Joon-Pil Hwang
Weaviate
- Introduction to vector databases & Weaviate
- Overview of vector embeddings
- How to find the right data - keyword (BM25), vector and hybrid searches + filtering
- Motivation for retrieval augmented generation (RAG)
- Hands-on
- Set up Weaviate & perform data ingestion
- Perform searches & RAG
- Vector databases in depth
- Indexing techniques to speed up search (HNSW & inverted indexes)
- Improving efficiency with quantization / encoding techniques
- Working with embedding models & LLMs, using Weaviate
- Architectural considerations (multi-tenancy implementations)
- Hands-on
- Work with larger datasets
- Try different embedding/language models
- Build a multi-tenant database
- Next steps with a vector database
- Multi-modal data and Weaviate
- Building an agentic workflow with Weaviate
- Introduction to Weaviate Agents
- Hands-on:
- Work with multi-modal embeddings
- Convenient interactions with Weaviate agents