langchain_community.llms.bedrock.LLMInputOutputAdapter

class langchain_community.llms.bedrock.LLMInputOutputAdapter

适配器类，用于将Langchain的输入准备成LLM模型期望的格式。

它还提供了一个辅助函数，用于从模型响应中提取生成的文本。

Attributes

provider_to_output_key_map

Methods

__init__()
aprepare_output_stream(provider, response[, ...])
prepare_input(provider, model_kwargs[, ...])
prepare_output(provider, response)
prepare_output_stream(provider, response[, ...])

__init__()

classmethod aprepare_output_stream(provider: str, response: Any, stop: Optional[List[str]] = None) → AsyncIterator[GenerationChunk]

Parameters

• provider (str) –

• response (Any) –

• stop (Optional[List[str]]) –

Return type

AsyncIterator[GenerationChunk]

classmethod prepare_input(provider: str, model_kwargs: Dict[str, Any], prompt: Optional[str] = None, system: Optional[str] = None, messages: Optional[List[Dict]] = None) → Dict[str, Any]

Parameters

• provider (str) –

• model_kwargs (Dict[str, Any]) –

• prompt (Optional[str]) –

• system (Optional[str]) –

• messages (Optional[List[Dict]]) –

Return type

Dict[str, Any]

classmethod prepare_output(provider: str, response: Any) → dict

Parameters

• provider (str) –

• response (Any) –

Return type

dict

classmethod prepare_output_stream(provider: str, response: Any, stop: Optional[List[str]] = None, messages_api: bool = False) → Iterator[GenerationChunk]

Parameters

• provider (str) –

• response (Any) –

• stop (Optional[List[str]]) –

• messages_api (bool) –

Return type

Iterator[GenerationChunk]