azure.ai.textanalytics.aio package¶

class azure.ai.textanalytics.aio.AsyncAnalyzeActionsLROPoller(client: Any, initial_response: Any, deserialization_callback: Callable, polling_method: azure.core.polling._async_poller.AsyncPollingMethod[PollingReturnType])[source]¶

async cancel() → None [source]¶

Cancel the operation currently being polled.

Returns: None
Return type: None
Raises: HttpResponseError – When the operation has already reached a terminal state.

continuation_token() → str ¶

Return a continuation token that allows to restart the poller later.

Returns: An opaque continuation token
Return type: str

done() → bool ¶

Check status of the long running operation.

Returns: ‘True’ if the process has completed, else ‘False’.
Return type: bool

polling_method() → azure.ai.textanalytics.aio._lro_async.AsyncAnalyzeActionsLROPollingMethod[source]¶

Return the polling method associated to this poller.

Returns: AsyncAnalyzeActionsLROPollingMethod
Return type: AsyncAnalyzeActionsLROPollingMethod

async result() → PollingReturnType¶

Return the result of the long running operation.

Returns: The deserialized resource of the long running operation, if one is available.
Raises: HttpResponseError – Server problem with the query.

status() → str ¶

Returns the current status string.

Returns: The current status string
Return type: str

async wait() → None ¶

Wait on the long running operation.

Raises: HttpResponseError – Server problem with the query.

property details¶

Long-running operation metadata.

Returns: A mapping of details about the long-running operation.
Return type: Mapping[str, Any]

class azure.ai.textanalytics.aio.AsyncAnalyzeHealthcareEntitiesLROPoller(client: Any, initial_response: Any, deserialization_callback: Callable, polling_method: azure.core.polling._async_poller.AsyncPollingMethod[PollingReturnType])[source]¶

async cancel(**kwargs: Any) → azure.core.polling._async_poller.AsyncLROPoller[None][source]¶

Cancel the operation currently being polled.

Keyword Arguments: polling_interval (int) – The polling interval to use to poll the cancellation status. The default value is 5 seconds.
Returns: Returns an instance of an AsyncLROPoller that returns None.
Return type: AsyncLROPoller[None]
Raises: HttpResponseError – When the operation has already reached a terminal state.

Example:

Cancel an existing health operation.¶

import os
from azure.core.exceptions import HttpResponseError
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

documents = [
    "RECORD #333582770390100 | MH | 85986313 | | 054351 | 2/14/2001 12:00:00 AM | \
    CORONARY ARTERY DISEASE | Signed | DIS | Admission Date: 5/22/2001 \
    Report Status: Signed Discharge Date: 4/24/2001 ADMISSION DIAGNOSIS: \
    CORONARY ARTERY DISEASE. HISTORY OF PRESENT ILLNESS: \
    The patient is a 54-year-old gentleman with a history of progressive angina over the past several months. \
    The patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and \
    50% left main disease , with a strong family history of coronary artery disease with a brother dying at \
    the age of 52 from a myocardial infarction and another brother who is status post coronary artery bypass grafting. \
    The patient had a stress echocardiogram done on July , 2001 , which showed no wall motion abnormalities ,\
    but this was a difficult study due to body habitus. The patient went for six minutes with minimal ST depressions \
    in the anterior lateral leads , thought due to fatigue and wrist pain , his anginal equivalent. Due to the patient's \
    increased symptoms and family history and history left main disease with total occasional of his RCA was referred \
    for revascularization with open heart surgery."
]

async with text_analytics_client:
    poller = await text_analytics_client.begin_analyze_healthcare_entities(documents)

    try:
        await poller.cancel()
    except HttpResponseError as e:
        # If the operation has already reached a terminal state it cannot be cancelled.
        print(e)

    else:
        print("Healthcare entities analysis was successfully cancelled.")

continuation_token() → str ¶

Return a continuation token that allows to restart the poller later.

Returns: An opaque continuation token
Return type: str

done() → bool ¶

Check status of the long running operation.

Returns: ‘True’ if the process has completed, else ‘False’.
Return type: bool

polling_method() → azure.ai.textanalytics.aio._lro_async.AsyncAnalyzeHealthcareEntitiesLROPollingMethod[source]¶

Return the polling method associated to this poller.

Returns: AsyncAnalyzeHealthcareEntitiesLROPollingMethod
Return type: AsyncAnalyzeHealthcareEntitiesLROPollingMethod

async result() → PollingReturnType¶

Return the result of the long running operation.

Returns: The deserialized resource of the long running operation, if one is available.
Raises: HttpResponseError – Server problem with the query.

status() → str ¶

Returns the current status string.

Returns: The current status string
Return type: str

async wait() → None ¶

Wait on the long running operation.

Raises: HttpResponseError – Server problem with the query.

property details¶

Long-running operation metadata.

Returns: A mapping of details about the long-running operation.
Return type: Mapping[str, Any]

class azure.ai.textanalytics.aio.AsyncTextAnalysisLROPoller(*args, **kwargs)[source]¶

Implements a protocol which returned poller objects are consistent with.

async cancel() → None [source]¶

Cancel the operation currently being polled.

Returns: None
Return type: None
Raises: HttpResponseError – When the operation has already reached a terminal state.

continuation_token() → str [source]¶

Return a continuation token that allows to restart the poller later.

Returns: An opaque continuation token
Return type: str

done() → bool [source]¶

Check status of the long running operation.

Returns: ‘True’ if the process has completed, else ‘False’.
Return type: bool

async result() → PollingReturnType_co[source]¶

Return the result of the long running operation.

Returns: The deserialized resource of the long running operation, if one is available.
Raises: HttpResponseError – Server problem with the query.

status() → str [source]¶

Returns the current status string.

Returns: The current status string
Return type: str

async wait() → None [source]¶

Wait on the long running operation.

Raises: HttpResponseError – Server problem with the query.

property details¶

Long-running operation metadata.

Returns: A mapping of details about the long-running operation.
Return type: Mapping[str, Any]

class azure.ai.textanalytics.aio.TextAnalyticsClient(endpoint: str, credential: Union[azure.core.credentials.AzureKeyCredential, azure.core.credentials_async.AsyncTokenCredential], *, default_language: Optional[str] = None, default_country_hint: Optional[str] = None, api_version: Optional[Union[str, azure.ai.textanalytics._base_client.TextAnalyticsApiVersion]] = None, **kwargs: Any)[source]¶

The Language service API is a suite of natural language processing (NLP) skills built with the 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, entities recognition, and language detection, and more.

