AI/ML Distributed Database Use Cases

Real-Time AI at Scale Masterclass

ScyllaDB Vector Search: Examples and Tutorials

Inside Tripadvisor’s Real-Time Personalization with ScyllaDB + AWS

See the engineering behind real-time personalization at Tripadvisor’s massive (and rapidly growing) scale

How ShareChat Scaled their ML Feature Store 1000X without Scaling the Database

How ShareChat successfully scaled 1000X without scaling the underlying database (ScyllaDB)

Using ScyllaDB to Implement Lists in Medium’s Feature Store

Discover how Medium is leveraging ScyllaDB to power a fast, scalable data layer for lists in Medium’s feature store.

Using ScyllaDB for Medium's Feature Store

Learn how Medium is using ScyllaDB to build a fast and scalable data layer for lists in their feature store.

Vector Search with ScyllaDB

How Agoda Scaled 50x Throughput with ScyllaDB

Feature Store Evolution Under Cost Constraints: When Cost is Part of the Architecture

The Harsh Reality of Building a Real-Time ML Feature Platform

Efficient Deduplication in RecSys at Scale: How We Managed to Reduce Server Cost by 90%

Efficient deduplication is key to delivering relevant recommendations at scale. Andrei shares how they optimized for 300M+ users, cutting costs by 90% while reducing latency. He covers how ScyllaDB, A

Build Real-Time ML Apps with Python, Feast & NoSQL

Tutorial: Build a Machine Learning Feature Store

This tutorial walks you through a sample feature store application with ScyllaDB Cloud.

How Agoda Scaled Its Feature Store 50X

Lessons learned on data modeling, cache optimization, and hardware selection

How ShareChat Cut Recommendation Engine Costs 90%, Step by Step

From managed Google Cloud services to ScyllaDB, Redpanda, Flink, and beyond

From Batch to Real-Time: How MoEngage Achieved Millisecond Personalization with ScyllaDB

How a leading customer engagement platform handles 250K writes per second at 1ms p99 latency with 200TB+ data

ScyllaDB Vector Search: 1B Vectors with 2ms P99s and 250K QPS Throughput

Results from a benchmark using the yandex-deep_1b dataset, which contains 1 billion vectors of 96 dimensions

Building a Low-Latency Vector Search Engine for ScyllaDB

ScyllaDB Vector Search is now available. Learn about the design decisions, testing, and optimizations involved in achieving our performance goals.