RetrieveResultItem#

class langchain_aws.retrievers.kendra.RetrieveResultItem[source]#

Bases: ResultItem

Retrieve API result item.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param Content: str | None = None#

The content of the item.

param DocumentAttributes: List[DocumentAttribute] | None = []#

The document attributes.

param DocumentId: str | None = None#

The document ID.

param DocumentTitle: str | None = None#

The document title.

param DocumentURI: str | None = None#

The document URI.

param Id: str | None = None#

The ID of the relevant result item.

param ScoreAttributes: dict | None = None#

The kendra score confidence

get_additional_metadata() → dict#

Document additional metadata dict. This returns any extra metadata except these:

  • result_id

  • document_id

  • source

  • title

  • excerpt

  • document_attributes

Return type:

dict

get_document_attributes_dict() → Dict[str, str | int | List[str] | None]#

Document attributes dict.

Return type:

Dict[str, str | int | List[str] | None]

get_excerpt() → str[source]#

Document excerpt or passage original content as retrieved by Kendra.

Return type:

str

get_score_attribute() → str#

Document Score Confidence

Return type:

str

get_title() → str[source]#

Document title.

Return type:

str

to_doc(page_content_formatter: ~typing.Callable[[~langchain_aws.retrievers.kendra.ResultItem], str] = <function combined_text>) → Document#

Converts this item to a Document.

Parameters:

page_content_formatter (Callable[[ResultItem], str])

Return type:

Document