Azure Cognitive Services Tutorial

Introduction

Azure Cognitive Services are a set of AI services and cognitive APIs provided by Microsoft Azure. These services are designed to help developers create intelligent applications without having direct AI or data science skills or knowledge. They provide machine learning capabilities to see, hear, speak, understand, and even begin to reason.

Setting Up Your Azure Account

To get started with Azure Cognitive Services, you need an Azure account. If you don't already have one, you can create a free account on the Azure website.

Creating a Cognitive Services Resource

Once you have your Azure account, you can create a Cognitive Services resource.

1. Log in to the Azure Portal.
2. In the left-hand menu, select "Create a resource".
3. Search for "Cognitive Services" and select it from the list.
4. Click "Create" and fill in the required details such as Subscription, Resource group, and Region.
5. Click "Review + create" and then "Create" to provision the resource.

Using Cognitive Services APIs

Azure Cognitive Services provides various APIs for different functionalities such as Computer Vision, Text Analytics, and Speech Services. Below are examples of how to use these APIs.

Computer Vision API

The Computer Vision API provides capabilities to analyze images and extract information.

Example: Analyzing an Image

To analyze an image, you need to make a POST request to the Computer Vision API endpoint.

curl -X POST "https://.api.cognitive.microsoft.com/vision/v3.1/analyze" \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: " \
-d '{"url": "https://example.com/image.jpg"}'

{
    "categories": [],
    "color": {
        "dominantColorForeground": "Black",
        "dominantColorBackground": "White",
        "dominantColors": ["Black", "White"],
        "accentColor": "B95F1E",
        "isBwImg": false,
        "isBWImg": false
    },
    "description": {
        "tags": ["outdoor", "tree", "sky"],
        "captions": [{
            "text": "a tree with a blue sky",
            "confidence": 0.85
        }]
    }
}

Text Analytics API

The Text Analytics API provides capabilities to analyze text for various insights such as sentiment and key phrases.

Example: Sentiment Analysis

To analyze the sentiment of a text, you need to make a POST request to the Text Analytics API endpoint.

curl -X POST "https://.api.cognitive.microsoft.com/text/analytics/v3.0/sentiment" \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: " \
-d '{
    "documents": [{
        "language": "en",
        "id": "1",
        "text": "I love using Azure Cognitive Services!"
    }]
}'

{
    "documents": [{
        "id": "1",
        "sentiment": "positive",
        "confidenceScores": {
            "positive": 0.99,
            "neutral": 0.01,
            "negative": 0.00
        }
    }],
    "errors": [],
    "modelVersion": "latest"
}

Speech Services API

The Speech Services API provides capabilities for speech-to-text, text-to-speech, and speech translation.

Example: Speech-to-Text

To convert speech to text, you need to make a POST request to the Speech Services API endpoint.

curl -X POST "https://.api.cognitive.microsoft.com/speech/v1.0/recognize" \
-H "Ocp-Apim-Subscription-Key: " \
--data-binary @audio.wav \
--header "Content-type: audio/wav"

{
    "RecognitionStatus": "Success",
    "DisplayText": "Hello world",
    "Offset": 10000000,
    "Duration": 20000000
}

Conclusion

Azure Cognitive Services provides a comprehensive suite of AI capabilities that can be easily integrated into your applications. By leveraging these services, you can add powerful AI features to your applications without needing extensive knowledge of machine learning or data science.