Utilizing Azure OpenAI entity extraction for search queries

The Azure OpenAI Entity Extraction tuning stage use large language models at query time to identify and extract meaningful entities from a user’s search query, such as people, organizations, products, or topics. By running as tuning stages, entity extraction dynamically influences how SmartHub interprets the query and shapes the resulting search behavior, improving relevance and intent recognition without modifying indexed content or requiring re-indexing.

Prerequisites

Note the following prerequisites before configuring the AI Visual Interpreter component:

Configure the component

  1. In the AutoClassifier administration portal, Add a new component to a new or existing pipeline.

  2. When adding your component, select Azure OpenAI Knowledge Graph Entity Extractor from the New Component list and provide a name for your component.

  3. Click Add Component.

  4. Select your Azure OpenAI Knowledge Graph Entity Extractor component from the list.

  5. In the Deployment URL field, enter the deployment url of your Azure OpenAI service resource. To find your Deployment URL, in Azure AI Studio, click Deployments from the left panel, then click on your deployed resource. On your deployed resource page, copy the Target URI value in the Endpoint section.

    You must include the API version in the endpoint URL. Upland BA Insight recommends copying the URL from Azure AI Studio as the API version is included.

  6. In the Api Key field, enter the Api key for your Azure OpenAI service resource. To find your Api key, in the Azure Portal, click on your Azure OpenAI service resource. In the left panel, click Keys and Endpoint and copy the value in the KEY field.

  7. In the Prompt field, define the instructions that guide the AI model on how to identify and extract entities from content using the selected ontology. Use this field to control what the model looks for and how entities should be interpreted during extraction.

  8. In the Ontology field, specify the entity types and relationships that you wish to extract. This ensures that both document content and user queries are analyzed using the same structured knowledge model. For more information, refer to the entity extractor ontology use cases and examples

  9. In the Input Property field, Specify the metadata field that will be analyzed for entity extraction. This determines which portion of the document (for example, body text or metadata) is used to populate the Knowledge Graph. If you are combining this component with the document chunker, you can use the chunk body property name.

  10. In the Max character Limit field, specify the maximum number of characters from the input property that will be sent to the AI model for entity extraction.

  11. Click Save.