​Meetup Description:

​Search is evolving fast. From new algorithms and tools to AI-driven solutions, the field is constantly shifting. BASED Meetup is where professionals & enthusiasts discuss the latest trends, breakthroughs and challenges in modern search.

​We dive into topics like:
- Agentic Retrieval-Augmented Generation (RAG);
- Innovative approaches to sparse, dense, and hybrid retrieval;
- Advances in indexing algorithms and vector quantization;
- Modern metrics for search quality;
- Optimization techniques for production-scale systems;
- Cross-lingual and multimodal search challenges;
- The intersection of search and generative AI;
… and much more.

​No sales pitches, no gatekeeping — just an open space to share ideas, learn from each other, and explore the technologies shaping the future of search.

​Whether you're building production systems, researching search algorithms, or just curious about the field, you're welcome here.

​Meetup Info:

​This is the 1st Meetup in the series. Next time, we hope to host your talks, too!:)

​Location:

​The place is located on the 5th floor of the building; ring the bell on the ground floor to get in.

​Agenda

​18:00 — Doors Open;
18:15 - 18:35 — Welcome Keynote (Evgeniya Sukhodolskaya & Daniel Wrigley, AutoScout24);
18:35 - 19:15 — "Dynamic Hybrid Search Optimization: A Practical Framework for Query Understanding" (Daniel Wrigley);
19:15 - 19:30 — Break;
19:30 - 20:10 — "PDF Retrieval at Scale with Vision Language Models" (Evgeniya Sukhodolskaya);
20:10 - 21:00 — Networking with Drinks & Pizza:)

​Talks Description:

​Talk 1: Dynamic Hybrid Search Optimization: A Practical Framework for Query Understanding
Speaker: Daniel Wrigley (OpenSource Connections)
Abstract: In hybrid search systems, balancing lexical and neural search techniques is critical for achieving optimal relevance. This talk introduces a systematic framework for dynamic hybrid search optimization, which predicts the "neuralness" of a query to dynamically configure search parameters at runtime. Leveraging query understanding and machine learning models trained on engineered features from query structure and search results, the approach demonstrates significant improvements in DCG, NDCG, and precision metrics in an e-commerce setting. Attendees will learn how to replicate the methodology, including feature engineering, model training, and production considerations. This method provides actionable insights for search practitioners aiming to optimize relevance in OpenSearch or similar search systems.

​Talk 2: PDF Retrieval at Scale with Visual Language Models
Speaker: Evgeniya Sukhodolskaya (Qdrant)
Abstract: Discover how Visual Language Models like ColPali and ColQwen unlock new possibilities in PDF retrieval. We will explore how these models handle complex layouts, tables, and visual elements — no OCR & no nightmares related to complex document parsing. You'll learn the theoretical advantages of these approaches & see practical techniques for optimizing their usage — essential for handling large-scale PDF document collections.
Join me for a deep dive into the next generation of PDF retrieval, from core model principles to scalable production workflows with Retrieval Augmented Generation (RAG).