Retrieve and process entities

Microsoft Azure provides a range of powerful AI tools and services that allow developers to build intelligent applications. One such tool is the ability to retrieve and process entities related to designing and implementing a Microsoft Azure AI solution. In this article, we will explore how to use Azure services to retrieve and process entities related to designing and implementing an AI solution.

Retrieving Entities with Azure Cognitive Services

Azure Cognitive Services is a collection of AI-powered APIs that enable developers to add intelligent features to their applications. One important API provided by Cognitive Services is the Entity Linking Intelligence Service (ELIS). ELIS allows you to perform entity recognition and linking in text documents, identifying and disambiguating entities such as people, places, organizations, and concepts.

To retrieve entities using ELIS, you need to make an API call to the ELIS endpoint. Here’s an example using Python and the requests library:

python
import requests

subscription_key = ‘your-subscription-key’
endpoint = ‘https://api.cognitive.microsoft.com/elis/v1.0/link’

headers = {
‘Ocp-Apim-Subscription-Key’: subscription_key,
‘Content-Type’: ‘application/json’
}

data = {
‘documents’: [
{
‘id’: ‘1’,
‘text’: ‘Microsoft Azure provides a range of powerful AI tools and services.’
}
]
}

response = requests.post(endpoint, headers=headers, json=data)
entities = response.json()[‘documents’][0][‘entities’]

for entity in entities:
print(‘Entity:’, entity[‘name’])
print(‘Wikipedia page:’, entity[‘wikipediaUrl’])
print()

In the example above, replace `’your-subscription-key’` with your actual ELIS subscription key. The API call is made to the ELIS endpoint, passing in the text to analyze. The response contains a list of entities found in the text, along with their Wikipedia page URLs.

Once you have retrieved the entities, you can process them according to your application’s requirements. For example, you can categorize them, perform sentiment analysis on the associated text, or extract additional information from the Wikipedia page.

Processing Entities with Azure Cognitive Search

Azure Cognitive Search provides advanced search capabilities over structured and unstructured data by using built-in AI models. It allows you to extract key phrases, entities, and other information from your data. To process entities using Azure Cognitive Search, you need to create an index that defines the structure of your data and specify how the entities should be extracted.

Here’s an example of how to create an index that extracts entities using Azure Cognitive Search:

PUT https://[search-service-name].search.windows.net/indexes/[index-name]?api-version=2020-06-30
Content-Type: application/json
api-key: [api-key]

{
“name”: “[index-name]”,
“fields”: [
{“name”: “id”, “type”: “Edm.String”, “key”: true, “searchable”: false},
{“name”: “text”, “type”: “Edm.String”, “searchable”: true, “sortable”: false, “filterable”: false, “facetable”: false}
],
“suggesters”: [
{
“name”: “entities”,
“searchMode”: “analyzingInfixMatching”,
“sourceFields”: [“text”]
}
],
“tokenizers”: [
{“name”: “microsoft_language_tokenizer”, “@odata.type”: “#Microsoft.Azure.Search.MicrosoftLanguageTokenizer”, “isSearchTokenizer”: true}
],
“analyzers”: [
{“name”: “language”, “@odata.type”: “#Microsoft.Azure.Search.MicrosoftLanguageAnalyzer”, “tokenizerName”: “microsoft_language_tokenizer”}
]
}

In the example above, replace `[search-service-name]` with the name of your Azure Cognitive Search service, `[api-key]` with your actual API key, and `[index-name]` with the desired index name. The index definition includes a field called `text` that will be used to extract entities.

Once you have created the index, you can use the search functionality to retrieve the entities. Here’s an example using the Azure Cognitive Search REST API:

POST https://[search-service-name].search.windows.net/indexes/[index-name]/docs/search?api-version=2020-06-30
Content-Type: application/json
api-key: [api-key]

{
“search”: “Microsoft Azure provides a range of powerful AI tools and services.”,
“searchFields”: “text”,
“searchMode”: “all”,
“select”: “id,text”,
“suggesterName”: “entities”
}

In the example above, replace `[search-service-name]`, `[api-key]`, and `[index-name]` with the corresponding values. The API call is made to the search endpoint for your Azure Cognitive Search service, passing in the search query and specifying the `suggesterName` that corresponds to the entities configured in the index.

The response contains a list of documents that match the search query, along with the entities extracted from each document.

In this article, we have explored how to retrieve and process entities related to designing and implementing a Microsoft Azure AI solution. By leveraging Azure Cognitive Services and Azure Cognitive Search, developers can build intelligent applications that make use of entities and their associated information.