Skip to content

Commit

Permalink
[QnA] Initial SDK (Azure#19544)
Browse files Browse the repository at this point in the history
* Template + first code gen

* Basic client

* First tests

* Added async client + tests

* Added answerspan test

* Added authoring APIs

* Some updates

* Pure generated clients

* Test updates

* Update test imports

* Clean working recordings

* Renamed directory

* Removed authoring for now

* Use unreleased core

* Remove conversation + ci yaml

* Some CI updates

* update language __init__.py to not have a space in the name

* Setup.py

* Updated core dependency

* CI fixes

* Added language nspkg

* Fix Python 2.7

* Added some more tests

* Test fixes

* Added live configuration

* Bumped msrest

* readme + samples

* No pypi or refdocs yet

* Review feedback

Co-authored-by: scbedd <45376673+scbedd@users.noreply.github.com>
  • Loading branch information
2 people authored and rakshith91 committed Jul 16, 2021
1 parent 740822c commit 4405ea2
Show file tree
Hide file tree
Showing 76 changed files with 6,685 additions and 1 deletion.
3 changes: 2 additions & 1 deletion eng/tox/allowed_pylint_failures.py
Original file line number Diff line number Diff line change
Expand Up @@ -56,5 +56,6 @@
"azure-purview-catalog",
"azure-messaging-nspkg",
"azure-agrifood-farming",
"azure-eventhub"
"azure-eventhub",
"azure-ai-language-questionanswering"
]
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
# Release History

## 1.0.0b1 (unreleased)

### Features Added
* Initial release.
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
include _meta.json
include *.md
include azure/__init__.py
include azure/ai/__init__.py
include azure/ai/language/__init__.py
recursive-include tests *.py
recursive-include samples *.py *.md
include azure/ai/language/questionanswering/py.typed
212 changes: 212 additions & 0 deletions sdk/cognitivelanguage/azure-ai-language-questionanswering/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,212 @@
[![Build Status](https://dev.azure.com/azure-sdk/public/_apis/build/status/azure-sdk-for-python.client?branchName=main)](https://dev.azure.com/azure-sdk/public/_build/latest?definitionId=46?branchName=main)

# 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][questionanswering_client_src] | [Package (PyPI)][questionanswering_pypi_package] | [API reference documentation][questionanswering_refdocs] | [Product documentation][questionanswering_docs] | [Samples][questionanswering_samples]

## Getting started

### Prerequisites

* Python 2.7, or 3.6 or later is required to use this package.
* An [Azure subscription][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_link]:

```bash
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`][questionanswering_client_class] class. You will need an **endpoint**, and an **API key** instantiate a client object. For more information regarding authenticating with Cognitive Services, see [Authenticate requests to Azure Cognitive Services][cognitive_auth].

#### 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][azure_portal].

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

```powershell
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`:

```python
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`][questionanswering_client_class] 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](#create-questionansweringclient).
- [Ask a question](#ask-a-question)
- [Ask a follow-up question](#ask-a-follow-up-question)
- [Asynchronous operations](#asynchronous-operations)

### Ask a question

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

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

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

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

```

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

### Ask a follow-up question

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

```python
params = qna.models.KnowledgebaseQueryParameters(
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(
project_name="FAQ",
knowledgebase_query_parameters=params
)
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:
```python
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.KnowledgebaseQueryParameters(
question="How long should my Surface battery last?"
)

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

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

## Troubleshooting

### General
Azure QuestionAnswering clients raise exceptions defined in [Azure Core][azure_core_readme].
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][questionanswering_rest_docs] requests.

