Request preview
kynetradb

One Rust binary: BM25 search + vector + KV + document + auth + files + realtime + agentic admin.

vs
Qdrant

Rust-native vector similarity search engine with HNSW, payload filtering, and distributed mode.

Feature comparison

DimensionkynetradbQdrant
Full-text searchBM25 — reference catalogueNone
Vector searchBrute-force cosine evaluationQdrant uses HNSW which scales better past ~100k vectorsHNSW
AuthPreview scopeBuilt-in
Row-Level SecurityPreview scopeNo
File storagePreview scopeNone
RealtimePreview scopeNone
Edge FunctionsPreview scopeNo
TypeScript SDKPreview scopeNo official client SDK
KV lookupsPreview scopeNo
Document filterPreview scopeYes
LLM runtimePreview scopeNo
Outbound DB syncPreview scopeNo
Self-hostPreview scopeYes
Single binaryPreview scopeYes
LicensePreview terms — request a scoped evaluationApache-2.0
Deploy targets19 target profiles1 listed target profiles
Free tierPreview access by requestyes — Qdrant Cloud free tier

When to pick Qdrant

The fastest and most memory-efficient dedicated vector engine in benchmarks. If you need pure vector search at scale, Qdrant is purpose-built for it.

  • You need HNSW at scale past ~100k vectors — kynetradb uses brute-force today.
  • Your team is already invested in Qdrant's SDK and ecosystem.

When to pick kynetradb

  • You want a comparison-led conversation about BM25 full-text, vector evaluation, and data-plane trade-offs.
  • You need a product-specific implementation scope rather than a generic migration claim.
  • You want to assess 19 hosting target profiles, including 5 Indian providers.
  • You want a scoped preview conversation about the data, deployment, and operating boundary.

Vector upsert + query — both APIs side by side

Upsert an embedding and query nearest neighbours. These are documentation-accurate shapes, not runnable end-to-end examples.

kynetradb
# kynetradb — upsert entity with embedding
curl -X POST https://your.host/v1/entities \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "kind": "product",
    "attrs": { "title": "Aurora Espresso" },
    "embedding": [0.1, 0.2, 0.3, 0.4]
  }'

# kynetradb — vector similarity query
curl -X POST https://your.host/v1/vector \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "vector": [0.1, 0.2, 0.3, 0.4],
    "top_k": 10
  }'
Qdrant
# Qdrant — REST API
# Upsert
curl -X PUT http://localhost:6333/collections/products/points \
  -H "Content-Type: application/json" \
  -d '{
    "points": [{"id": 1, "vector": [0.1, 0.2, 0.3, 0.4], "payload": {"title": "Aurora Espresso"}}]
  }'

# Query
curl -X POST http://localhost:6333/collections/products/points/search \
  -H "Content-Type: application/json" \
  -d '{"vector": [0.1, 0.2, 0.3, 0.4], "limit": 10}'
See all 20 comparisonsQdrant homepage ↗