Further documentation can be found in https://docs.microsoft.com/azure/cognitive-services/language-service/overview

Parameters

endpoint (str) – Supported Cognitive Services or Language resource endpoints (protocol and hostname, for example: ‘https://<resource-name>.cognitiveservices.azure.com’).
credential (AzureKeyCredential or AsyncTokenCredential) – Credentials needed for the client to connect to Azure. This can be the an instance of AzureKeyCredential if using a Cognitive Services/Language API key or a token credential from azure.identity.

Keyword Arguments

default_country_hint (str) – Sets the default country_hint to use for all operations. Defaults to “US”. If you don’t want to use a country hint, pass the string “none”.
default_language (str) – Sets the default language to use for all operations. Defaults to “en”.
api_version (str or TextAnalyticsApiVersion) – The API version of the service to use for requests. It defaults to the latest service version. Setting to an older version may result in reduced feature compatibility.

Example:

Creating the TextAnalyticsClient with endpoint and API key.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient
endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(endpoint, AzureKeyCredential(key))

Creating the TextAnalyticsClient with endpoint and token credential from Azure Active Directory.¶

import os
from azure.ai.textanalytics.aio import TextAnalyticsClient
from azure.identity.aio import DefaultAzureCredential

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
credential = DefaultAzureCredential()

text_analytics_client = TextAnalyticsClient(endpoint, credential=credential)

async analyze_sentiment(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, disable_service_logs: Optional[bool] = None, language: Optional[str] = None, model_version: Optional[str] = None, show_opinion_mining: Optional[bool] = None, show_stats: Optional[bool] = None, string_index_type: Optional[str] = None, **kwargs: Any) → List[Union[azure.ai.textanalytics._models.AnalyzeSentimentResult, azure.ai.textanalytics._models.DocumentError]][source]¶

Analyze sentiment for a batch of documents. Turn on opinion mining with show_opinion_mining.

Returns a sentiment prediction, as well as sentiment scores for each sentiment class (Positive, Negative, and Neutral) for the document and each sentence within it.

See https://aka.ms/azsdk/textanalytics/data-limits for service data limits.

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

show_opinion_mining (bool) – Whether to mine the opinions of a sentence and conduct more granular analysis around the aspects of a product or service (also known as aspect-based sentiment analysis). If set to true, the returned SentenceSentiment objects will have property mined_opinions containing the result of this analysis. Only available for API version v3.1 and up.
language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics in the statistics field of the document-level response.
string_index_type (str) – Specifies the method used to interpret string offsets. UnicodeCodePoint, the Python encoding, is the default. To override the Python default, you can also pass in Utf16CodeUnit or TextElement_v8. For additional information see https://aka.ms/text-analytics-offsets
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

The combined list of AnalyzeSentimentResult and DocumentError in the order the original documents were passed in.

Return type

list[AnalyzeSentimentResult or DocumentError]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The show_opinion_mining, disable_service_logs, and string_index_type keyword arguments.

Example:

Analyze sentiment in a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))

documents = [
    """I had the best day of my life. I decided to go sky-diving and it made me appreciate my whole life so much more.
    I developed a deep-connection with my instructor as well, and I feel as if I've made a life-long friend in her.""",
    """This was a waste of my time. All of the views on this drop are extremely boring, all I saw was grass. 0/10 would
    not recommend to any divers, even first timers.""",
    """This was pretty good! The sights were ok, and I had fun with my instructors! Can't complain too much about my experience""",
    """I only have one word for my experience: WOW!!! I can't believe I have had such a wonderful skydiving company right
    in my backyard this whole time! I will definitely be a repeat customer, and I want to take my grandmother skydiving too,
    I know she'll love it!"""
]

async with text_analytics_client:
    result = await text_analytics_client.analyze_sentiment(documents)

docs = [doc for doc in result if not doc.is_error]

print("Let's visualize the sentiment of each of these documents")
for idx, doc in enumerate(docs):
    print(f"Document text: {documents[idx]}")
    print(f"Overall sentiment: {doc.sentiment}")

async begin_abstract_summary(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, continuation_token: Optional[str] = None, disable_service_logs: Optional[bool] = None, display_name: Optional[str] = None, language: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, model_version: Optional[str] = None, string_index_type: Optional[str] = None, sentence_count: Optional[int] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncTextAnalysisLROPoller[azure.core.async_paging.AsyncItemPaged[Union[azure.ai.textanalytics._models.AbstractiveSummaryResult, azure.ai.textanalytics._models.DocumentError]]][source]¶

Start a long-running abstractive summarization operation.

For a conceptual discussion of abstractive summarization, see the service documentation: https://learn.microsoft.com/azure/cognitive-services/language-service/summarization/overview

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
show_stats (bool) – If set to true, response will contain document level statistics.
sentence_count (Optional[int]) – It controls the approximate number of sentences in the output summaries.
model_version (Optional[str]) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
string_index_type (Optional[str]) – Specifies the method used to interpret string offsets.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.
display_name (str) – An optional display name to set for the requested analysis.

Returns

An instance of an AsyncTextAnalysisLROPoller. Call result() on the this object to return a heterogeneous pageable of AbstractiveSummaryResult and DocumentError.

Return type

AsyncTextAnalysisLROPoller[AsyncItemPaged[ AbstractiveSummaryResult or DocumentError]]

Raises

HttpResponseError –

New in version 2023-04-01: The begin_abstract_summary client method.

