​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:

​How not to get lost: Detailed instructions TBD

We enjoy experimenting with the meetup's format, and are inspired by you & your feedback!
This time, we'll try gathering from you any search-related questions & posting answers to the top-X of them post-meetup, next time we could try something else, feel free to propose ideas!

​Agenda

​18:00 — Doors Open;
18:10 - 18:30 — Welcome Keynote (Evgeniya Sukhodolskaya, CSEE speaker);
18:30 - 19:00 — "Old problems, new contexts: finding the right context by fast-forwarding 20 years of search" (David Louis Hollembaek, Veeva Systems)
19:00 - 19:10 — Break
19:10 - 19:40 — "Retrieval for every occasion: combining knowledge graphs and vector search" (Hande Kafkas, cognee)
19:40 - 20:10 — "Search results diversification" (Peter Straßer, Elastic)
20:10 - 20:15 — Closing Note (Daniel Wrigley)
20:15 - 21:00 — Networking with drinks & pizza sponsored by Qdrant:)

​Talk Descriptions:

​Talk 1: Old problems, new contexts: find the right context quickly by fast-forwarding on 20 years of search development
Speaker: David Louis Hollembaek (Veeva Systems)
Abstract: The challenges of building effective AI systems today echo the early days of web search, where a common problem was frequently underestimated: getting the context right. Let's step back to look at how the context problem was approached in the past, then skip ahead to using modern tools.

Talk 2: Retrieval for every occasion: combining knowledge graphs and vector search
Speaker: Hande Kafkas (cognee)
Abstract: We'll explore how agentic AI systems use distinct memory retrieval patterns to build context-aware applications that span from vector search to knowledge graph reasoning. We'll walk through how traditional RAG compares to graph-based cognitive architectures wrt search, and why chain-of-thought reasoning might be overkill for your workflows.
Expect hands-on demonstrations using open-source tools, where we'll show how different search types impact the result, helping you build more reliable AI applications.

​Talk 3: Search results diversification
Speaker: Peter Straßer (Elastic)
Abstract: In search, our goal is to bring the most relevant results to the top. But what happens when the best results are all nearly identical?
This talk dives into why you should sometimes prefer diversity over pure relevance. We’ll explore methods to achieve this balance and how you can bring these techniques to your own applications.

​Venue

​We're hosted this time by the Center for Software Engineering Excellence (CSEE) - Munich’s talent hub for ambitious builders, a student-led organization at TUM connecting academia, industry, and tech communities through hands-on projects and events