Blogs by Ashwin

  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...

  Improve an Index With Analyzers and Tokenized Terms By default, Azure AI Search is set up to examine text and find useful tokens for your index. The appropriate tokens guaranty that users may swiftly locate the documents they require. An ideal index is often produced by the default configuration. However, you might wish to specify exactly how text is processed if you have uncommon or unique fields. Analyzers in AI Search Text is retrieved by AI Search when it indexes your material. That text must be processed in order to create a helpful index with terms that aid users in finding documents. For example: The text should be broken into words, often by using whitespace and punctuation characters as delimiters. Stopwords, such as "the" and "it", should be removed because users don't search for them. Words should be reduced to their root form. For example, past tense words, such as "ran", should be replaced with present tense words, such as "run...

  How Search Scores Are Calculated ? The final stage of processing a search query is scoring. The documents that are retrieved from the first three stages are ranked by the search engine. The number of times detected search phrases exist in a document, the size of the document, and the rarity of each keyword all affect the score. The search results are automatically sorted by search score, with the highest score appearing first. An $orderby clause can be included to break a tie between two documents that have the same search score. Improve Score For More Relevant Documents The final score may not be the highest for the most relevant document because the default scoring is based on phrase frequency and rarity. Because every dataset is unique, AI Search allows you to use scoring profiles to affect a document's score. The most straightforward scoring profile defines different weights for fields in an index. Functions like freshness and distance can also be included in the score profil...