Skip to Content
We are live but in Staging 🎉
VectorOverview

Vector

K3’s vector primitive is a per-bucket vector engine backed by VBase  (managed Milvus). Use it to make objects searchable by what they mean — not just what they’re called.

The engine exposes hybrid retrieval (dense embeddings + sparse BM25 fused via RRF), cross-encoder reranking, and multi-collection search in a single bucket-scoped API. VBase sits underneath — for advanced Milvus features K3 doesn’t surface (custom indexes, partition lifecycle, raw client SDKs), point your engine at your own VBase cluster via the external mode or use VBase’s API directly.

What you can do

  • Two ways to manage a collection: bind to a Scriptum embedding template (K3 chunks + embeds for you) or push pre-embedded vectors directly with your own dimensions / metric / sparse mode.
  • One search RPC, three query shapes: text (server embeds it), pre-embedded vector (fast lane), or file-by-S3-key (multimodal — image / audio / video).
  • Hybrid retrieval: dense + sparse BM25 fused via RRF (k=60), with optional Jina reranking on the top-K.
  • Multi-collection search by leaving collection_name empty — K3 fans the query out across compatible collections (same dimensions + embedding type) and returns merged results with per-collection statuses.
  • Five dense element types (float / binary / float16 / bfloat16 / int8) — pick the right precision-vs-speed for your model.
  • Direct vector writes (InsertVectors / UpsertVectors / DeleteVectors) on EXTERNAL-mode collections — no ingest pipeline needed.

Two collection-creation modes

ModeRPCWho owns the schemaWhen to pick
PipelineAddVectorPipelineScriptum template (*_embedding_index)You’re ingesting unstructured content (PDFs, images, audio) — K3 chunks, embeds, and indexes for you
Manual / externalAddVectorCollectionYou — declare dimensions, metric, sparse mode, embed_modelYou have your own embedding pipeline (third-party models, pre-computed batches) and want to push vectors directly

Engine modes (VBase integration)

The vector Engine has three provisioning modes:

ModeWhat it doesWhen to pick
autoK3 provisions a VBase database for you on a managed clusterDefault — zero setup, K3 handles everything
externalPoint the bucket’s engine at your own VBase clusterYou operate VBase yourself or need direct raw-Milvus access
pickUse an existing VBase service-ID in your orgShared VBase service across multiple K3 buckets

For raw Milvus features K3 doesn’t expose (partition lifecycle, alter collection, custom index types), use VBase’s API directly against the same endpoint — K3 doesn’t lock writes.

In this section

  • Quickstart — configure engine + first collection + first search, 5 minutes
  • Core Concepts — proto-grounded types: Engine, Collection, VectorRecord, Search shapes/modes/filters, Template
  • API Reference — five RPC groups (Engine · Collections · Search · Vectors · Templates) with VBase touchpoints
  • CLI Guidedodil k3 vector store · vector collection · search · vector templates
  • Recipes — pipeline collection (RAG), external collection (BYO embeddings), multi-collection search, hybrid + rerank, multimodal search

See also

  • VBase  — the underlying managed-Milvus product (escape hatch for raw access)
  • Pipelines — what feeds pipeline-mode collections (Scriptum *_embedding_index templates)
  • Object Storage — where the bucket lives + where S3-key file queries point
  • Conventions — auth, headers, error envelope
  • CLI Basics — install + common flags