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

TaskGuide
Understand the Vector CatalogOverview
Create and manage collectionsCollections
Track source and qualityLineage & quality

Tutorials and concepts

  • Vector Search — Query the catalog with semantic search.
  • Agents — Ground answers using catalog results.