Booking.com Scales Vector Search With Weaviate For Daily Messaging And RAG

Vector search looks easy, until you hit massive scale! I am super excited to share a new episode of the Weaviate Podcast with Başak Eskili from @bookingcom on production-scale vector search, RAG, and agentic AI with @weaviate_io! 🎙️💚 The podcast begins by discussing Booking's tipping point into adopting vector search and emerging use cases. 🚀 The scale of Partner-to-Guest messaging alone is insane! There are nearly 250,000 such exchanges *daily*, and Booking's Agent is already helping with 10s of thousands of these! 🤖💬 Başak describes how the team navigated increasing scale and workload complexity. They ran an exhaustive evaluation of Weaviate with 100M embeddings and tests often left out of common ANN benchmarks. This includes Filtered Vector Search, Multi-Threaded Concurrency, and testing with simultaneous Reads and Writes. 🎛️ The podcast concludes with Başak's career journey to Booking and her thoughts on Travel Agents! 🧳 This is an awesome one. I'm extremely proud of the Weaviate team for this success, and very grateful to Başak for sharing this story on the podcast. 💚 Links below! 👇