.. role:: raw-html-m2r(raw)
   :format: html



.. image:: https://dev.azure.com/azure-sdk/public/_apis/build/status/azure-sdk-for-python.client?branchName=main
   :target: https://dev.azure.com/azure-sdk/public/_build/latest?definitionId=46?branchName=main
   :alt: Build Status


Azure Conversational Language Understanding client library for Python
=====================================================================

Conversational Language Understanding, aka **CLU** for short, is a cloud-based conversational AI service which is mainly used in bots to extract useful information from user utterance (natural language processing).
The CLU **analyze api** encompasses two projects; conversation, and orchestration projects.
You can use the "conversation" project if you want to extract intents (intention behind a user utterance) and custom entities.
You can also use the "orchestration" project which orchestrates multiple language apps to get the best response (language apps like Question Answering, Luis, and Conversation).

`Source code <https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/cognitivelanguage/azure-ai-language-conversations>`_ | `Package (PyPI) <https://pypi.org/project/azure-ai-language-conversations/>`_ | `API reference documentation <https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-language-conversations/latest/azure.ai.language.conversations.html>`_ | `Product documentation <https://docs.microsoft.com/azure/cognitive-services/language-service/conversational-language-understanding/overview>`_ | `Samples <https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/cognitivelanguage/azure-ai-language-conversations/samples/README.md>`_

*Disclaimer*
----------------

*Azure SDK Python packages support for Python 2.7 ended 01 January 2022. For more information and questions, please refer to https://github.com/Azure/azure-sdk-for-python/issues/20691*

Getting started
---------------

Prerequisites
^^^^^^^^^^^^^


* Python 3.6 or later is required to use this package.
* An `Azure subscription <https://azure.microsoft.com/free/>`_
* An existing Text Analytics resource

..

   Note: the new unified Cognitive Language Services are not currently available for deployment.


Install the package
^^^^^^^^^^^^^^^^^^^

Install the Azure Conversations client library for Python with `pip <https://pypi.org/project/pip/>`_\ :

.. code-block:: bash

   pip install azure-ai-language-conversations

Authenticate the client
^^^^^^^^^^^^^^^^^^^^^^^

In order to interact with the CLU service, you'll need to create an instance of the `ConversationAnalysisClient <https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-language-conversations/latest/azure.ai.language.conversations.html#azure.ai.language.conversations.ConversationAnalysisClient>`_ class. You will need an **endpoint**\ , and an **API key** to instantiate a client object. For more information regarding authenticating with Cognitive Services, see `Authenticate requests to Azure Cognitive Services <https://docs.microsoft.com/azure/cognitive-services/authentication/>`_.

