Azure Cognitive Services

Published in

PEAKUP Tech News

5 min readMay 20, 2023

Azure Cognitive Services is a collection of pre-built APIs, SDKs, and services that makes it easier to add intelligent features to applications without needing to build the underlying machine learning models. These pre-built services include a variety of features such as natural language processing, computer vision, speech recognition, and more.

By leveraging Azure Cognitive Services, developers can quickly and easily incorporate advanced AI features into their applications, without the need for specialized knowledge in data science or machine learning. This can help to accelerate development timelines and enable organizations to deliver more intelligent and engaging applications.

Some of the key services available within Azure Cognitive Services include:

Language services: This includes features such as text analytics, sentiment analysis, language detection, and more.
Vision services: This includes features such as image recognition, face detection, and more.
Speech services: This includes features such as speech-to-text, text-to-speech, and more.
Decision services: This includes features such as personalization, recommendation, and more.

Azure Cognitive Services can be accessed via a variety of programming languages and development tools, including .NET, Java, Python, and more. These services can be deployed on-premises or in the cloud, depending on the needs of the organization.

Overall, Azure Cognitive Services provides a powerful set of tools and services for developers looking to add intelligent features to their applications. With pre-built APIs and services for a variety of AI features, it can help to accelerate development timelines and enable organizations to deliver more intelligent and engaging applications to their users.

Azure Cognitive Services provides pre-built APIs, SDKs, and services that enable developers to add intelligent features to their applications, such as natural language processing, computer vision, speech recognition, and more. These services can be accessed via a variety of programming languages and development tools and can be deployed on-premises or in the cloud. By leveraging Azure Cognitive Services, developers can add advanced AI features to their applications without needing specialized knowledge in data science or machine learning, which can help to accelerate development timelines and deliver more intelligent and engaging applications to users.

Benefits of Cognitive Services

Azure Cognitive Services offers several benefits for developers and organizations, including:

Easy to use: With pre-built APIs and services, developers can quickly and easily add advanced AI features to their applications without needing to build the underlying machine learning models themselves.
Accelerated development timelines: By leveraging pre-built services, developers can save time and accelerate the development timeline for their applications.
No specialized knowledge required: Developers do not need specialized knowledge in data science or machine learning to use Azure Cognitive Services.
A variety of features: Azure Cognitive Services provides a variety of features, including natural language processing, computer vision, speech recognition, and more.
Accessible via multiple programming languages: Azure Cognitive Services can be accessed via a variety of programming languages, including .NET, Java, Python, and more.
Can be deployed on-premises or in the cloud: Depending on the needs of the organization, Azure Cognitive Services can be deployed on-premises or in the cloud.

Overall, Azure Cognitive Services provides a powerful set of tools and services that can help developers to add intelligent features to their applications, accelerate development timelines, and deliver more engaging and intelligent applications to their users.

Demo with Azure Cognitive Services Python SDK

To demonstrate how to use Azure Cognitive Services, we will be using the Python SDK. In this demo, we will be using the Text Analytics service to analyze the sentiment of some sample text.

First, you will need to create a Text Analytics resource in your Azure portal. Once you have done this, you will need to create a Python script to use the Text Analytics API.

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

key = os.environ["COGNITIVE_SERVICES_KEY"]
endpoint = os.environ["COGNITIVE_SERVICES_ENDPOINT"]def authenticate_client():
    ta_credential = AzureKeyCredential(key)
    text_analytics_client = TextAnalyticsClient(endpoint=endpoint, credential=ta_credential)
    return text_analytics_clientdef sentiment_analysis_example(client):    documents = [
        "I had the best day of my life. I wish you were there with me.",
        "The restaurant was crowded and the food was terrible",
        "The movie was really good"
    ]    response = client.analyze_sentiment(documents=documents)[0]    for idx, doc in enumerate(response.documents):
        print("Document text: {}\\\\n".format(documents[idx]))
        print("Overall sentiment: {}\\\\n".format(doc.sentiment))
        print("Scores: positive={}; neutral={}; negative={} \\\\n".format(
            doc.confidence_scores.positive,
            doc.confidence_scores.neutral,
            doc.confidence_scores.negative,
        ))if __name__ == "__main__":
    client = authenticate_client()
    sentiment_analysis_example(client)

In this script, we first import the necessary modules and authenticate the client using your Text Analytics API key and endpoint. We then define a function to perform sentiment analysis on a list of sample documents.

When we run the sentiment_analysis_example function, it will analyze the sentiment of the sample documents using the Text Analytics API and output the results.

This is just a basic example of how to use Azure Cognitive Services with Python. There are many other services and features available, so be sure to check out the Azure Cognitive Services documentation for more information.

Demo with Azure Cognitive Services Vision API and Python SDK

To demonstrate how to use Azure Cognitive Services Vision API, we will be using the Python SDK. In this demo, we will be using the Computer Vision service to analyze an image and extract information from it.

First, you will need to create a Computer Vision resource in your Azure portal. Once you have done this, you will need to create a Python script to use the Computer Vision API.

import os
from azure.cognitiveservices.vision.computervision import ComputerVisionClient
from azure.cognitiveservices.vision.computervision.models import VisualFeatureTypes
from msrest.authentication import CognitiveServicesCredentials
from pprint import pprint

subscription_key = os.environ["COGNITIVE_SERVICES_SUBSCRIPTION_KEY"]
endpoint = os.environ["COGNITIVE_SERVICES_ENDPOINT"]computervision_client = ComputerVisionClient(endpoint, CognitiveServicesCredentials(subscription_key))image_url = "<https://www.example.com/image.jpg>"image_analysis = computervision_client.analyze_image(image_url, visual_features=[VisualFeatureTypes.tags, VisualFeatureTypes.description])pprint(image_analysis.tags)
pprint(image_analysis.description.captions)

In this script, we first import the necessary modules and authenticate the client using your Computer Vision API key and endpoint. We then define a function to perform image analysis on a given image URL.

When we run the script, it will analyze the image using the Computer Vision API and output the tags and description of the image.

This is just a basic example of how to use Azure Cognitive Services Vision API with Python. There are many other services and features available, so be sure to check out the Azure Cognitive Services documentation for more information.

Pricing

The pricing for Azure Cognitive Services varies depending on the specific service and the amount of usage. Some services offer a free tier with limited usage, while others require a paid subscription. You can find more information on pricing for each service on the Azure Cognitive Services pricing page.

Azure Cognitive Services