What are the main use cases for Weaviate?

Weaviate's combination of vector search, keyword search, and structured filtering in one system suits a range of applications that need more than pure semantic similarity alone.

1. Retrieval-augmented generation (RAG) - retrieving grounded context for LLM-powered applications, often via the built-in generative search modules.
2. Semantic and hybrid product/document search - especially where exact terminology (product codes, technical terms) and semantic meaning both matter.
3. Recommendation systems - finding items similar to a user's history or preferences.
4. Multimodal search - combining text and image embeddings (via modules like CLIP) for cross-modal search.
5. Question-answering and conversational AI agents - powered by the Query Agent or custom generative-search integrations.
6. Knowledge management with relationships - using cross-references to model connected data alongside semantic search.

What tends to draw teams to Weaviate specifically, versus a narrower ANN-only library, is exactly this combination: built-in hybrid search, generative integration, and relationship modeling within one system, rather than needing to combine several separate specialized tools to cover the same ground.