检索查询引擎

class llama_index.query_engine.retriever_query_engine.RetrieverQueryEngine(retriever: BaseRetriever, response_synthesizer: Optional[ResponseSynthesizer] = None, callback_manager: Optional[CallbackManager] = None)

Retriever query engine.

参数
classmethod from_args(retriever: BaseRetriever, service_context: Optional[ServiceContext] = None, node_postprocessors: Optional[List[BaseNodePostprocessor]] = None, verbose: bool = False, response_mode: ResponseMode = ResponseMode.COMPACT, text_qa_template: Optional[Prompt] = None, refine_template: Optional[Prompt] = None, simple_template: Optional[Prompt] = None, response_kwargs: Optional[Dict] = None, use_async: bool = False, streaming: bool = False, optimizer: Optional[BaseTokenUsageOptimizer] = None, **kwargs: Any) → RetrieverQueryEngine

Initialize a RetrieverQueryEngine object."

参数

  • retriever (BaseRetriever) -- A retriever object.

  • service_context (Optional[ServiceContext]) -- A ServiceContext object.

  • node_postprocessors (Optional[List[BaseNodePostprocessor]]) -- A list of node postprocessors.

  • verbose (bool) -- Whether to print out debug info.

  • response_mode (ResponseMode) -- A ResponseMode object.

  • text_qa_template (Optional[QuestionAnswerPrompt]) -- A QuestionAnswerPrompt object.

  • refine_template (Optional[RefinePrompt]) -- A RefinePrompt object.

  • simple_template (Optional[SimpleInputPrompt]) -- A SimpleInputPrompt object.

  • response_kwargs (Optional[Dict]) -- A dict of response kwargs.

  • use_async (bool) -- Whether to use async.

  • streaming (bool) -- Whether to use streaming.

  • optimizer (Optional[BaseTokenUsageOptimizer]) -- A BaseTokenUsageOptimizer object.

property retriever: BaseRetriever

Get the retriever object.