The use case: how Booking.com deploys Weaviate
Booking.com's Machine Learning & Data Science team uses Weaviate as the backend of its centralized embedding service, which provides vector search and data management for machine learning, agentic, and GenAI projects across the company. It replaced OpenSearch.
More reported results
Figures published in Weaviate’s case study. They are not independently measured by usedby.
Weaviate outperformed OpenSearch by 20x in the benchmark, with a 40x reduction in usage cost.
Booking.com built a performance benchmark that closely resembled its production workloads: 100 million embeddings, increasing concurrent threads, and nearest-neighbor, filtered KNN, and mixed read/write queries.
In the customer’s words
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.Other AI tools used by Booking.com
Other public relationships recorded on usedby.
Arize AIConfirmed
GleanConfirmed
H2O.aiConfirmed
HoneycombConfirmed
ServiceNowConfirmed
SourcegraphConfirmedOther companies using Weaviate
Customers across industries, with public evidence.
DeleganceConfirmed
DocsBotConfirmed
Loti AIConfirmed
MarvelXConfirmed
MorningstarConfirmedGo straight to the source
Based on Weaviate’s published case study. We check the public evidence; the results are reported by the vendor.
weaviate.io- Last checked
- Nov 4, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 40%Checked
Printed word for word on the page, near the name of Booking.com.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Booking.com.
- Booking.com uses WeaviateChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
In benchmark tests based on actual production workloads, Weaviate outperformed OpenSearch by 20x at scale and with 40% lower operational costs.