Example:

Perform abstractive summarization on a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

document = [
    "At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, "
    "human-centric approach to learning and understanding. As Chief Technology Officer of Azure AI Cognitive "
    "Services, I have been working with a team of amazing scientists and engineers to turn this quest into a "
    "reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of "
    "human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the "
    "intersection of all three, there's magic-what we call XYZ-code as illustrated in Figure 1-a joint "
    "representation to create more powerful AI that can speak, hear, see, and understand humans better. "
    "We believe XYZ-code will enable us to fulfill our long-term vision: cross-domain transfer learning, "
    "spanning modalities and languages. The goal is to have pretrained models that can jointly learn "
    "representations to support a broad range of downstream AI tasks, much in the way humans do today. "
    "Over the past five years, we have achieved human performance on benchmarks in conversational speech "
    "recognition, machine translation, conversational question answering, machine reading comprehension, "
    "and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious "
    "aspiration to produce a leap in AI capabilities, achieving multisensory and multilingual learning that "
    "is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational "
    "component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
]
async with text_analytics_client:
    poller = await text_analytics_client.begin_abstract_summary(document)
    abstract_summary_results = await poller.result()
    async for result in abstract_summary_results:
        if result.kind == "AbstractiveSummarization":
            print("Summaries abstracted:")
            [print(f"{summary.text}\n") for summary in result.summaries]
        elif result.is_error is True:
            print("...Is an error with code '{}' and message '{}'".format(
                result.error.code, result.error.message
            ))

async begin_analyze_actions(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], actions: List[Union[azure.ai.textanalytics._models.RecognizeEntitiesAction, azure.ai.textanalytics._models.RecognizeLinkedEntitiesAction, azure.ai.textanalytics._models.RecognizePiiEntitiesAction, azure.ai.textanalytics._models.ExtractKeyPhrasesAction, azure.ai.textanalytics._models.AnalyzeSentimentAction, azure.ai.textanalytics._models.RecognizeCustomEntitiesAction, azure.ai.textanalytics._models.SingleLabelClassifyAction, azure.ai.textanalytics._models.MultiLabelClassifyAction, azure.ai.textanalytics._models.AnalyzeHealthcareEntitiesAction, azure.ai.textanalytics._models.ExtractiveSummaryAction, azure.ai.textanalytics._models.AbstractiveSummaryAction]], *, continuation_token: Optional[str] = None, display_name: Optional[str] = None, language: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncTextAnalysisLROPoller[azure.core.async_paging.AsyncItemPaged[List[Union[azure.ai.textanalytics._models.RecognizeEntitiesResult, azure.ai.textanalytics._models.RecognizeLinkedEntitiesResult, azure.ai.textanalytics._models.RecognizePiiEntitiesResult, azure.ai.textanalytics._models.ExtractKeyPhrasesResult, azure.ai.textanalytics._models.AnalyzeSentimentResult, azure.ai.textanalytics._models.RecognizeCustomEntitiesResult, azure.ai.textanalytics._models.ClassifyDocumentResult, azure.ai.textanalytics._models.AnalyzeHealthcareEntitiesResult, azure.ai.textanalytics._models.ExtractiveSummaryResult, azure.ai.textanalytics._models.AbstractiveSummaryResult, azure.ai.textanalytics._models.DocumentError]]]][source]¶

Start a long-running operation to perform a variety of text analysis actions over a batch of documents.

We recommend you use this function if you’re looking to analyze larger documents, and / or combine multiple text analysis actions into one call. Otherwise, we recommend you use the action specific endpoints, for example analyze_sentiment().

Note

See the service documentation for regional support of custom action features: https://aka.ms/azsdk/textanalytics/customfunctionalities

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.
actions (list[RecognizeEntitiesAction or RecognizePiiEntitiesAction or ExtractKeyPhrasesAction or RecognizeLinkedEntitiesAction or AnalyzeSentimentAction or RecognizeCustomEntitiesAction or SingleLabelClassifyAction or MultiLabelClassifyAction or AnalyzeHealthcareEntitiesAction or AbstractiveSummaryAction or ExtractiveSummaryAction]) – A heterogeneous list of actions to perform on the input documents. Each action object encapsulates the parameters used for the particular action type. The action results will be in the same order of the input actions.

Keyword Arguments

display_name (str) – An optional display name to set for the requested analysis.
language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
show_stats (bool) – If set to true, response will contain document level statistics.
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.

Returns

An instance of an AsyncTextAnalysisLROPoller. Call result() on the poller object to return a pageable heterogeneous list of lists. This list of lists is first ordered by the documents you input, then ordered by the actions you input. For example, if you have documents input [“Hello”, “world”], and actions RecognizeEntitiesAction and AnalyzeSentimentAction, when iterating over the list of lists, you will first iterate over the action results for the “Hello” document, getting the RecognizeEntitiesResult of “Hello”, then the AnalyzeSentimentResult of “Hello”. Then, you will get the RecognizeEntitiesResult and AnalyzeSentimentResult of “world”.

Return type

AsyncTextAnalysisLROPoller[AsyncItemPaged[ list[RecognizeEntitiesResult or RecognizeLinkedEntitiesResult or RecognizePiiEntitiesResult or ExtractKeyPhrasesResult or AnalyzeSentimentResult or RecognizeCustomEntitiesResult or ClassifyDocumentResult or AnalyzeHealthcareEntitiesResult or ExtractiveSummaryResult or AbstractiveSummaryResult or DocumentError]]]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The begin_analyze_actions client method.

New in version 2022-05-01: The RecognizeCustomEntitiesAction, SingleLabelClassifyAction, MultiLabelClassifyAction, and AnalyzeHealthcareEntitiesAction input options and the corresponding RecognizeCustomEntitiesResult, ClassifyDocumentResult, and AnalyzeHealthcareEntitiesResult result objects

New in version 2023-04-01: The ExtractiveSummaryAction and AbstractiveSummaryAction input options and the corresponding ExtractiveSummaryResult and AbstractiveSummaryResult result objects.

Example:

Start a long-running operation to perform a variety of text analysis actions over a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient
from azure.ai.textanalytics import (
    RecognizeEntitiesAction,
    RecognizeLinkedEntitiesAction,
    RecognizePiiEntitiesAction,
    ExtractKeyPhrasesAction,
    AnalyzeSentimentAction,
)

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

documents = [
    'We went to Contoso Steakhouse located at midtown NYC last week for a dinner party, and we adore the spot! '
    'They provide marvelous food and they have a great menu. The chief cook happens to be the owner (I think his name is John Doe) '
    'and he is super nice, coming out of the kitchen and greeted us all.'
    ,

    'We enjoyed very much dining in the place! '
    'The Sirloin steak I ordered was tender and juicy, and the place was impeccably clean. You can even pre-order from their '
    'online menu at www.contososteakhouse.com, call 312-555-0176 or send email to order@contososteakhouse.com! '
    'The only complaint I have is the food didn\'t come fast enough. Overall I highly recommend it!'
]

async with text_analytics_client:
    poller = await text_analytics_client.begin_analyze_actions(
        documents,
        display_name="Sample Text Analysis",
        actions=[
            RecognizeEntitiesAction(),
            RecognizePiiEntitiesAction(),
            ExtractKeyPhrasesAction(),
            RecognizeLinkedEntitiesAction(),
            AnalyzeSentimentAction(),
        ]
    )

    pages = await poller.result()