Get an API key
~~~~~~~~~~~~~~

You can get the **endpoint** and an **API key** from the Cognitive Services resource in the `Azure Portal <https://portal.azure.com/>`_.

Alternatively, use the `Azure CLI <https://docs.microsoft.com/cli/azure/>`_ command shown below to get the API key from the Cognitive Service resource.

.. code-block:: powershell

   az cognitiveservices account keys list --resource-group <resource-group-name> --name <resource-name>

Create ConversationAnalysisClient
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Once you've determined your **endpoint** and **API key** you can instantiate a ``ConversationAnalysisClient``\ :

.. code-block:: python

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.language.conversations import ConversationAnalysisClient

   endpoint = "https://<my-custom-subdomain>.cognitiveservices.azure.com/"
   credential = AzureKeyCredential("<api-key>")
   client = ConversationAnalysisClient(endpoint, credential)

Key concepts
------------

ConversationAnalysisClient
^^^^^^^^^^^^^^^^^^^^^^^^^^

The `ConversationAnalysisClient <https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-language-conversations/latest/azure.ai.language.conversations.html#azure.ai.language.conversations.ConversationAnalysisClient>`_ is the primary interface for making predictions using your deployed Conversations models. For asynchronous operations, an async ``ConversationAnalysisClient`` is in the ``azure.ai.language.conversation.aio`` namespace.

Examples
--------

The ``azure-ai-language-conversation`` client library provides both synchronous and asynchronous APIs.

The following examples show common scenarios using the ``client`` `created above <#create-conversationanalysisclient>`_.

Analyze Text with a Conversation App
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

If you would like to extract custom intents and entities from a user utterance, you can call the ``client.analyze_conversations()`` method with your conversation's project name as follows:

.. code-block:: python

   # import libraries
   import os
   from azure.core.credentials import AzureKeyCredential

   from azure.ai.language.conversations import ConversationAnalysisClient
   from azure.ai.language.conversations.models import (
       CustomConversationalTask,
       ConversationAnalysisOptions,
       CustomConversationTaskParameters,
       TextConversationItem
   )

   # get secrets
   clu_endpoint = os.environ["AZURE_CONVERSATIONS_ENDPOINT"]
   clu_key = os.environ["AZURE_CONVERSATIONS_KEY"]
   project_name = os.environ["AZURE_CONVERSATIONS_PROJECT_NAME"]
   deployment_name = os.environ["AZURE_CONVERSATIONS_DEPLOYMENT_NAME"]

   # analyze quey
   client = ConversationAnalysisClient(clu_endpoint, AzureKeyCredential(clu_key))
   with client:
       query = "Send an email to Carol about the tomorrow's demo"
       result = client.analyze_conversation(
               task=CustomConversationalTask(
                   analysis_input=ConversationAnalysisOptions(
                       conversation_item=TextConversationItem(
                           id=1,
                           participant_id=1,
                           text=query
                       )
                   ),
                   parameters=CustomConversationTaskParameters(
                       project_name=project_name,
                       deployment_name=deployment_name
                   )
               )
           )

   # view result
   print("query: {}".format(result.results.query))
   print("project kind: {}\n".format(result.results.prediction.project_kind))

   print("top intent: {}".format(result.results.prediction.top_intent))
   print("category: {}".format(result.results.prediction.intents[0].category))
   print("confidence score: {}\n".format(result.results.prediction.intents[0].confidence))

   print("entities:")
   for entity in result.results.prediction.entities:
       print("\ncategory: {}".format(entity.category))
       print("text: {}".format(entity.text))
       print("confidence score: {}".format(entity.confidence))
       if entity.resolutions:
           print("resolutions")
           for resolution in entity.resolutions:
               print("kind: {}".format(resolution.resolution_kind))
               print("value: {}".format(resolution.additional_properties["value"]))
       if entity.extra_information:
           print("extra info")
           for data in entity.extra_information:
               print("kind: {}".format(data.extra_information_kind))
               if data.extra_information_kind == "ListKey":
                   print("key: {}".format(data.key))
               if data.extra_information_kind == "EntitySubtype":
                   print("value: {}".format(data.value))

Analyze Text with an Orchestration App
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

If you would like to pass the user utterance to your orchestrator (worflow) app, you can call the ``client.analyze_conversations()`` method with your orchestration's project name. The orchestrator project simply orchestrates the submitted user utterance between your language apps (Luis, Conversation, and Question Answering) to get the best response according to the user intent. See the next example:

.. code-block:: python

   # import libraries
   import os
   from azure.core.credentials import AzureKeyCredential

