Tool
GigaChat
13 cases from 8 companies use GigaChat in their stack. 1 was checked in an online A/B test; 2 report results in production. Tasks: Build an assistant over internal docs, Rank search results, Evaluate models, Label data with LLMs. Methods: RAG, BM25, Cross-encoder reranking, Supervised fine-tuning, Hybrid search and 37 more. Companies: Sber, Rabota.ru, HSE University, SberDevices and 4 more.
| The Search of the Future | general | 2026-05 | |
| Building a Coffee Recommender System with LLM and RAG | retail | 2026-05 | |
| Graphs and Agents in Action: Building a CoPilot for All Sber Branches | banking | 2025-05 | |
| AI in Education: HSE University Case Studies | edtech | 2025-05 | |
| AI Sales Agents: Architecture, Bottlenecks and the Evolution of Capabilities | saas-b2b | 2025-05 | |
BERTScore for the Russian Language![]() | ![]() | general | 2024-11 |
| Advanced Use of GigaChat at Rabota.ru: Synthetic Data and Search | classifieds | 2024-05 | |
GigaSearch, or a Search System on GigaChat![]() | ![]() | search-engine | 2024-05 |
| Advanced application of GigaChat at Rabota.ru. Recommendations and auto-moderation | classifieds | 2024-05 | |
| How We Got RAG Running in Production | general | 2024-05 | |
| Review and Adaptation of RAG Evaluation Tools for the Russian Language | insurance | 2024-05 | |
Building a Playlist You Will Like![]() | ![]() | media-streaming | 2024-05 |
Application of LLM models in disease diagnosis: strategies and prospects![]() | ![]() | healthtech | 2024-05 |



