Skip to content

Comparison

Feature-by-feature against the vector databases RAG teams actually evaluate. This is a feature inventory, not a benchmark - for raw vector-search throughput see each project's published numbers.

Feature matrix

FeatureDASHPineconeWeaviateMilvusQdrantChroma
Open sourceyes (Apache-2.0 intended)no, proprietaryyes, BSD-3yes, Apache-2.0yes, Apache-2.0yes, Apache-2.0
Claim + Evidence modelfirst-classnonononono
Citation provenance per resultfirst-classnot modelednot modelednot modelednot modelednot modeled
Contradiction handlingfirst-classnomanual, via modulesnonono
stance_mode: support_onlyyesnonononono
Temporal validity windowsfirst-classmetadata onlymanualmanualmanualmanual
OpenAI-compatible embeddingsyes, nativepartialyesvia proxyvia proxyyes
Swap embedding providertrait-basedn/aplugin-basedn/an/afunction-based
HNSW ANNyes (built-in)yes, proprietaryyesyesyesyes
Graph primitivesfirst-classnoyes, no contradiction semanticsnopayload-based onlyno
Hash-chained audit logyes, SHA-256nonononono
Tenant isolationyes, allowlist + scoped keysyesyes (OIDC)yespartialno
Per-tenant rate limitsyesyesyesyespartialno
Scoped API keysyeslimitedyesyeslimitedno
Key revocation (hot reload)yesyesyesyespartialno
JWT auth with kid rotationyesJWT onlyyes (OIDC)yespartialno
Durable WAL + replayyes, built-inmanagedyesyesyesno
Backpressure-aware HTTPyes (queue + 503)managedyesyesyesno
Docker Compose / systemdyesn/ayesyesyesno
Benchmark suite + CI guardyesn/apartialyespartialno
Managed cloud optionno (self-hosted)yesyesyesyesyes

When to use DASH

  • RAG where wrong answers have a cost: legal research, clinical decision support, financial due diligence, enterprise knowledge bases, regulatory compliance.
  • Citation-grade provenance on every retrieved claim - a source, a stance, a quality score, ideally a span.
  • The retrieval layer must know a claim was contradicted and demote or filter it.
  • Temporal validity windows ("what was true in Q3 2024?") as a first-class query, not a metadata hack.
  • Tamper-evident audit: every state change SHA-256-chained, verifiable with scripts/verify_audit_chain.sh.
  • Multi-tenant SaaS needing per-tenant rate limits, scoped keys, revocation, and strict allowlists in one process.
  • Auditable storage and retrieval with no managed-cloud component and no proprietary extension.

When NOT to use DASH

  • Pure image, audio, or video similarity search. DASH is text-claim-centric - use Milvus or Pinecone.
  • Sub-millisecond latency at billion-vector scale. DASH is not optimized for this - use Milvus with GPU indexing or Pinecone serverless.
  • Fully managed cloud with no ops responsibility. DASH is self-hosted only - use Pinecone, Weaviate Cloud, or Qdrant Cloud.
  • No notion of evidence, citation, contradiction, or temporal validity in the data. The differentiators are not free - a simpler store (Qdrant, Chroma) reaches "vector search" faster.
  • General-purpose graph database. DASH has typed claim edges with RAG semantics, not a full property graph - use Neo4j or Memgraph.
  • OLAP analytics over the vector store. Use ClickHouse or Druid.

Released under the Apache 2.0 License.