azure.ai.language.questionanswering.aio.operations package¶

class azure.ai.language.questionanswering.aio.operations.QuestionAnsweringClientOperationsMixin[source]¶

async query_knowledge_base(options: _models.QueryKnowledgeBaseOptions, *, project_name: str, deployment_name: str, **kwargs: Any) → _models.KnowledgeBaseAnswers[source]¶

async query_knowledge_base(*, project_name: str, deployment_name: str, qna_id: Optional[int] = 'None', question: Optional[str] = 'None', top: Optional[int] = 'None', user_id: Optional[str] = 'None', confidence_score_threshold: Optional[float] = 'None', context: Optional[_models.KnowledgeBaseAnswerRequestContext] = 'None', ranker_type: Optional[Union[str, _models.RankerType]] = 'None', filters: Optional[_models.QueryFilters] = 'None', answer_span_request: Optional[_models.AnswerSpanRequest] = 'None', include_unstructured_sources: Optional[bool] = 'None', **kwargs: Any) → _models.KnowledgeBaseAnswers

Answers the specified question using your knowledge base.

Parameters

options (QueryKnowledgeBaseOptions) – POST body of the request. Provide either options, OR individual keyword arguments. If both are provided, only the options object will be used.

Keyword Arguments

project_name (str) – The name of the project to use.
deployment_name (str) – The name of the specific deployment of the project to use.
qna_id (int) – Exact QnA ID to fetch from the knowledge base, this field takes priority over question.
question (str) – User question to query against the knowledge base. Provide either options, OR individual keyword arguments. If both are provided, only the options object will be used.
top (int) – Max number of answers to be returned for the question.
user_id (str) – Unique identifier for the user.
confidence_score_threshold (float) – Minimum threshold score for answers, value ranges from 0 to 1.
context (KnowledgeBaseAnswerRequestContext) – Context object with previous QnA’s information.
ranker_type (str or RankerType) – (Optional) Set to ‘QuestionOnly’ for using a question only Ranker. Possible values include: “Default”, “QuestionOnly”.
filters (QueryFilters) – Filter QnAs based on give metadata list and knowledge base source names.
answer_span_request (AnswerSpanRequest) – To configure Answer span prediction feature.
include_unstructured_sources (bool) – (Optional) Flag to enable Query over Unstructured Sources.

Returns

KnowledgeBaseAnswers

Return type

KnowledgeBaseAnswers

Raises

~azure.core.exceptions.HttpResponseError

async query_text(options: _models.QueryTextOptions, **kwargs: Any) → _models.TextAnswers[source]¶

async query_text(*, question: str, records: List[_models.TextRecord], language: Optional[str] = 'None', **kwargs: Any) → _models.TextAnswers

Answers the specified question using the provided text in the body.