    # To enumerate / zip for async, unless you install a third party library,
    # you have to read in all of the elements into memory first.
    # If you're not looking to enumerate / zip, we recommend you just asynchronously
    # loop over it immediately, without going through this step of reading them into memory
    document_results = []
    async for page in pages:
        document_results.append(page)

for doc, action_results in zip(documents, document_results):
    print(f"\nDocument text: {doc}")
    for result in action_results:
        if result.kind == "EntityRecognition":
            print("...Results of Recognize Entities Action:")
            for entity in result.entities:
                print(f"......Entity: {entity.text}")
                print(f".........Category: {entity.category}")
                print(f".........Confidence Score: {entity.confidence_score}")
                print(f".........Offset: {entity.offset}")

        elif result.kind == "PiiEntityRecognition":
            print("...Results of Recognize PII Entities action:")
            for pii_entity in result.entities:
                print(f"......Entity: {pii_entity.text}")
                print(f".........Category: {pii_entity.category}")
                print(f".........Confidence Score: {pii_entity.confidence_score}")

        elif result.kind == "KeyPhraseExtraction":
            print("...Results of Extract Key Phrases action:")
            print(f"......Key Phrases: {result.key_phrases}")

        elif result.kind == "EntityLinking":
            print("...Results of Recognize Linked Entities action:")
            for linked_entity in result.entities:
                print(f"......Entity name: {linked_entity.name}")
                print(f".........Data source: {linked_entity.data_source}")
                print(f".........Data source language: {linked_entity.language}")
                print(
                    f".........Data source entity ID: {linked_entity.data_source_entity_id}"
                )
                print(f".........Data source URL: {linked_entity.url}")
                print(".........Document matches:")
                for match in linked_entity.matches:
                    print(f"............Match text: {match.text}")
                    print(f"............Confidence Score: {match.confidence_score}")
                    print(f"............Offset: {match.offset}")
                    print(f"............Length: {match.length}")

        elif result.kind == "SentimentAnalysis":
            print("...Results of Analyze Sentiment action:")
            print(f"......Overall sentiment: {result.sentiment}")
            print(
                f"......Scores: positive={result.confidence_scores.positive}; \
                neutral={result.confidence_scores.neutral}; \
                negative={result.confidence_scores.negative} \n"
            )

        elif result.is_error is True:
            print(
                f"...Is an error with code '{result.error.code}' and message '{result.error.message}'"
            )

    print("------------------------------------------")

async begin_analyze_healthcare_entities(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, continuation_token: Optional[str] = None, disable_service_logs: Optional[bool] = None, display_name: Optional[str] = None, language: Optional[str] = None, model_version: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, string_index_type: Optional[str] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncAnalyzeHealthcareEntitiesLROPoller[azure.core.async_paging.AsyncItemPaged[Union[azure.ai.textanalytics._models.AnalyzeHealthcareEntitiesResult, azure.ai.textanalytics._models.DocumentError]]][source]¶

Analyze healthcare entities and identify relationships between these entities in a batch of documents.

Entities are associated with references that can be found in existing knowledge bases, such as UMLS, CHV, MSH, etc.

We also extract the relations found between entities, for example in “The subject took 100 mg of ibuprofen”, we would extract the relationship between the “100 mg” dosage and the “ibuprofen” medication.

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics.
language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
display_name (str) – An optional display name to set for the requested analysis.
string_index_type (str) – Specifies the method used to interpret string offsets. Can be one of ‘UnicodeCodePoint’ (default), ‘Utf16CodeUnit’, or ‘TextElement_v8’. For additional information see https://aka.ms/text-analytics-offsets
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.
disable_service_logs (bool) – Defaults to true, meaning that the Language service will not log your input text on the service side for troubleshooting. If set to False, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the Text Analytics natural language processing functions. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

An instance of an AsyncAnalyzeHealthcareEntitiesLROPoller. Call result() on the poller object to return a heterogeneous pageable of AnalyzeHealthcareEntitiesResult and DocumentError.

Return type

AsyncAnalyzeHealthcareEntitiesLROPoller[AsyncItemPaged[ AnalyzeHealthcareEntitiesResult or DocumentError]]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The begin_analyze_healthcare_entities client method.

New in version 2022-05-01: The display_name keyword argument.

Example:

Analyze healthcare entities in a batch of documents.¶

import os
import typing
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import HealthcareEntityRelation
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

documents = [
    """
    Patient needs to take 100 mg of ibuprofen, and 3 mg of potassium. Also needs to take
    10 mg of Zocor.
    """,
    """
    Patient needs to take 50 mg of ibuprofen, and 2 mg of Coumadin.
    """
]

async with text_analytics_client:
    poller = await text_analytics_client.begin_analyze_healthcare_entities(documents)
    result = await poller.result()
    docs = [doc async for doc in result if not doc.is_error]

print("Let's first visualize the outputted healthcare result:")
for doc in docs:
    for entity in doc.entities:
        print(f"Entity: {entity.text}")
        print(f"...Normalized Text: {entity.normalized_text}")
        print(f"...Category: {entity.category}")
        print(f"...Subcategory: {entity.subcategory}")
        print(f"...Offset: {entity.offset}")
        print(f"...Confidence score: {entity.confidence_score}")
        if entity.data_sources is not None:
            print("...Data Sources:")
            for data_source in entity.data_sources:
                print(f"......Entity ID: {data_source.entity_id}")
                print(f"......Name: {data_source.name}")
        if entity.assertion is not None:
            print("...Assertion:")
            print(f"......Conditionality: {entity.assertion.conditionality}")
            print(f"......Certainty: {entity.assertion.certainty}")
            print(f"......Association: {entity.assertion.association}")
    for relation in doc.entity_relations:
        print(f"Relation of type: {relation.relation_type} has the following roles")
        for role in relation.roles:
            print(f"...Role '{role.name}' with entity '{role.entity.text}'")
    print("------------------------------------------")

print("Now, let's get all of medication dosage relations from the documents")
dosage_of_medication_relations = [
    entity_relation
    for doc in docs
    for entity_relation in doc.entity_relations if entity_relation.relation_type == HealthcareEntityRelation.DOSAGE_OF_MEDICATION
]

async begin_extract_summary(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, continuation_token: Optional[str] = None, disable_service_logs: Optional[bool] = None, display_name: Optional[str] = None, language: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, model_version: Optional[str] = None, string_index_type: Optional[str] = None, max_sentence_count: Optional[int] = None, order_by: Optional[typing_extensions.Literal[Rank, Offset]] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncTextAnalysisLROPoller[azure.core.async_paging.AsyncItemPaged[Union[azure.ai.textanalytics._models.ExtractiveSummaryResult, azure.ai.textanalytics._models.DocumentError]]][source]¶

Start a long-running extractive summarization operation.

