The AI capability 'suggested replies' in Deskhero utilizes advanced natural language processing and machine learning algorithms. Here's how it works:
Use case 1
Data analysis and embeddings generation - Deskhero analyzes previous tickets, knowledge base articles, and other relevant data to generate embeddings vectors using OpenAI Embeddings API. These vectors capture the semantic meaning of the text.
Use case 2
Vector database storage - The generated embeddings vectors are stored in a vector database, allowing for efficient and fast retrieval.
Use case 3
AI-powered suggestions - When a new ticket comes in, Deskhero compares the query against the stored embeddings vectors to find similar and relevant data. This data is then passed to ChatGPT, an AI model, along with the original question. ChatGPT generates a response based on the attached data, which is presented as a suggested reply to the agent.
