Case Study: OpenTable achieves accurate, scalable AI restaurant discovery with Qdrant

OpenTable powers AI restaurant discovery for 60,000+ restaurants with Qdrant

OpenTable, a global restaurant reservation platform, recognized that the rise of generative AI was changing how diners discover restaurants. They needed to build a conversational, intelligent assistant named Concierge that could provide accurate, natural language answers. Their challenge was to ensure high answerability and precision, requiring a vector database capable of handling sparse embeddings and heavy filtering across their vast dataset of over 60,000 restaurants.

OpenTable implemented Qdrant Cloud as their vector database. Qdrant provided the necessary capabilities for sparse embeddings and high-precision filtering, which was crucial for the project's performance and latency targets. The solution resulted in a successful global launch of Concierge, which met its latency goals and maintained high answerability without extensive post-launch tuning. Operationally, Qdrant became one of the most stable components in their stack, allowing the team to focus on improving the model and user experience instead of troubleshooting the database.

OpenTable