Company
X5 Tech
10 cases from X5 Tech (Retail, General, Adtech), each digested from a public talk or engineering post and linked to the original. 1 was checked in an online A/B test; 5 report results in production.
Tasks: Retrieve and rank from millions of items, Build a data platform, Build an assistant over internal docs, Recommend to new users and new items, Reduce ML cost and 4 more. Methods: RAG, Cross-encoder reranking, BM25, A/B/n test, Learning to rank, Two-stage recommender and 36 more. Tools: Apache Kafka, Redis, NVIDIA Triton, Grafana, GitLab, Kubernetes and 51 more.
A Reranker in Retail: Turning Advertising into Recommendations![]() | ![]() | retail | 2026-05 |
A Speech Platform in Production![]() | ![]() | retail | 2026-05 |
An Authorization Model in a Lakehouse Without Downtime![]() | ![]() | retail | 2026-05 |
ABsalute: A/B Testing Automation![]() | ![]() | retail | 2026-05 |
Fast MVPs: Prototyping AI Agent Use Cases![]() | ![]() | retail | 2026-05 |
Real-Time Analytics on ClickHouse![]() | ![]() | retail | 2026-05 |
Building RAG Systems That Work Accurately: From Prototype to Thousands of Users a Day![]() | ![]() | retail | 2026-05 |
Embedders 2025: A New Vector in Text Representation![]() | ![]() | retail | 2025-05 |
RAG Tricks: Practical Steps for Corporate Document RAG![]() | ![]() | general | 2024-05 |
Bootstrapping Time Series![]() | ![]() | general | 2023-05 |
