Weaviate
Weaviate is a vector database platform built for semantic search and AI-driven retrieval. It supports organizing content into collections/classes, storing vector embeddings alongside structured data, and querying with meaning—not just keywords. Weaviate is widely used for building RAG (retrieval-augmented generation) systems because it helps teams keep their knowledge organized, improve search relevance, and reduce retrieval errors over time.
Connect Weaviate so BOBs can continuously inspect and refine how your vector database is structured—turning schema management into an ongoing, low-effort job. Instead of manual cleanup, BOBs can pull the current schema, decide what needs restructuring based on your business knowledge needs, and apply changes so your AI retrieval stays accurate as your data evolves.
This unlocks use cases like maintaining consistent class naming and structure across environments, preparing a clean schema before new knowledge is ingested, removing outdated or duplicate classes, and proactively reducing retrieval mistakes that come from messy or mismatched classes. With a better-organized vector store, your downstream AI can run more reliable semantic search and RAG workflows across support, sales, internal docs, and other knowledge-heavy operations.
What can BOBs do with Weaviate?
Perform actions
- Create Class
- Delete Class
- Get Schema
- List Class ID Options