Hawk AI Overview
High level descriptions of each feature
Visual Search
All images are converted to vectors to support image upload or taking a picture, as well as describing an image. This feature image to text description features is also used in the unified search.
Concept Search
All descriptions, names and other relevant meta data are converted to a vector as well using an embedding model. The search phrase, sentence or “concept” when entered into the search bar, is converted to a vector as well and matched to the best result. This feature is also referred to as “Natural Language Processing”
Unified Search
The unified search bar combines the best results from keyword, concept and image search and then sorts them by relevancy.
Smart Response
When the appropriate content is returned, it is then run through a prompt that explains to only answer the question with the content in the index that was returned and then provide the appropriate response to the question. If the question can not be handled by the Smart Response process with a high enough level of confidence, then no response is provided.