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

```python
from azure.core.exceptions import HttpResponseError

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

### Logging
This library uses the standard
[logging][python_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][sdk_logging_docs].

## Next steps

* View our [samples][questionanswering_samples].
* Read about the different [features][questionanswering_docs_features] of the Question Answering service.
* Try our service [demos][questionanswering_docs_demos].

## Contributing

See the [CONTRIBUTING.md][contributing] 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][cla].

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

<!-- LINKS -->
[azure_cli]: https://docs.microsoft.com/cli/azure/
[azure_portal]: https://portal.azure.com/
[azure_subscription]: https://azure.microsoft.com/free/
[cla]: https://cla.microsoft.com
[coc_contact]: mailto:opencode@microsoft.com
[coc_faq]: https://opensource.microsoft.com/codeofconduct/faq/
[code_of_conduct]: https://opensource.microsoft.com/codeofconduct/
[cognitive_auth]: https://docs.microsoft.com/azure/cognitive-services/authentication/
[contributing]: https://github.com/Azure/azure-sdk-for-python/blob/main/CONTRIBUTING.md
[python_logging]: https://docs.python.org/3/library/logging.html
[sdk_logging_docs]: https://docs.microsoft.com/azure/developer/python/azure-sdk-logging
[azure_core_ref_docs]: https://azuresdkdocs.blob.core.windows.net/$web/python/azure-core/latest/azure.core.html
[azure_core_readme]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/README.md
[pip_link]:https://pypi.org/project/pip/
[questionanswering_client_class]: https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/cognitivelanguage/azure-ai-language-questionanswering/azure/ai/language/questionanswering/_question_answering_client.py#L27
[questionanswering_client_src]: https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/cognitivelanguage/azure-ai-language-questionanswering/
[questionanswering_docs]: https://azure.microsoft.com/services/cognitive-services/qna-maker/
[questionanswering_docs_chat]: https://docs.microsoft.com/azure/cognitive-services/qnamaker/how-to/chit-chat-knowledge-base
[questionanswering_docs_demos]: https://azure.microsoft.com/services/cognitive-services/qna-maker/#demo
[questionanswering_docs_features]: https://azure.microsoft.com/services/cognitive-services/qna-maker/#features
[questionanswering_pypi_package]: https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/cognitivelanguage/azure-ai-language-questionanswering/
[questionanswering_refdocs]: https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/cognitivelanguage/azure-ai-language-questionanswering/
[questionanswering_rest_docs]: https://docs.microsoft.com/rest/api/cognitiveservices-qnamaker/
[questionanswering_samples]: https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/cognitivelanguage/azure-ai-language-questionanswering/samples/README.md

![Impressions](https://azure-sdk-impressions.azurewebsites.net/api/impressions/azure-sdk-for-python%2Fsdk%2Ftemplate%2Fazure-template%2FREADME.png)
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
__path__ = __import__('pkgutil').extend_path(__path__, __name__)
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
__path__ = __import__('pkgutil').extend_path(__path__, __name__)
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
__path__ = __import__('pkgutil').extend_path(__path__, __name__)
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
# coding=utf-8
# --------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# Code generated by Microsoft (R) AutoRest Code Generator.
# Changes may cause incorrect behavior and will be lost if the code is regenerated.
# --------------------------------------------------------------------------

from ._question_answering_client import QuestionAnsweringClient
from ._version import VERSION

__version__ = VERSION
__all__ = ['QuestionAnsweringClient']

try:
from ._patch import patch_sdk # type: ignore
patch_sdk()
except ImportError:
pass
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
# coding=utf-8
# --------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for license information.
# Code generated by Microsoft (R) AutoRest Code Generator.
# Changes may cause incorrect behavior and will be lost if the code is regenerated.
# --------------------------------------------------------------------------

from typing import TYPE_CHECKING

from azure.core.configuration import Configuration
from azure.core.pipeline import policies

from ._version import VERSION

if TYPE_CHECKING:
# pylint: disable=unused-import,ungrouped-imports
from typing import Any

from azure.core.credentials import AzureKeyCredential


class QuestionAnsweringClientConfiguration(Configuration):
"""Configuration for QuestionAnsweringClient.
Note that all parameters used to create this instance are saved as instance
attributes.
:param credential: Credential needed for the client to connect to Azure.
:type credential: ~azure.core.credentials.AzureKeyCredential
:param endpoint: Supported Cognitive Services endpoint (e.g., https://:code:`<resource-name>`.api.cognitiveservices.azure.com).
:type endpoint: str
"""

def __init__(
self,
credential, # type: AzureKeyCredential
endpoint, # type: str
**kwargs # type: Any
):
# type: (...) -> None
if credential is None:
raise ValueError("Parameter 'credential' must not be None.")
if endpoint is None:
raise ValueError("Parameter 'endpoint' must not be None.")
super(QuestionAnsweringClientConfiguration, self).__init__(**kwargs)

self.credential = credential
self.endpoint = endpoint
self.api_version = "2021-05-01-preview"
kwargs.setdefault("sdk_moniker", "ai-language-questionanswering/{}".format(VERSION))
self._configure(**kwargs)

def _configure(
self, **kwargs # type: Any
):
# type: (...) -> None
self.user_agent_policy = kwargs.get("user_agent_policy") or policies.UserAgentPolicy(**kwargs)
self.headers_policy = kwargs.get("headers_policy") or policies.HeadersPolicy(**kwargs)
self.proxy_policy = kwargs.get("proxy_policy") or policies.ProxyPolicy(**kwargs)
self.logging_policy = kwargs.get("logging_policy") or policies.NetworkTraceLoggingPolicy(**kwargs)
self.http_logging_policy = kwargs.get("http_logging_policy") or policies.HttpLoggingPolicy(**kwargs)
self.retry_policy = kwargs.get("retry_policy") or policies.RetryPolicy(**kwargs)
self.custom_hook_policy = kwargs.get("custom_hook_policy") or policies.CustomHookPolicy(**kwargs)
self.redirect_policy = kwargs.get("redirect_policy") or policies.RedirectPolicy(**kwargs)
self.authentication_policy = kwargs.get("authentication_policy")
if self.credential and not self.authentication_policy:
self.authentication_policy = policies.AzureKeyCredentialPolicy(
self.credential, "Ocp-Apim-Subscription-Key", **kwargs
)
Loading

0 comments on commit 4405ea2

Please sign in to comment.