For a conceptual discussion of extractive summarization, see the service documentation: https://learn.microsoft.com/azure/cognitive-services/language-service/summarization/overview

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
show_stats (bool) – If set to true, response will contain document level statistics.
max_sentence_count (Optional[int]) – Maximum number of sentences to return. Defaults to 3.
order_by (Optional[str]) – Possible values include: “Offset”, “Rank”. Default value: “Offset”.
model_version (Optional[str]) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
string_index_type (Optional[str]) – Specifies the method used to interpret string offsets.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.
display_name (str) – An optional display name to set for the requested analysis.

Returns

An instance of an AsyncTextAnalysisLROPoller. Call result() on the this object to return a heterogeneous pageable of ExtractiveSummaryResult and DocumentError.

Return type

AsyncTextAnalysisLROPoller[AsyncItemPaged[ ExtractiveSummaryResult or DocumentError]]

Raises

HttpResponseError –

New in version 2023-04-01: The begin_extract_summary client method.

Example:

Perform extractive summarization on a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

document = [
    "At Microsoft, we have been on a quest to advance AI beyond existing techniques, by taking a more holistic, "
    "human-centric approach to learning and understanding. As Chief Technology Officer of Azure AI Cognitive "
    "Services, I have been working with a team of amazing scientists and engineers to turn this quest into a "
    "reality. In my role, I enjoy a unique perspective in viewing the relationship among three attributes of "
    "human cognition: monolingual text (X), audio or visual sensory signals, (Y) and multilingual (Z). At the "
    "intersection of all three, there's magic-what we call XYZ-code as illustrated in Figure 1-a joint "
    "representation to create more powerful AI that can speak, hear, see, and understand humans better. "
    "We believe XYZ-code will enable us to fulfill our long-term vision: cross-domain transfer learning, "
    "spanning modalities and languages. The goal is to have pretrained models that can jointly learn "
    "representations to support a broad range of downstream AI tasks, much in the way humans do today. "
    "Over the past five years, we have achieved human performance on benchmarks in conversational speech "
    "recognition, machine translation, conversational question answering, machine reading comprehension, "
    "and image captioning. These five breakthroughs provided us with strong signals toward our more ambitious "
    "aspiration to produce a leap in AI capabilities, achieving multisensory and multilingual learning that "
    "is closer in line with how humans learn and understand. I believe the joint XYZ-code is a foundational "
    "component of this aspiration, if grounded with external knowledge sources in the downstream AI tasks."
]

async with text_analytics_client:
    poller = await text_analytics_client.begin_extract_summary(document)
    extract_summary_results = await poller.result()
    async for result in extract_summary_results:
        if result.kind == "ExtractiveSummarization":
            print("Summary extracted: \n{}".format(
                " ".join([sentence.text for sentence in result.sentences]))
            )
        elif result.is_error is True:
            print("...Is an error with code '{}' and message '{}'".format(
                result.error.code, result.error.message
            ))

async begin_multi_label_classify(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], project_name: str, deployment_name: str, *, continuation_token: Optional[str] = None, disable_service_logs: Optional[bool] = None, display_name: Optional[str] = None, language: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncTextAnalysisLROPoller[azure.core.async_paging.AsyncItemPaged[Union[azure.ai.textanalytics._models.ClassifyDocumentResult, azure.ai.textanalytics._models.DocumentError]]][source]¶

Start a long-running custom multi label classification operation.

For information on regional support of custom features and how to train a model to classify your documents, see https://aka.ms/azsdk/textanalytics/customfunctionalities

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.
project_name (str) – Required. This field indicates the project name for the model.
deployment_name (str) – This field indicates the deployment name for the model.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
show_stats (bool) – If set to true, response will contain document level statistics.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.
display_name (str) – An optional display name to set for the requested analysis.

Returns

An instance of an AsyncTextAnalysisLROPoller. Call result() on the this object to return a heterogeneous pageable of ClassifyDocumentResult and DocumentError.

Return type

AsyncTextAnalysisLROPoller[AsyncItemPaged[ ClassifyDocumentResult or DocumentError]]

Raises

HttpResponseError –

New in version 2022-05-01: The begin_multi_label_classify client method.

Example:

Perform multi label classification on a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]
project_name = os.environ["MULTI_LABEL_CLASSIFY_PROJECT_NAME"]
deployment_name = os.environ["MULTI_LABEL_CLASSIFY_DEPLOYMENT_NAME"]
path_to_sample_document = os.path.abspath(
    os.path.join(
        os.path.abspath(__file__),
        "..",
        "..",
        "./text_samples/custom_classify_sample.txt",
    )
)

with open(path_to_sample_document) as fd:
    document = [fd.read()]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

async with text_analytics_client:
    poller = await text_analytics_client.begin_multi_label_classify(
        document,
        project_name=project_name,
        deployment_name=deployment_name
    )

    pages = await poller.result()
    document_results = []
    async for page in pages:
        document_results.append(page)

for doc, classification_result in zip(document, document_results):
    if classification_result.kind == "CustomDocumentClassification":
        classifications = classification_result.classifications
        print(f"\nThe movie plot '{doc}' was classified as the following genres:\n")
        for classification in classifications:
            print("'{}' with confidence score {}.".format(
                classification.category, classification.confidence_score
            ))
    elif classification_result.is_error is True:
        print("Movie plot '{}' has an error with code '{}' and message '{}'".format(
            doc, classification_result.error.code, classification_result.error.message
        ))

async begin_recognize_custom_entities(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], project_name: str, deployment_name: str, *, continuation_token: Optional[str] = None, disable_service_logs: Optional[bool] = None, display_name: Optional[str] = None, language: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, string_index_type: Optional[str] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncTextAnalysisLROPoller[azure.core.async_paging.AsyncItemPaged[Union[azure.ai.textanalytics._models.RecognizeCustomEntitiesResult, azure.ai.textanalytics._models.DocumentError]]][source]¶

Start a long-running custom named entity recognition operation.

