Blogs by Ashwin

  Introduction By extracting more information from the source data, you can significantly enhance an index using Azure AI Search's predefined skills. However, there can be times when you have certain data extraction requirements that call for some bespoke functionality and cannot be satisfied by the established abilities. For example: Integrate the Form Recognizer service to extract data from forms Consume an Azure Machine Learning model to integrate predicted values into an index Any other custom logic Custom skills can be implemented as web-hosted services (like Azure Functions) that enable the necessary interface for integration into a skillset in order to support these scenarios. Define Custom Skill Schema The expected structure for input and output data that is required by abilities in an Azure AI Search skillset must be implemented by your custom skill. Input Schema A JSON structure with a record for every document to be handled is defined by the input schema for a custom ski...

  Apply Filtering and Sorting Users frequently like to filter and order query results according to field values in search solutions. Both of these features are supported by Azure AI Search via the search query API. Filtering Results You can apply filters to queries in two ways: By including filter criteria in a simple search expression. By providing an OData filter expression as a $filter parameter with a full syntax search expression. You can apply a filter to any filterable field in the index. Filtering With Facets When presenting users with filtering criteria based on field values in a result set, facets are a helpful tool. They function best when a field contains a limited number of discrete values that can be shown in the user interface as options or links. In order to use facets, you must first define the facetable fields for which you wish to extract the potential values. Sorting Results The query process's relevancy score is used by default to rank the results, with the hig...

  Understand The Indexing Process For every indexed entity, a document is created as part of the indexing process. An enrichment pipeline produces the documents repeatedly during indexing, combining enriched fields retrieved by cognitive skills with metadata from the data source. You can think of each indexed document as a JSON structure, which initially consists of a document with the index fields you have mapped to fields extracted directly from the source data. You can set up the indexer to extract image data from documents in the data source and add each image to a collection called normalized_images. You can use the collection of photographs as an input for skills that extract information from image data by normalizing the image data in this manner. Every talent adds fields to the document. For instance, a skill that determines the language used in a document may store its result in a language field. The document is structured hierarchically, and the skills are applied to a sp...