Azure AI Search plugin in Microsoft Security Copilot (Preview)

By Ashwin Venugopal -

 





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 the required way and following steps are required to get an index ready for integration into Copilot. 

Connect Azure AI Search to Copilot

To create the connection:
  1. Open Copilot, after ensuring authentication.
  2. Select the Copilot sources icon in the prompt bar.
  3. Go to Microsoft > Azure AI search and choose Set up.
  4. In Azure AI Search settings, enter the following information in the corresponding field-
    1. Azure AI Search instance- the name of search instance.
    2. Index- the name of the index within the instance to search.
    3. Vector- the name of the field label in the index containing the vector of embeddings.
    4. Text- the name of the field label in the index containing the text to search.
    5. Title- the title of each document to display as a source.
    6. Value- the API key for authentication.

The information needed for the plugin setup is available on Azure AI Search page in the Azure portal.  

      5. Select Save to complete the setup.                                                                        
      6. Close the Azure AI Search settings window. 

Although it is well-suited for knowledge-based scenarios, this plugin is not limited to them. Apps like Copilot are able to search through and retrieve information from vast amounts of data and content thanks to Azure AI Search's indexing and vectorizing capabilities. 

Limitations

  • Only one index at a time can be connected using the plugin. To query a different index, update the plugin settings.
  • The plugin supports hybrid search (keyword and vector search), so it can only support queries on indexes that were configured according to the required settings in Requirements.
  • To invoke the plugin, explicitly mention "Azure AI Search" in the prompt.
  • Copilot displays the titles of the referenced documents from the index, but they aren't hyperlinked. 

Conclusion

The information about Azure AI Search plugin and its limitations is in-short explained here. 















Comments

Post a Comment

Popular posts from this blog

Deployment (Part 3)

By Ashwin Venugopal -
Image
  To read part 1, please click  here To read part 2, please click  here Microsoft Monitoring Agent (MMA) MMA is used across multiple Microsoft solutions and has undergone a few name changes as its features and functionality have evolved. If it is being considered to be used, then following areas should be covered during a Microsoft Sentinel deployment project: Consider the timelines and the strategy for a migration to AMA (Azure Monitor Agent) before the MMA end-of-life.  Consider the central deployment and management methodology for MMA. Determine which endpoints are in scope for deployment as these affect the log ingestion volume significantly.  Azure Monitor Agent (AMA) Organizations with MMA as the main Microsoft Sentinel agent should start planning the migration to AMA as soon as possible to avoid a rushed migration. One of the main advantages of AMA is the ability to control the log collection policy centrally and apply different policies against different...
Read more

Deployment (Part 1)

By Ashwin Venugopal -
Image
  To read part 2, please click  here To read part 3, please click  here Azure Resources Microsoft Sentinel needs following resources to be created: Subscription (if a dedicated subscription(s) will be used) Resource group(s) Log Analytics workspace(s) Automation rules/playbook Alert rules Workbooks Microsoft Sentinel offers hundreds of alert rules, workbooks, and automation playbook templates along with hunting scripts. The templates can be used to activate/deploy schedule alerts, create customized dashboards, create automation playbooks and perform threat-hunting activities. Generally, once deployed, the resources created have to be adjusted to match the existing environment, configure local credentials, etc. Methods of deployment: Manual- Administrator can manually configures the Microsoft Sentinel resources with the help of Azure portal. Any manual process has the inherent risks of human operator error, lack of compliance with potential change control procedures, and u...
Read more

Deployment (Part 2)

By Ashwin Venugopal -
Image
  To read part 1, please click  here To read part 3, please click  here Microsoft Sentinel Content Hub Content in Microsoft Sentinel includes any of the following types: Data connectors offer log ingestion from different sources into Microsoft Sentinel. Parsers give log formatting/transformation into ASIM formats, supporting usage across various Microsoft Sentinel content types and scenarios. Workbooks provide monitoring, visualization, and interactively with data in Microsoft Sentinel, highlighting meaningful insights for users.  Analytics rules give alerts that point to relevant SOC actions via incidents.  Hunting Queries are used by SOC teams to proactively hunt for threats in Microsoft Sentinel. Notebooks help SOC teams in using advanced hunting features in Jupyter and Azure Notebooks. Watchlists support the ingestion of specific data for enhanced threat detection and reduced alert fatigue.  Playbooks and Azure Logic Apps Custom Connectors provide featu...
Read more