn(event)
log(event)
predict(event)
save()

参数

• feature_embedder (base.Embedder) –

• kwargs (Any) –

__init__(feature_embedder: Embedder, **kwargs: Any)

参数

• feature_embedder (Embedder) –

• kwargs (Any) –

learn(event: PickBestEvent) → None

参数

event (PickBestEvent) –

返回类型

None

log(event: PickBestEvent) → None

参数

event (PickBestEvent) –

返回类型

None

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

参数

event (PickBestEvent) –

返回类型

列表[元组[int, float]]

save() → None

返回类型

None