langchain_experimental.rl_chain.pick_best_chain.PickBestFeatureEmbedder¶
- class langchain_experimental.rl_chain.pick_best_chain.PickBestFeatureEmbedder(auto_embed: bool, model: Optional[Any] = None, *args: Any, **kwargs: Any)[source]¶
将`BasedOn`和`ToSelectFrom`输入嵌入到可以被学习策略使用的格式中。
- 属性:
model name (Any, optional): 用于特征表示的嵌入类型。默认为BERT SentenceTransformer。
Methods
__init__(auto_embed[, model])format(event)format_auto_embed_off(event)将`BasedOn`和`ToSelectFrom`转换为VW可用的格式
format_auto_embed_on(event)get_indexed_dot_product(context_emb, action_embs)get_label(event)- Parameters
auto_embed (bool) –
model (Optional[Any]) –
args (Any) –
kwargs (Any) –
- __init__(auto_embed: bool, model: Optional[Any] = None, *args: Any, **kwargs: Any)[source]¶
- Parameters
auto_embed (bool) –
model (Optional[Any]) –
args (Any) –
kwargs (Any) –
- format(event: PickBestEvent) str[source]¶
- Parameters
event (PickBestEvent) –
- Return type
str
- format_auto_embed_off(event: PickBestEvent) str[source]¶
将`BasedOn`和`ToSelectFrom`转换为VW可用的格式
- Parameters
event (PickBestEvent) –
- Return type
str
- format_auto_embed_on(event: PickBestEvent) str[source]¶
- Parameters
event (PickBestEvent) –
- Return type
str
- get_context_and_action_embeddings(event: PickBestEvent) tuple[source]¶
- Parameters
event (PickBestEvent) –
- Return type
tuple
- get_indexed_dot_product(context_emb: List, action_embs: List) Dict[source]¶
- Parameters
context_emb (List) –
action_embs (List) –
- Return type
Dict
- get_label(event: PickBestEvent) tuple[source]¶
- Parameters
event (PickBestEvent) –
- Return type
tuple