Tool
OpenSearch
12 cases from 11 companies use OpenSearch in their stack. 2 were checked in an online A/B test; 4 report results in production. Tasks: Rank search results, Build an assistant over internal docs, Answer questions over data, Retrieve and rank from millions of items and 4 more. Methods: RAG, Vector / semantic search, Cross-encoder reranking, Query rewriting / decomposition, BM25 and 41 more. Companies: Pinterest, Atlassian, LY Corporation, Raiffeisenbank, Alfa-Bank, SberDevices and 5 more.
| Unified Context-Intent Embeddings for Scalable Text-to-SQL | social | 2026-03 | |
| Unraveling Rovo search relevance | saas-b2b | 2025-08 | |
Introducing a RAG-based bot to streamline CS![]() | ![]() | social | 2025-06 |
| Make Retrieval Smarter: How We Built Smart Search over a Document Base | general | 2025-05 | |
| From Chaos to Control: Building a Streamlit Tracer for Debugging RAG Systems | general | 2025-05 | |
| Applying NLP Models to Automate Call Center Work | banking | 2024-05 | |
GigaSearch, or a Search System on GigaChat![]() | ![]() | search-engine | 2024-05 |
| How We Got RAG Running in Production | general | 2024-05 | |
Data Quality as part of the Data Catalog at SIBUR. Experience implementing the practice in a large organization![]() | ![]() | general | 2024-05 |
| How we built Text-to-SQL at Pinterest | social | 2024-04 | |
| When a picture is worth more than words | travel | 2022-12 | |
| Search Pipeline: Part II | general | 2022-11 |


