Introduction to Vector Search with Weaviate
summary
Claims that Weaviate runs as an open-source vector DB that stores objects plus embeddings, exposes REST/GraphQL CRUD, and scales with HNSW approximate nearest neighbor indexing. Live demos show a fast 3,500-article demo and a full English Wikipedia index (~25 million pages, paragraphs indexed) with semantic search, QA that extracts the “TV tower” answer, and a multimodal image+text pipeline using models from Hugging Face/OpenAI or custom encoders run in a container.
AI-written summary · about
chapters (10)
- 0:00Start
- 2:03How To Build a Rest Api and Programming Languages for Data Scientists
- 2:47Machine Learning Models
- 3:58Use Machine Learning To Understand the Context of Data on Structured Data
- 7:44Full-Time Crowd Support
- 8:37What Is a Vector Database
- 13:13Basic Search Pipeline
- 15:49User Interface
- 17:09Near-Text Search
- 23:05Hiring
related talks
31mBuild your own search application with Weaviate
23mWeaviate Vector Search Engine – Introduction
38mAI-powered Vector Search Engine Weaviate
13mSearch through your data with Weaviate
27mUsing Weaviate for building Generative AI apps
45mA gentle introduction to Vector Databases
11mLightning Talk: Weaviate Vector Search Engine - Enhancing Cybersecurity
50mA fun and absurd introduction to Vector Databases