For information on regional support of custom features and how to train a model to recognize custom entities, see https://aka.ms/azsdk/textanalytics/customentityrecognition

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.
project_name (str) – Required. This field indicates the project name for the model.
deployment_name (str) – This field indicates the deployment name for the model.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
show_stats (bool) – If set to true, response will contain document level statistics.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.
string_index_type (str) – Specifies the method used to interpret string offsets. UnicodeCodePoint, the Python encoding, is the default. To override the Python default, you can also pass in Utf16CodeUnit or TextElement_v8. For additional information see https://aka.ms/text-analytics-offsets
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.
display_name (str) – An optional display name to set for the requested analysis.

Returns

An instance of an AsyncTextAnalysisLROPoller. Call result() on the this object to return a heterogeneous pageable of RecognizeCustomEntitiesResult and DocumentError.

Return type

AsyncTextAnalysisLROPoller[AsyncItemPaged[ RecognizeCustomEntitiesResult or DocumentError]]

Raises

HttpResponseError –

New in version 2022-05-01: The begin_recognize_custom_entities client method.

Example:

Recognize custom entities in a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]
project_name = os.environ["CUSTOM_ENTITIES_PROJECT_NAME"]
deployment_name = os.environ["CUSTOM_ENTITIES_DEPLOYMENT_NAME"]
path_to_sample_document = os.path.abspath(
    os.path.join(
        os.path.abspath(__file__),
        "..",
        "..",
        "./text_samples/custom_entities_sample.txt",
    )
)

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

with open(path_to_sample_document) as fd:
    document = [fd.read()]

async with text_analytics_client:
    poller = await text_analytics_client.begin_recognize_custom_entities(
        document,
        project_name=project_name,
        deployment_name=deployment_name
    )

    document_results = await poller.result()

    async for custom_entities_result in document_results:
        if custom_entities_result.kind == "CustomEntityRecognition":
            for entity in custom_entities_result.entities:
                print(
                    "Entity '{}' has category '{}' with confidence score of '{}'".format(
                        entity.text, entity.category, entity.confidence_score
                    )
                )
        elif custom_entities_result.is_error is True:
            print("...Is an error with code '{}' and message '{}'".format(
                custom_entities_result.error.code, custom_entities_result.error.message
                )
            )

async begin_single_label_classify(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], project_name: str, deployment_name: str, *, continuation_token: Optional[str] = None, disable_service_logs: Optional[bool] = None, display_name: Optional[str] = None, language: Optional[str] = None, polling_interval: Optional[int] = None, show_stats: Optional[bool] = None, **kwargs: Any) → azure.ai.textanalytics.aio._lro_async.AsyncTextAnalysisLROPoller[azure.core.async_paging.AsyncItemPaged[Union[azure.ai.textanalytics._models.ClassifyDocumentResult, azure.ai.textanalytics._models.DocumentError]]][source]¶

Start a long-running custom single label classification operation.

For information on regional support of custom features and how to train a model to classify your documents, see https://aka.ms/azsdk/textanalytics/customfunctionalities

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.
project_name (str) – Required. This field indicates the project name for the model.
deployment_name (str) – This field indicates the deployment name for the model.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
show_stats (bool) – If set to true, response will contain document level statistics.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.
polling_interval (int) – Waiting time between two polls for LRO operations if no Retry-After header is present. Defaults to 5 seconds.
continuation_token (str) – Call continuation_token() on the poller object to save the long-running operation (LRO) state into an opaque token. Pass the value as the continuation_token keyword argument to restart the LRO from a saved state.
display_name (str) – An optional display name to set for the requested analysis.

Returns

An instance of an AsyncTextAnalysisLROPoller. Call result() on the this object to return a heterogeneous pageable of ClassifyDocumentResult and DocumentError.

Return type

AsyncTextAnalysisLROPoller[AsyncItemPaged[ ClassifyDocumentResult or DocumentError]]

Raises

HttpResponseError –

New in version 2022-05-01: The begin_single_label_classify client method.

Example:

Perform single label classification on a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]
project_name = os.environ["SINGLE_LABEL_CLASSIFY_PROJECT_NAME"]
deployment_name = os.environ["SINGLE_LABEL_CLASSIFY_DEPLOYMENT_NAME"]
path_to_sample_document = os.path.abspath(
    os.path.join(
        os.path.abspath(__file__),
        "..",
        "..",
        "./text_samples/custom_classify_sample.txt",
    )
)

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key),
)

with open(path_to_sample_document) as fd:
    document = [fd.read()]

async with text_analytics_client:
    poller = await text_analytics_client.begin_single_label_classify(
        document,
        project_name=project_name,
        deployment_name=deployment_name
    )

    pages = await poller.result()

    document_results = []
    async for page in pages:
        document_results.append(page)

for doc, classification_result in zip(document, document_results):
    if classification_result.kind == "CustomDocumentClassification":
        classification = classification_result.classifications[0]
        print("The document text '{}' was classified as '{}' with confidence score {}.".format(
            doc, classification.category, classification.confidence_score)
        )
    elif classification_result.is_error is True:
        print("Document text '{}' has an error with code '{}' and message '{}'".format(
            doc, classification_result.error.code, classification_result.error.message
        ))

async close() → None ¶: Close sockets opened by the client. Calling this method is unnecessary when using the client as a context manager.

async detect_language(documents: Union[List[str], List[azure.ai.textanalytics._models.DetectLanguageInput], List[Dict[str, str]]], *, country_hint: Optional[str] = None, disable_service_logs: Optional[bool] = None, model_version: Optional[str] = None, show_stats: Optional[bool] = None, **kwargs: Any) → List[Union[azure.ai.textanalytics._models.DetectLanguageResult, azure.ai.textanalytics._models.DocumentError]][source]¶

Detect language for a batch of documents.

Returns the detected language and a numeric score between zero and one. Scores close to one indicate 100% certainty that the identified language is true. See https://aka.ms/talangs for the list of enabled languages.

See https://aka.ms/azsdk/textanalytics/data-limits for service data limits.

Parameters

documents (list[str] or list[DetectLanguageInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and country_hint on a per-item basis you must use as input a list[DetectLanguageInput] or a list of dict representations of DetectLanguageInput, like {“id”: “1”, “country_hint”: “us”, “text”: “hello world”}.

