Registry / azure / azure-ai-language-questionanswering

azure-ai-language-questionanswering

library1.1.0pypypi✓ verified 84d ago

Microsoft Azure Question Answering client library for Python, enabling extraction of answers from custom knowledge bases or FAQ data. Version 1.1.0 supports both custom and prebuilt question answering, with synchronous and asynchronous clients. Released monthly as part of Azure SDK.

azure llm-agents

pip install azure-ai-language-questionanswering

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · AZURE-AI-LANGUAGE-

azure-ai-language-questionanswering

azurepythonv1.1.0

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

QuestionAnsweringClient

✓ from azure.ai.language.questionanswering import QuestionAnsweringClient

✗ from azure.ai.language.questionanswering.models import QuestionAnsweringClient

Client class is in the top-level module, not models

AnswersFromTextOptions

✓ from azure.ai.language.questionanswering.models import AnswersFromTextOptions

✗ from azure.ai.language.questionanswering import AnswersFromTextOptions

Model classes are under .models

AnswersOptions

✓ from azure.ai.language.questionanswering.models import AnswersOptions

Authenticate using endpoint and key, then query a knowledge base.

import os from azure.ai.language.questionanswering import QuestionAnsweringClient from azure.core.credentials import AzureKeyCredential endpoint = os.environ.get('AZURE_QA_ENDPOINT', '') credential = AzureKeyCredential(os.environ.get('AZURE_QA_KEY', '')) client = QuestionAnsweringClient(endpoint, credential) response = client.get_answers( question="What is a good pet?", project_name="SampleProject", deployment_name="production" ) if response.answers: print(response.answers[0].answer)

Debug

Known issues

breakingIn version 1.1.0, the `get_answers` method signature changed: `top` parameter renamed to `top_answers` and `confidence_threshold` renamed to `confidence_score_threshold`.

fix

Update calls to use new parameter names.

affects: <1.1.0 -> 1.1.0

deprecatedThe `text_documents` parameter in `get_answers_from_text` is deprecated in favor of `text_documents` as part of `AnswersFromTextOptions`.

fix

Use `AnswersFromTextOptions` model to pass text documents.

affects: <=1.1.0

gotchaBoth `project_name` and `deployment_name` are required for custom QnA (non-text queries). Missing them results in a ResourceNotFound error.

fix

Ensure both parameters are provided when querying a project.

affects: all

gotchaWhen using `get_answers_from_text`, the `text_documents` parameter expects a list of `TextDocument` objects, not raw strings.

fix

Import `TextDocument` from models and wrap strings: `from azure.ai.language.questionanswering.models import TextDocument`.

affects: all

Errors

Common errors & fixes

AttributeError: 'QuestionAnsweringClient' object has no attribute 'get_answers'

Using an older version of the library (<1.0.0) where method was `query_knowledgebase`

fix

Upgrade to version 1.1.0 and use `get_answers` method.

azure.core.exceptions.ResourceNotFoundError: (NotFound) The specified project does not exist.

`project_name` or `deployment_name` missing or incorrect

fix

Ensure both parameters are provided and match exactly the names in Azure AI Language resource.

TypeError: get_answers() got an unexpected keyword argument 'top'

Using `top` parameter which was renamed to `top_answers` in version 1.1.0

fix

Replace `top` with `top_answers` in the call.

Upgrade

Version history

1.1.0latest on PyPI · released Oct 13, 2022

Audit

Dependencies

azure-corerequiredHTTP pipeline and authentication

azure-identityoptionalDefaultAzureCredential for auth

Agent activity

46 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/Azure/azure-sdk-for-python ↗

packagehttps://pypi.org/project/azure-ai-language-questionanswering/ ↗

homepagehttps://azure.microsoft.com/services/cognitive-services/question-answering/ ↗