Search through your data with Weaviate
summary
Live demo shows Weaviate ingesting a news corpus, vectorizing text (and images) with built‑in models, and serving vectorized semantic search plus filters via GraphQL API and REST clients (Python/Go/Java/JS). Queries return relevant articles that have a 0% keyword match to the query yet high semantic relevance, support on‑the‑fly classification and extractive answers, and produce summaries. The demo combines vector nearest‑neighbour lookup with structured filters and it visibly surfaces the intended results.
AI-written summary · about
chapters (9)
- 0:00Welcome to Weaviate
- 1:57How search engines work
- 3:02Vector search and ML models
- 4:48Vector search with filters
- 6:13Demo: Semantic search with filters
- 8:38Demo: Concrete vs abstract results
- 10:21Demo: Q&A with filters
- 11:45Summary and use cases
- 12:05Closing and open-source invite
related talks
38mAI-powered Vector Search Engine Weaviate
23mWeaviate Vector Search Engine – Introduction
31mBuild your own search application with Weaviate
24mIntroduction to Vector Search 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?