Semantic Ranking In Azure AI Search

By Ashwin Venugopal -

 




Introduction

Imagine you are employed by a company creating an app aimed at local tourists. You possess a vast amount of data regarding local attractions, yet when users look for information, they occasionally do not see the most pertinent articles at the forefront of their search results. In order to enhance the user experience of your app, you have to explore methods to provide users with more relevant results through the use of Azure AI Search.

What is Semantic Ranking?

Semantic ranking is a feature in Azure AI Search designed to enhance the order of search results. It leverages language understanding to more effectively align the context of the user's original query with the ranking of the search results.

BM25 Ranking Function

Azure AI Search, by default, utilizes the BM25 ranking function. The BM25 ranking function evaluates search results based on how often the search term is found in a document. Typically, the BM25 ranking function produces high-quality rankings, as documents that contain a search term frequently are often the most pertinent. However, this is not always the case. The BM25 ranking method does not consider the semantics of the query, and sometimes enhancing ranking can be achieved through the inclusion of language understanding.

Semantic Ranking

Semantic ranking serves two purposes, it enhances the response to the question by including captions and responses in the results, and it enhances the ranking of the query results based on language comprehension.

In order to extract the context and meaning of the query, semantic ranking combines language understanding models with the BM25 ranking to compute a new relevance score.

Semantic Captions and Answers

In addition to the ranking search results, semantic captions and replies offer extra results that you can show to help visitors better comprehend the results. Semantic captions highlight the most pertinent material in summary phrases that are taken straight from the document.

Semantic answers is an optional additional feature of semantic ranking that provides answers to questions. If the search query appears to be a question and the search results contains text that appears to be a relevant answer, then the semantic answer is returned.

Conclusion

We have successfully learnt about Semantic Ranking in Azure AI search.

 






















Comments

Post a Comment

Popular posts from this blog

Connect Data to Azure Sentinel Using Data Connectors

By Ashwin Venugopal -
Image
  Ingest Log Data with Data Connectors You should connect your data sources with Azure Sentinel Connectors to collect the log data whose page displays a growing list of the connectors provided by Azure Sentinel, after selecting the Open connector page (the detailed connector page has a left and right blade).  The information about the connector, the connector's status, and the last time a log was received if connected is provided by the left blade. Whereas the right tab has two tabs- Instructions and Next Steps. The instructions tab can be different based on the connector having Prerequisites and Configuration which can be followed to connect to the data source. The Next Steps tab offers a quick reference to workbooks, query samples, and analytical templates. Data connectors can only be disconnected/deactivated, not deleted. Note-  The connector does not install Workbooks and Analytical Templates as they are already available in the Sentinel environment for out of the box...
Read more

Information Protection Scanner: Resolve Issues with Information Protection Scanner Deployment

By Ashwin Venugopal -
Image
  About If you are experiencing problems with the Microsoft Purview Information Protection scanner, check the health of your deployment by utilizing the Start-ScannerDiagnosticsPowerShell cmdlet to start the scanner diagnostic tool. The diagnostics tool checks the following details and then creates a log files with the results: Whether the database is up to date. Whether network URLs are accessible. Whether there's a valid authentication token and policy can be acquired. Whether the profile is defined in the Azure portal. Whether offline/online configuration exists and can be acquired. Whether the rules configured are valid.  The Start-ScannerDiagnostics command does not perform a comprehensive check of prerequisites. If you encounter problems with the scanner, you need to verify that your system meets the scanner's requirements, and that your scanner's configuration and installation are finished.  Verify Scanning Details Per Scanner Node and Repository Run the Get-ScanSt...
Read more

Azure AI Search plugin in Microsoft Security Copilot (Preview)

By Ashwin Venugopal -
Image
  Introduction Azure AI Search is a service that allows to reliably extract content search, extract, and understand at scale. It is typically used to search for documents, data surveys, and chat-style Copilot apps over proprietary data. Indexing and querying are Azure AI Search's two main workloads. While querying allows to search the content from index, indexing loads the content into the search engine and makes it searchable. By connecting to one of the Azure AI Search indexes from within Copilot, the Microsoft Security Copilot integration for Azure enables to use the content in Copilot to produce contextualized, pertinent, and targeted responses.  Requirement Before using the Azure AI Search plugin in Copilot, the desired Azure AI Search index to connect to Copilot is configured as follows: The text field must be searchable.  The title field must be filterable. The vector-field must use text-embedding-ada-002. Integrated vectorization can be used to setup an index in t...
Read more