To harness the powerful capabilities of Concept Search in HawkSearch, a structured process needs to be followed. This process ensures that the feature is not only enabled correctly but also configured to meet your specific search needs.

Here’s a step-by-step instruction:

Feature Activation

The Concept Search feature must first be enabled by our internal personnel. To initiate this process, please contact the our CSD team through email or fill out the interest form within the workbench. They will work with you to activate the feature on your behalf, ensuring a smooth and efficient setup.

Configure Fields for Concept Search

Once the Concept Search feature is enabled, the next step is to set up the specific field for concept search functionality. This process requires identifying and selecting the text field within your index that contains textual descriptions essential for creating search embeddings. Please note that the system imposes a limit of 512 tokens for configuring Concept Search embeddings. Therefore, it is crucial to choose the fields containing meaningful content to ensure the optimal performance of Concept Search. For comprehensive guidance and best practice on completing the configuration, please refer to this detailed article.

Perform a Full Index Rebuild

After configuring the fields, a crucial step is to rebuild the full index. This process allows the system to create the necessary embeddings for the configured field, ensuring that the Concept Search can function as intended. Rebuilding the full index integrates all the setup changes and prepares the system for executing concept searches. Please note that this process involves creating a new index and updating all related components, as detailed in the provided documentation.

Making Concept Search Requests

With the feature enabled, fields configured, and the full index rebuilt, your are now ready to utilize Concept Search! This allows users to benefit from enhanced search results that understand the context and semantics of their queries, leading to more accurate and relevant search outcomes.

Example Request:

{
    "ClientGuid": "xxxxx",
    "RequestType":"ConceptSearch",
    "kValue":3,
    "Keyword": "Show me products that are good for cooking on a hiking trip"
}

By following these steps, you can unlock the full potential of Concept Search, significantly improving the search experience on your platform. Concept Search not only makes your search more intelligent but also ensures that users find exactly what they’re looking for. For more technical details regarding the concept search request, please refer to this article or check out the API reference.