Vector Catalog
The Vector Catalog is Bundata’s managed store for vector-ready intelligence: embeddings and indexed smart bites from your extraction and enrichment pipelines. It powers Vector Search (semantic retrieval) and grounded answers for agents, with source lineage and metadata for filtering and citations.
Overview
Ingest smart bites from extraction workflows into collections, run semantic search over collections, filter by metadata (source, date, document type), and use catalog results to ground agent and RAG responses with citable sources.
Key tasks
| Task | Guide |
|---|---|
| Understand the Vector Catalog | Overview |
| Create and manage collections | Collections |
| Track source and quality | Lineage & quality |
Tutorials and concepts
- First vector search — Query the catalog.
- Extraction overview — Where smart bites come from.
Related product areas
- Vector Search — Query the catalog with semantic search.
- Agents — Ground answers using catalog results.