Vector Search
Vector Search lets you query the Vector Catalog with natural language or embeddings to retrieve relevant smart bites. Results support RAG (retrieval-augmented generation), agent grounding, and semantic search over contracts, policies, and other unstructured documents.
Overview
- Run semantic queries (e.g. “What is the refund policy?”) and get ranked chunks.
- Filter by metadata (source, date, document type).
- Use results in your app or pass them to an LLM for grounded answers with source lineage.
Key tasks
| Task | Guide |
|---|---|
| Understand Vector Search | Overview |
| How semantic retrieval works | Semantic retrieval |
| Scope queries with filters | Filtering |
| Improve relevance and recall | Best practices |
Tutorials and concepts
- First vector search — Run your first semantic query.
- Vector Catalog overview — Where search runs.
Related product areas
- Vector Catalog — The store that Vector Search queries.
- Agents — Ground answers using search results.