azure.ai.language.questionanswering package

class azure.ai.language.questionanswering.QuestionAnsweringClient(endpoint: str, credential: AzureKeyCredential, **kwargs: Any)[source]

The language service API is a suite of natural language processing (NLP) skills built with best-in-class Microsoft machine learning algorithms. The API can be used to analyze unstructured text for tasks such as sentiment analysis, key phrase extraction, language detection and question answering. Further documentation can be found in https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/overview.

Parameters
  • endpoint (str) – Supported Cognitive Services endpoint (e.g., https://<resource-name>.api.cognitiveservices.azure.com).

  • credential (AzureKeyCredential) – Credential needed for the client to connect to Azure.

close()None[source]
query_knowledgebase(*args: ‘_models.KnowledgeBaseQueryOptions’, **kwargs: Any)_models.KnowledgeBaseAnswers

Answers the specified question using your knowledge base.

Parameters

knowledge_base_query_options (KnowledgeBaseQueryOptions) – Post body of the request. Provide either knowledge_base_query_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.

  • question (str) – User question to query against the knowledge base. Provide either knowledge_base_query_options, OR individual keyword arguments. If both are provided, only the options object will be used.

  • qna_id (int) – Exact QnA ID to fetch from the knowledge base, this field takes priority over question.

  • 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”.

  • strict_filters (StrictFilters) – 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.

  • cls (callable) – A custom type or function that will be passed the direct response

Returns

KnowledgeBaseAnswers, or the result of cls(response)

Return type

KnowledgeBaseAnswers

Raises

~azure.core.exceptions.HttpResponseError

query_text(*args: ‘_models.TextQueryOptions’, **kwargs: Any)_models.TextAnswers

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

Parameters

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

Keyword Arguments
  • question (str) – User question to query against the given text records. Provide either text_query_options, OR individual keyword arguments. If both are provided, only the options object will be used.

  • records (list[TextInput]) – Text records to be searched for given question. Provide either text_query_options, OR individual keyword arguments. If both are provided, only the options object will be used.

  • language (str) – Language of the text records. This is BCP-47 representation of a language. For example, use “en” for English; “es” for Spanish etc. If not set, use “en” for English as default.

  • string_index_type (str or StringIndexType) – Specifies the method used to interpret string offsets. Defaults to Text Elements (Graphemes) according to Unicode v8.0.0. For additional information see https://aka.ms/text-analytics-offsets. Possible values include: “TextElements_v8”, “UnicodeCodePoint”, “Utf16CodeUnit”. Default value: “TextElements_v8”.

  • cls (callable) – A custom type or function that will be passed the direct response

Returns

TextAnswers, or the result of cls(response)

Return type

TextAnswers

Raises

~azure.core.exceptions.HttpResponseError

send_request(request: HttpRequest, **kwargs: Any)HttpResponse[source]

Runs the network request through the client’s chained policies. For more information on this code flow, see https://aka.ms/azsdk/python/protocol/quickstart

Parameters

request (HttpRequest) – The network request you want to make. Required.

Keyword Arguments

stream (bool) – Whether the response payload will be streamed. Defaults to False.

Returns

The response of your network call. Does not do error handling on your response.

Return type

HttpResponse