The AI capability 'In app search' works by utilizing advanced technologies to deliver accurate and relevant search results for companies in the shaping of stone industry. Here's how it works:
Use case 1
Embeddings generation - Each ticket, knowledge base article, and scraped website related to shaping of stone is sent to the OpenAI Embeddings API to generate embeddings vectors. These vectors capture the semantic meaning of the data.
Use case 2
Vector database - The generated embeddings vectors are stored in a vector database, allowing for efficient and fast retrieval of relevant data during searches.
Use case 3
Query processing - When a search query is entered through the search bar, it is compared against the embeddings vectors using the OpenAI Embeddings API. The system then searches through the stored data for similar and relevant information.
Use case 4
Use case 4: AI-powered response - The relevant data is then passed to ChatGPT along with the original question. ChatGPT uses the attached data to provide a human-like response, which is presented to the user as a search response or a suggested reply for support agents.
