DBTB INT Samiur Rahman r
summary
Claim that a custom semantic search for millions of documents often outperforms using Elasticsearch out of the box, with examples of what was built at Mattermark and why relevance improved; practical notes on engineering tradeoffs and deployment challenges for production search; concrete recommendation to prioritize core skills — linear algebra and convex optimization — plus software engineering for shipping models; brief pointers to evaluation metrics and when to prefer off‑the‑shelf vs bespoke systems.
AI-written summary · about
related talks
40mLevel Up: Everything you need to know about search, ...
47mWhy, What, When and How of Running Diff Types of Sear...
37mSearch and Recommendations: 3 Sides of the Same Coin #bbuzz
01h 09mVector Search: Ask Me Anything!
32mRetrieval Augmentation and Semantic Search at Scale
13mA Beginner’s Guide to Semantic Search
33mA Practical Approach To Semantic Search
30mSearch on Steroids — A Story of Semantics