How Booking.com uses Weaviate
40%
“Weaviate outperformed OpenSearch by 20x at scale and with 40% lower operational costs”
As published on weaviate.io. Captured by usedby on Oct 2, 2026.
What happened
Booking.com's Machine Learning & Data Science team uses Weaviate as the backend of a centralized embedding service that provides vector search and data management for machine learning, agentic, and GenAI projects across the company. It replaced OpenSearch as the vector store.
Summary written by usedby from the source page, in English. The figures are those of Weaviate and Booking.com, not ours.
- 20x“Weaviate outperformed OpenSearch by 20x in the benchmark, with a 40x reduction in usage cost.”
In benchmark tests based on actual production workloads, Weaviate outperformed OpenSearch by 20x at scale and with 40% lower operational costs.
Our evaluation confirmed that systems built specifically for vector search behave better than general-purpose search engines with vector capabilities added on. Among the evaluated options, Weaviate showed the most consistent performance across our scenarios, so we selected it as the new backend for our shared embedding services platform.
What the story claims, and what we checked
We compared the story with its live page on Oct 3, 2026.
- The figure: 40%CheckedPrinted word for word on the page, near the name of Booking.com.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Booking.com.
- Booking.com uses WeaviateCheckedConfirmed line. Latest check across sources: Oct 2, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.
More stories
Same company, same tool or same industry.
