Azure Portal

By Ashwin Venugopal -

 




Debug Search Issues Using Azure Portal

When you initially set up your search service, you need to establish certain assumptions regarding the data you will be indexing. You decide on the structure of the index and the method for ingesting that data. Yet, you won't be able to confirm whether all your decisions were correct until you execute your built indexer.

Explore How To Use Debug Session Tool In Azure AI Search

The Debug Session tool is an interactive visual editor that allows you to navigate through the enrichment pipeline of a document during its enrichment process. You can enter each specific skill, apply modifications and corrections, and then execute the indexer in real-time. After addressing any problems, you can refresh and republish the indexer so it can be re-executed to enrich all documents within your index.

Once you have assigned a name to your debug session and selected the index for debugging, the search service transfers all necessary components to an Azure Storage account. This transfer encompasses the skillset, indexer, source data, and a processed version of the document that resides in the final index.

A skill graph, an enriched data source, a skill detail pane, an execution pane, and an errors/warnings pane comprise the session. You can extend an expression evaluator in the skill detail pane to verify the value and test the inputs and outputs.

Debug a Skillset With Debug Sessions

To create a Debug Session, you navigate to your search service in the Azure portal and carry out these steps:

Create a Debug Session

  1. Select Debug Sessions under Search management in the Overview pane.
  2. Select + Add Debug Session.
  3. In Debug session name, provide a name that will help you remember which skillset, indexer, and data source the debug session is about.
  4. In Storage connection string, find a general-purpose storage account for caching the debug session.
  5. In Indexer template, select the indexer that drives the skillset you want to debug. Copies of both the indexer and skillset are used to initialize the session.
  6. In Document to debug, choose the first document in the index or select a specific document.
  7. Select Save Session to get started.

Explore and Edit a Skill

You can examine how a document is enhanced as it moves through each AI skill in your Debug Session. You can choose a talent, examine its inputs and outputs, and even inspect its JSON definition.

  1. In the dependency graph, select a skill.
  2. In the details pane to the right, select the Executions tab, then in OUTPUTS, open the Expression evaluator by selecting next to organizations.
  3. To edit the skill, select the Skill Settings tab.
  4. Make any changes to the JSON of the skill, then select Save.
  5. To test that the changes have fixed your issue, select Run.
  6. If the issue is now resolved and you want to publish the changes, at the top of the pane select Commit changes.
  7. To finish the debugging session, select Save Session.

Validate Field Mappings

If your input data doesn't exactly fit the target index's schema, indexers can be changed. During the indexing process, use field mappings to restructure and correct this mismatch in your data.

  1. Select Skill Graph, and check that Dependency graph is selected.
  2. Select the second step in the enrichment pipeline, Field Mappings.
  3. Make any changes to where data should be mapped to.
  4. Select Save.
  5. Select the last step, Output Field Mappings.
  6. Output field mappings from the skills can be fixed in the detail pane.
  7. Select Save.
  8. To test that the changes have fixed your issue, select Run.
  9. If the issue is now resolved and you want to publish the changes, at the top of the pane select Commit changes.

Conclusion

We have successfully learnt about debugging the search issues using Azure Portal.










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