   from azure.ai.language.conversations import ConversationAnalysisClient
   from azure.ai.language.conversations.models import (
       CustomConversationalTask,
       ConversationAnalysisOptions,
       CustomConversationTaskParameters,
       TextConversationItem
   )

   # get secrets
   clu_endpoint = os.environ["AZURE_CONVERSATIONS_ENDPOINT"]
   clu_key = os.environ["AZURE_CONVERSATIONS_KEY"]
   project_name = os.environ["AZURE_CONVERSATIONS_WORKFLOW_PROJECT_NAME"]
   deployment_name = os.environ["AZURE_CONVERSATIONS_WORKFLOW_DEPLOYMENT_NAME"]

   # analyze query
   client = ConversationAnalysisClient(clu_endpoint, AzureKeyCredential(clu_key))
   with client:
       query = "How are you?"
       result = client.analyze_conversation(
               task=CustomConversationalTask(
                   analysis_input=ConversationAnalysisOptions(
                       conversation_item=TextConversationItem(
                           id=1,
                           participant_id=1,
                           text=query
                       )
                   ),
                   parameters=CustomConversationTaskParameters(
                       project_name=project_name,
                       deployment_name=deployment_name
                   )
               )
           )

   # view result
   print("query: {}".format(result.results.query))
   print("project kind: {}\n".format(result.results.prediction.project_kind))

   # top intent
   top_intent = result.results.prediction.top_intent
   print("top intent: {}".format(top_intent))
   top_intent_object = result.results.prediction.intents[top_intent]
   print("confidence score: {}".format(top_intent_object.confidence))
   print("project kind: {}".format(top_intent_object.target_kind))

   if top_intent_object.target_kind == "question_answering":
       print("\nview qna result:")
       qna_result = top_intent_object.result
       for answer in qna_result.answers:
           print("\nanswer: {}".format(answer.answer))
           print("answer: {}".format(answer.confidence))

Optional Configuration
----------------------

Optional keyword arguments can be passed in at the client and per-operation level. The azure-core `reference documentation <https://azuresdkdocs.blob.core.windows.net/$web/python/azure-core/latest/azure.core.html>`_ describes available configurations for retries, logging, transport protocols, and more.

Troubleshooting
---------------

General
^^^^^^^

The Conversations client will raise exceptions defined in `Azure Core <https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/README.md>`_.

Logging
^^^^^^^

This library uses the standard
`logging <https://docs.python.org/3/library/logging.html>`_ library for logging.
Basic information about HTTP sessions (URLs, headers, etc.) is logged at INFO
level.

Detailed DEBUG level logging, including request/response bodies and unredacted
headers, can be enabled on a client with the ``logging_enable`` argument.

See full SDK logging documentation with examples `here <https://docs.microsoft.com/azure/developer/python/azure-sdk-logging>`_.

.. code-block:: python

   import sys
   import logging
   from azure.core.credentials import AzureKeyCredential
   from azure.ai.language.conversations import ConversationAnalysisClient

   # Create a logger for the 'azure' SDK
   logger = logging.getLogger('azure')
   logger.setLevel(logging.DEBUG)

   # Configure a console output
   handler = logging.StreamHandler(stream=sys.stdout)
   logger.addHandler(handler)

   endpoint = "https://<my-custom-subdomain>.cognitiveservices.azure.com/"
   credential = AzureKeyCredential("<my-api-key>")

   # This client will log detailed information about its HTTP sessions, at DEBUG level
   client = ConversationAnalysisClient(endpoint, credential, logging_enable=True)
   result = client.analyze_conversations(...)

Similarly, ``logging_enable`` can enable detailed logging for a single operation, even when it isn't enabled for the client:

.. code-block:: python

   result = client.analyze_conversations(..., logging_enable=True)

Next steps
----------

Contributing
------------

See the `CONTRIBUTING.md <https://github.com/Azure/azure-sdk-for-python/blob/main/CONTRIBUTING.md>`_ for details on building, testing, and contributing to this library.

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit `cla.microsoft.com <https://cla.microsoft.com>`_.

When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the `Microsoft Open Source Code of Conduct <https://opensource.microsoft.com/codeofconduct/>`_. For more information see the `Code of Conduct FAQ <https://opensource.microsoft.com/codeofconduct/faq/>`_ or contact `opencode@microsoft.com <mailto:opencode@microsoft.com>`_ with any additional questions or comments.

:raw-html-m2r:`<!-- LINKS -->`


.. image:: https://azure-sdk-impressions.azurewebsites.net/api/impressions/azure-sdk-for-python%2Fsdk%2Ftemplate%2Fazure-template%2FREADME.png
   :target: https://azure-sdk-impressions.azurewebsites.net/api/impressions/azure-sdk-for-python%2Fsdk%2Ftemplate%2Fazure-template%2FREADME.png
   :alt: Impressions



Indices and tables
------------------

* :ref:`genindex`
* :ref:`modindex`
* :ref:`search`

.. toctree::
  :maxdepth: 5
  :glob:
  :caption: Developer Documentation

  azure.ai.language.conversations.rst