AI-powered Vector Search Engine Weaviate
summary
Weaviate is an open source, cloud‑native vector search engine from SeMI Technologies that stores objects as vectors, serves CRUD over REST and GraphQL, and runs modular inference services (containerized) to vectorize text or images. Live demos use a news dataset of a few thousand articles, show nearText filter searches ranked by nearest neighbor, and expose scores like 87% certainty. Built modules include BERT (Hugging Face) for text, ResNet50 for images, QA and NER, and it scales to millions of objects with horizontal scaling coming soon.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 2:44Unstructured Data
- 11:20Demo
- 17:12Scalar Search
- 19:12Graph Connections
- 21:12Modular Architecture
- 23:26Named Entity Recognition
- 27:50Module System
- 33:10Open Source
related talks
23mWeaviate Vector Search Engine – Introduction
24mIntroduction to Vector Search with Weaviate
13mSearch through your data with Weaviate
31mBuild your own search application with Weaviate
11mLightning Talk: Weaviate Vector Search Engine - Enhancing Cybersecurity
27mUsing Weaviate for building Generative AI apps
45mA gentle introduction to Vector Databases
50mWhat Comes After ChatGPT? Vector Databases - the Simple & Powerful Future of ML?