Blogs by Ashwin

  Index Any Data Using Azure AI Search Push API The most adaptable method for adding data to an Azure AI Search index is the REST API. Any programming language or interactive application that can send JSON requests to an endpoint can be used. Supported REST API Operations There are two supported REST APIs provided by AI Search- Search and management APIs. How To Call Search REST API ? If you want to call any of the search APIs you need to: Use the HTTPS endpoint provided by your search service, you must include an api-version in the URI. The request header must include an api-key attribute. To find the endpoint, api-version, and api-key go to the Azure portal. In the portal, navigate to your search service, then select Search explorer. Choose Keys to locate the api-key on the left. If you're doing more than just accessing the index with the REST API, you can use either the primary or secondary admin key. You can make and use query keys if you only need to search an index. An a...

  Index Data From External Data Sources Using Azure Data Factory An organization's search solution frequently has to include external data that isn't stored in Azure. Because it offers numerous methods for creating and pushing data into indexes, Azure AI Search is adaptable. Push Data Into Search Index Using Azure Data Factory (ADF) One method is to use ADF to push data into an index using a zero-code option. Almost 100 distinct data stores are connected to ADF. You can link an infinite number of data stores using connectors like HTTP and REST. These data stores are utilized in pipelines as either a source or a target (referred to as sinks). In a copy activity, the Azure AI Search index connector can be utilized as a sink. Create ADF Pipeline To Push Data Into Search Index The steps you need to take to use and ADF pipeline to push data into a search index are: Create an Azure AI Search index with all the fields you want to store data in. Create a pipeline with a copy data step....

  How To Use Custom Azure Machine Learning Skillset ? You can create robust AI models and host them on Azure using Azure Machine Learning. The endpoints of these AI models can be utilized in search strategies to improve indexes. Adding a machine learning custom skill to a search index functions in the same way as adding any other custom talent. Custom Azure Machine Learning Skill Schema An Azure Machine Learning (AML) custom skill enriches a search index at the document level. Your document indexer must have an AmlSkill in its skill set. Note that batchSize options are not included in the custom skill. One document at a time will be processed by the AML model. The remaining parameters, timeout and degree of parallelism, regulate how the skill is performed. The timeout value in the aforementioned schema is set at 30 seconds. One should be the starting point for the degree of parallelism. You may be able to raise this figure, depending on your infrastructure. Scaling up the Kubernet...

  Improve Search Experience By Ordering Results By Distance From a Given Reference Point Users frequently wish to look for products connected to a specific area. For instance, they may want to locate the coffee shop closest to their location. AI Search has geospatial features that you can use in queries to compare locations on the surface of the Earth. What are Geo-Spatial Functions? The hotel's location is a crucial factor to take into account when making a reservation. For instance, you will want a hotel close to the Eiffel Tower if you're planning a trip to view it. To ask AI Search to return results based on their location information, you can use two functions in your query: geo.distance - This function returns the distance in a straight line across the Earth's surface from the point you specify to the location of the search result. geo.intersects - This function returns true if the location of a search result is inside a polygon that you specify. Make sure the locat...

  Create a Custom Analyzer When you define the index, you provide a custom analyzer. The Azure site does not allow you to define a custom index, instead, you must use JSON code. During the design phase, make use of the index's analyzers section. One tokenizer, one or more character filters, and one or more token filters may be included. Use a unique name for your analyzer and set the @odata.type property to Microsoft.Azure.Search.CustomAnalyzer. Test Custom Analyzer You can utilize the REST API's Analyze Text function after defining your custom analyzer as part of your index. To submit test text and make sure the analyzer returns tokens appropriately, use the text function. Create these queries using any REST testing tool, like the well-known Postman program. Be sure to test with lots of different text values until you're sure that the custom analyzer behaves as you expect. Use a Custom Analyzer For a Field You can set up your index to utilize a custom analyzer once you...

  What are tokenizers ? The part that separates the text into the tokens that will be kept in the index is called the tokenizer. Additionally, tokenizers deconstruct words into their most basic forms. Often, a token is a single word, but you might want to create unusual tokens such as: A full postal address. A complete URL or email address. Words based on the grammar of a specific language. There are 13 different tokenizers to choose from. These tokenizers include: classic- This tokenizer processes text based on grammar for European languages. keyword- This tokenizer emits the entire input as a single token. Use this tokenizer for fields that should always be indexed as one value. lowercase- This tokenizer divides text at non-letters and then modifies the resulting tokens to all lower case. microsoft_language_tokenizer - This tokenizer divides text based on the grammar of the language you specify. pattern- This tokenizer divides texts where it matches a regular expression that y...