Keyword Arguments

country_hint (str) – Country of origin hint for the entire batch. Accepts two letter country codes specified by ISO 3166-1 alpha-2. Per-document country hints will take precedence over whole batch hints. Defaults to “US”. If you don’t want to use a country hint, pass the string “none”.
model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics in the statistics field of the document-level response.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

The combined list of DetectLanguageResult and DocumentError in the order the original documents were passed in.

Return type

list[DetectLanguageResult or DocumentError]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The disable_service_logs keyword argument.

Example:

Detecting language in a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))
documents = [
    """
    The concierge Paulette was extremely helpful. Sadly when we arrived the elevator was broken, but with Paulette's help we barely noticed this inconvenience.
    She arranged for our baggage to be brought up to our room with no extra charge and gave us a free meal to refurbish all of the calories we lost from
    walking up the stairs :). Can't say enough good things about my experience!
    """,
    """
    最近由于工作压力太大，我们决定去富酒店度假。那儿的温泉实在太舒服了，我跟我丈夫都完全恢复了工作前的青春精神！加油！
    """
]
async with text_analytics_client:
    result = await text_analytics_client.detect_language(documents)

reviewed_docs = [doc for doc in result if not doc.is_error]

print("Let's see what language each review is in!")

for idx, doc in enumerate(reviewed_docs):
    print("Review #{} is in '{}', which has ISO639-1 name '{}'\n".format(
        idx, doc.primary_language.name, doc.primary_language.iso6391_name
    ))

async extract_key_phrases(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, disable_service_logs: Optional[bool] = None, language: Optional[str] = None, model_version: Optional[str] = None, show_stats: Optional[bool] = None, **kwargs: Any) → List[Union[azure.ai.textanalytics._models.ExtractKeyPhrasesResult, azure.ai.textanalytics._models.DocumentError]][source]¶

Extract key phrases from a batch of documents.

Returns a list of strings denoting the key phrases in the input text. For example, for the input text “The food was delicious and there were wonderful staff”, the API returns the main talking points: “food” and “wonderful staff”

See https://aka.ms/azsdk/textanalytics/data-limits for service data limits.

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics in the statistics field of the document-level response.
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

The combined list of ExtractKeyPhrasesResult and DocumentError in the order the original documents were passed in.

Return type

list[ExtractKeyPhrasesResult or DocumentError]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The disable_service_logs keyword argument.

Example:

Extract the key phrases in a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))
articles = [
    """
    Washington, D.C. Autumn in DC is a uniquely beautiful season. The leaves fall from the trees
    in a city chock-full of forests, leaving yellow leaves on the ground and a clearer view of the
    blue sky above...
    """,
    """
    Redmond, WA. In the past few days, Microsoft has decided to further postpone the start date of
    its United States workers, due to the pandemic that rages with no end in sight...
    """,
    """
    Redmond, WA. Employees at Microsoft can be excited about the new coffee shop that will open on campus
    once workers no longer have to work remotely...
    """
]

async with text_analytics_client:
    result = await text_analytics_client.extract_key_phrases(articles)

articles_that_mention_microsoft = []
for idx, doc in enumerate(result):
    if not doc.is_error:
        print("Key phrases in article #{}: {}".format(
            idx + 1,
            ", ".join(doc.key_phrases)
        ))

async recognize_entities(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, disable_service_logs: Optional[bool] = None, language: Optional[str] = None, model_version: Optional[str] = None, show_stats: Optional[bool] = None, string_index_type: Optional[str] = None, **kwargs: Any) → List[Union[azure.ai.textanalytics._models.RecognizeEntitiesResult, azure.ai.textanalytics._models.DocumentError]][source]¶

Recognize entities for a batch of documents.

Identifies and categorizes entities in your text as people, places, organizations, date/time, quantities, percentages, currencies, and more. For the list of supported entity types, check: https://aka.ms/taner

See https://aka.ms/azsdk/textanalytics/data-limits for service data limits.

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics in the statistics field of the document-level response.
string_index_type (str) – Specifies the method used to interpret string offsets. UnicodeCodePoint, the Python encoding, is the default. To override the Python default, you can also pass in Utf16CodeUnit or TextElement_v8. For additional information see https://aka.ms/text-analytics-offsets
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

The combined list of RecognizeEntitiesResult and DocumentError in the order the original documents were passed in.

Return type

list[RecognizeEntitiesResult or DocumentError]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The disable_service_logs and string_index_type keyword arguments.

Example:

Recognize entities in a batch of documents.¶

import os
import typing
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))
reviews = [
    """I work for Foo Company, and we hired Contoso for our annual founding ceremony. The food
    was amazing and we all can't say enough good words about the quality and the level of service.""",
    """We at the Foo Company re-hired Contoso after all of our past successes with the company.
    Though the food was still great, I feel there has been a quality drop since their last time
    catering for us. Is anyone else running into the same problem?""",
    """Bar Company is over the moon about the service we received from Contoso, the best sliders ever!!!!"""
]

async with text_analytics_client:
    result = await text_analytics_client.recognize_entities(reviews)

result = [review for review in result if not review.is_error]
organization_to_reviews: typing.Dict[str, typing.List[str]] = {}

for idx, review in enumerate(result):
    for entity in review.entities:
        print(f"Entity '{entity.text}' has category '{entity.category}'")

        if entity.category == 'Organization':
            organization_to_reviews.setdefault(entity.text, [])
            organization_to_reviews[entity.text].append(reviews[idx])

for organization, reviews in organization_to_reviews.items():
    print(
        "\n\nOrganization '{}' has left us the following review(s): {}".format(
            organization, "\n\n".join(reviews)
        )
    )

async recognize_linked_entities(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, disable_service_logs: Optional[bool] = None, language: Optional[str] = None, model_version: Optional[str] = None, show_stats: Optional[bool] = None, string_index_type: Optional[str] = None, **kwargs: Any) → List[Union[azure.ai.textanalytics._models.RecognizeLinkedEntitiesResult, azure.ai.textanalytics._models.DocumentError]][source]¶

Recognize linked entities from a well-known knowledge base for a batch of documents.

Identifies and disambiguates the identity of each entity found in text (for example, determining whether an occurrence of the word Mars refers to the planet, or to the Roman god of war). Recognized entities are associated with URLs to a well-known knowledge base, like Wikipedia.

See https://aka.ms/azsdk/textanalytics/data-limits for service data limits.

