Self-Managed Vector Index Store

Data storeKnowledge & DataKnowledge & Dataarc:SelfManagedVectorIndexStore

An open-source vector store deployable on-premises, in the team's own cloud, or as a managed offering, holding embeddings plus metadata under a user-defined schema with an HNSW index.

Responsibility. Provides portable vector and hybrid search under the operator's deployment control.

Also known as: Open-source vector search engine

Variant of Vector Index Store abstract

When to choose. Choose when a team comfortable operating infrastructure needs to deploy anywhere (on-premises for data sovereignty, own cloud for cost control) without sacrificing developer experience.

Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

is configured by structural

is read by dependency

Dense-Sparse Hybrid Retriever Ch6.2A

is written by dependency

is monitored by assurance

alternative to variability

Design guidance

MAY be preferred when knowledge-graph integration or out-of-the-box hybrid search is a core requirement, accepting lower raw single-node throughput.
MUST NOT be exposed in production without authentication; anonymous access MUST be disabled.
MUST persist indexed vectors, metadata and graph structures on durable volumes rather than ephemeral container storage.
SHOULD set explicit resource limits and reservations and cap default query result counts to prevent runaway resource use.
SHOULD be clustered with replication across nodes when 99.9%+ uptime is required; single-node deployments are an unacceptable single point of failure.
SHOULD scale beyond three replicated nodes by adding nodes and increasing shard count so data is partitioned, not merely replicated; MAY use heterogeneous nodes and multi-zone/region clusters for disaster recovery.

Quantitative guidance

As stated by the sources; verify before use.

Memory sizing ~1 KB per 768-dim vector with M=16; 10M vectors ~10 GB plus overhead -> 16 GB reservation / 32 GB limit (Ch6.2B).
Example limits 8 CPU / 32 GB, reservations 4 CPU / 16 GB (Ch6.2B).
10M-document collection: pure vector search 15-30 ms, hybrid 25-50 ms for top-10 (Ch6.2B).

Classification

Patterns: HNSW indexHybrid vector + keyword searchFiltered search (ACORN)GraphQL queries combining vector search with relationship traversalBuilt-in vectorization via embedding-provider integrationsBuilt-in BM25 + vector hybrid searchContainerized deployment with durable volumeResource limits with 2x reservation headroomGossip-based multi-node clustering with shard replicationPrometheus metrics endpoint
Technologies: WeaviateGraphQLWeaviate (schema-based knowledge organization)NVIDIA NIM (vectorizer integration)OpenAICohereDocker ComposePrometheusGrafanaMilvus
Quality attributes: Flexibility (ISO/IEC 25010)Cost efficiencyPrivacy (NIST AI RMF: privacy-enhanced)Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)Security (ISO/IEC 25010 | NIST AI RMF: secure and resilient)Maintainability (ISO/IEC 25010)
Risks mitigated: Vendor lock-inData loss from ephemeral container storageUnauthenticated access to the knowledge baseRunaway memory consumption destabilizing hosts

Sources

Ch4.1: T. Nguyen, "Introduction to AI Agent Deployment and Scaling," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.1. ISBN: 9798244538229.
Ch5.8: T. Nguyen, "Semantic Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.8. ISBN: 9798244538229.
Ch6.2A: T. Nguyen, "Vector Database Selection," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.2A. ISBN: 9798244538229.
Ch6.2B: T. Nguyen, "Production Vector Database Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.2B. ISBN: 9798244538229.
Ch6.3B: T. Nguyen, "ETL Worked Example - Load Phase & Pipeline Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.3B. ISBN: 9798244538229.
Ch6.5: T. Nguyen, "Production RAG Systems," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.5. ISBN: 9798244538229.