Azure Cognitive Language Services Question Answering client library for Python

Question Answering is a cloud-based API service that lets you create a conversational question-and-answer layer over your existing data. Use it to build a knowledge base by extracting questions and answers from your semi-structured content, including FAQ, manuals, and documents. Answer users’ questions with the best answers from the QnAs in your knowledge base—automatically. Your knowledge base gets smarter, too, as it continually learns from users' behavior.

Source code | Package (PyPI) | API reference documentation | Product documentation | Samples

Getting started

Prerequisites

• Python 2.7, or 3.6 or later is required to use this package.
• An Azure subscription
• An existing Question Answering resource

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

Install the package

Install the Azure QuestionAnswering client library for Python with pip:

pip install azure-ai-language-questionanswering

Authenticate the client

In order to interact with the Question Answering service, you'll need to create an instance of the QuestionAnsweringClient 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.

Get an API key

You can get the endpoint and an API key from the Cognitive Services resource or Question Answering resource in the Azure Portal.

Alternatively, use the Azure CLI command shown below to get the API key from the Question Answering resource.

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

Create QuestionAnsweringClient

Once you've determined your endpoint and API key you can instantiate a QuestionAnsweringClient:

from azure.core.credentials import AzureKeyCredential
from azure.ai.language.questionanswering import QuestionAnsweringClient

endpoint = "https://{myaccount}.api.cognitive.microsoft.com"
credential = AzureKeyCredential("{api-key}")

client = QuestionAnsweringClient(endpoint, credential)

Key concepts

QuestionAnsweringClient

The QuestionAnsweringClient is the primary interface for asking questions using a knowledge base with your own information, or text input using pre-trained models. For asynchronous operations, an async QuestionAnsweringClient is in the azure.ai.language.questionanswering.aio namespace.

Examples

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

The following examples show common scenarios using the client created above.

• Ask a question
• Ask a follow-up question
• Asynchronous operations

Ask a question

The only input required to ask a question using a knowledge base is just the question itself:

from azure.ai.language.questionanswering import models as qna

params = qna.KnowledgeBaseQueryOptions(
    question="How long should my Surface battery last?"
)

output = client.query_knowledgebase(
    params,
    project_name="FAQ",
)
for candidate in output.answers:
    print("({}) {}".format(candidate.confidence_score, candidate.answer))
    print("Source: {}".format(candidate.source))

You can set additional properties on KnowledgeBaseQueryOptions to limit the number of answers, specify a minimum confidence score, and more.

Ask a follow-up question

If your knowledge base is configured for chit-chat, you can ask a follow-up question provided the previous question-answering ID and, optionally, the exact question the user asked:

params = qna.models.KnowledgeBaseQueryOptions(
    question="How long should charging take?"
    context=qna.models.KnowledgeBaseAnswerRequestContext(
        previous_user_query="How long should my Surface battery last?",
        previous_qna_id=previous_answer.id
    )
)

output = client.query_knowledgebase(
    params,
    project_name="FAQ"
)
for candidate in output.answers:
    print("({}) {}".format(candidate.confidence_score, candidate.answer))
    print("Source: {}".format(candidate.source))

Asynchronous operations

The above examples can also be run asynchronously using the client in the aio namespace:

from azure.core.credentials import AzureKeyCredential
from azure.ai.language.questionanswering.aio import QuestionAnsweringClient
from azure.ai.language.questionanswering import models as qna

client = QuestionAnsweringClient(endpoint, credential)

params = qna.KnowledgeBaseQueryOptions(
    question="How long should my Surface battery last?"
)

output = await client.query_knowledgebase(
    params,
    project_name="FAQ"
)

Optional Configuration

Optional keyword arguments can be passed in at the client and per-operation level. The azure-core reference documentation describes available configurations for retries, logging, transport protocols, and more.

Troubleshooting

General

Azure QuestionAnswering clients raise exceptions defined in Azure Core. When you interact with the Cognitive Language Services Question Answering client library using the Python SDK, errors returned by the service correspond to the same HTTP status codes returned for REST API requests.

For example, if you submit a question to a non-existant knowledge base, a 400 error is returned indicating "Bad Request".

from azure.core.exceptions import HttpResponseError

try:
    client.query_knowledgebase(
        params,
        project_name="invalid-knowledge-base"
    )
except HttpResponseError as error:
    print("Query failed: {}".format(error.message))

Logging

This library uses the standard logging 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.

Next steps

• View our samples.
• Read about the different features of the Question Answering service.
• Try our service demos.

Contributing

See the 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.

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. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.