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics in the statistics field of the document-level response.
string_index_type (str) – Specifies the method used to interpret string offsets. UnicodeCodePoint, the Python encoding, is the default. To override the Python default, you can also pass in Utf16CodeUnit or TextElement_v8. For additional information see https://aka.ms/text-analytics-offsets
disable_service_logs (bool) – If set to true, you opt-out of having your text input logged on the service side for troubleshooting. By default, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Setting this parameter to true, disables input logging and may limit our ability to remediate issues that occur. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

The combined list of RecognizeLinkedEntitiesResult and DocumentError in the order the original documents were passed in.

Return type

list[RecognizeLinkedEntitiesResult or DocumentError]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The disable_service_logs and string_index_type keyword arguments.

Example:

Recognize linked entities in a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics.aio import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=AzureKeyCredential(key))
documents = [
    """
    Microsoft was founded by Bill Gates with some friends he met at Harvard. One of his friends,
    Steve Ballmer, eventually became CEO after Bill Gates as well. Steve Ballmer eventually stepped
    down as CEO of Microsoft, and was succeeded by Satya Nadella.
    Microsoft originally moved its headquarters to Bellevue, Washington in January 1979, but is now
    headquartered in Redmond.
    """
]

async with text_analytics_client:
    result = await text_analytics_client.recognize_linked_entities(documents)

docs = [doc for doc in result if not doc.is_error]

print(
    "Let's map each entity to it's Wikipedia article. I also want to see how many times each "
    "entity is mentioned in a document\n\n"
)
entity_to_url = {}
for doc in docs:
    for entity in doc.entities:
        print("Entity '{}' has been mentioned '{}' time(s)".format(
            entity.name, len(entity.matches)
        ))
        if entity.data_source == "Wikipedia":
            entity_to_url[entity.name] = entity.url

async recognize_pii_entities(documents: Union[List[str], List[azure.ai.textanalytics._models.TextDocumentInput], List[Dict[str, str]]], *, categories_filter: Optional[List[Union[str, azure.ai.textanalytics._generated.v2023_04_01.models._text_analytics_client_enums.PiiEntityCategory]]] = None, disable_service_logs: Optional[bool] = None, domain_filter: Optional[Union[str, azure.ai.textanalytics._models.PiiEntityDomain]] = None, language: Optional[str] = None, model_version: Optional[str] = None, show_stats: Optional[bool] = None, string_index_type: Optional[str] = None, **kwargs: Any) → List[Union[azure.ai.textanalytics._models.RecognizePiiEntitiesResult, azure.ai.textanalytics._models.DocumentError]][source]¶

Recognize entities containing personal information for a batch of documents.

Returns a list of personal information entities (“SSN”, “Bank Account”, etc) in the document. For the list of supported entity types, check https://aka.ms/azsdk/language/pii

See https://aka.ms/azsdk/textanalytics/data-limits for service data limits.

Parameters

documents (list[str] or list[TextDocumentInput] or list[dict[str, str]]) – The set of documents to process as part of this batch. If you wish to specify the ID and language on a per-item basis you must use as input a list[TextDocumentInput] or a list of dict representations of TextDocumentInput, like {“id”: “1”, “language”: “en”, “text”: “hello world”}.

Keyword Arguments

language (str) – The 2 letter ISO 639-1 representation of language for the entire batch. For example, use “en” for English; “es” for Spanish etc. If not set, uses “en” for English as default. Per-document language will take precedence over whole batch language. See https://aka.ms/talangs for supported languages in Language API.
model_version (str) – The model version to use for the analysis, e.g. “latest”. If a model version is not specified, the API will default to the latest, non-preview version. See here for more info: https://aka.ms/text-analytics-model-versioning
show_stats (bool) – If set to true, response will contain document level statistics in the statistics field of the document-level response.
domain_filter (str or PiiEntityDomain) – Filters the response entities to ones only included in the specified domain. I.e., if set to ‘phi’, will only return entities in the Protected Healthcare Information domain. See https://aka.ms/azsdk/language/pii for more information.
categories_filter (list[str or PiiEntityCategory]) – Instead of filtering over all PII entity categories, you can pass in a list of the specific PII entity categories you want to filter out. For example, if you only want to filter out U.S. social security numbers in a document, you can pass in [PiiEntityCategory.US_SOCIAL_SECURITY_NUMBER] for this kwarg.
string_index_type (str) – Specifies the method used to interpret string offsets. UnicodeCodePoint, the Python encoding, is the default. To override the Python default, you can also pass in Utf16CodeUnit or TextElement_v8. For additional information see https://aka.ms/text-analytics-offsets
disable_service_logs (bool) – Defaults to true, meaning that the Language service will not log your input text on the service side for troubleshooting. If set to False, the Language service logs your input text for 48 hours, solely to allow for troubleshooting issues in providing you with the service’s natural language processing functions. Please see Cognitive Services Compliance and Privacy notes at https://aka.ms/cs-compliance for additional details, and Microsoft Responsible AI principles at https://www.microsoft.com/ai/responsible-ai.

Returns

The combined list of RecognizePiiEntitiesResult and DocumentError in the order the original documents were passed in.

Return type

list[RecognizePiiEntitiesResult or DocumentError]

Raises

HttpResponseError or TypeError or ValueError –

New in version v3.1: The recognize_pii_entities client method.

Example:

Recognize personally identifiable information entities in a batch of documents.¶

import os
from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient

endpoint = os.environ["AZURE_LANGUAGE_ENDPOINT"]
key = os.environ["AZURE_LANGUAGE_KEY"]

text_analytics_client = TextAnalyticsClient(
    endpoint=endpoint, credential=AzureKeyCredential(key)
)
documents = [
    """Parker Doe has repaid all of their loans as of 2020-04-25.
    Their SSN is 859-98-0987. To contact them, use their phone number
    555-555-5555. They are originally from Brazil and have Brazilian CPF number 998.214.865-68"""
]

result = text_analytics_client.recognize_pii_entities(documents)
docs = [doc for doc in result if not doc.is_error]

print(
    "Let's compare the original document with the documents after redaction. "
    "I also want to comb through all of the entities that got redacted"
)
for idx, doc in enumerate(docs):
    print(f"Document text: {documents[idx]}")
    print(f"Redacted document text: {doc.redacted_text}")
    for entity in doc.entities:
        print("...Entity '{}' with category '{}' got redacted".format(
            entity.text, entity.category
        ))