Open-Source Spotlight - Qdrant - Kacper Łukawski

Qdrant: a vector similarity search engine with extended filtering support 00:00 Intro and a few words about Qdrant 01:11 Qdrant stack 02:12 Demo: visual food discovery 03:43 HNSW algorithm 04:34 Unique extended filtering approach 08:09 Using Qdrant in Data Science projects 10:17 How are the embeddings generated? 13:02 Demo: visual & faceted search 17:00 How to run Qdrant? 18:16 Plans for making the similarity learning easier 18:40 Who works on it? 20:14 The roadmap of Qdrant 21:01 How to contribute to the project? 23:08 Advice: have a look at what similarity learning can offer 24:25 How not to get annoyed with neural search? Links: - Github: https://github.com/qdrant/qdrant - Filterable HNSW: https://blog.vasnetsov.com/posts/categorical-hnsw/ - Food discovery demo: https://food-discovery.qdrant.tech/#/ - H&M demo: https://h-and-m.qdrant.tech/ - H&M source code: https://github.com/qdrant/demo-hnm - Qdrant Helm chart: https://github.com/qdrant/qdrant-helm MLOps Zoomcamp: https://github.com/DataTalksClub/mlops-zoomcamp Join DataTalks.Club: https://datatalks.club/slack.html Our events: https://datatalks.club/events.html