Embedding Search (Index)

This page is the entry point to NornicDB's embedding and vector-search documentation.

Start here

• Embedding Search Overview — overview + key concepts.
• Embedding & Search Architecture — data model + execution paths.
• Embedding & Search Flow Diagrams — Mermaid diagrams.
• Embedding & Search Examples — end-to-end examples.

User-facing guides

• Vector Embeddings — embedding generation.
• Vector Search — hybrid search and RRF usage.
• Qdrant gRPC — Qdrant compatibility layer.

Agent-ready skills

• Managed Embeddings — WITH EMBEDDING, db.index.vector.embed, provider config.
• Vector & Full-Text Search — CREATE/DROP VECTOR INDEX, db.index.vector.queryNodes.
• RAG Procedures — db.retrieve, db.rerank, db.infer.
• gRPC (Qdrant + NornicSearch) — gRPC surface for vector ingestion and hybrid search.

Implementation references

• pkg/search/search.go — unified search service + vector pipeline selection.
• pkg/qdrantgrpc/points_service.go — Qdrant Points API mapping.