Qdrant

Open-source vector search engine using a filterable HNSW index with payload indexes and sparse vectors.

Provider: default
Kind: Vector database
Category: Data
Official docs: https://qdrant.tech/documentation/concepts/indexing/

Properties · 6 set by this component

property	type	values	required	kind default	this component
dimensions	integer	—	no	—	inherited
distanceMetric	enum	cosine \| euclidean \| dot-product	no	—	inherited
hnswEfConstruct · component property	integer	—	no	100	inherited
hnswM · component property	integer	—	no	16	inherited
hybridSearch	boolean	—	no	false	▸ true
indexType	enum	flat \| hnsw \| ivf \| disk-ann \| lsh	no	—	▸ hnsw
managed	boolean	—	no	false	▸ false
metadataFiltering	boolean	—	no	false	▸ true
namespaces	boolean	—	no	false	inherited
onDiskPayload · component property	boolean	—	no	false	inherited
quantization	enum	none \| scalar \| product \| binary	no	none	▸ none
replicas	integer	—	no	—	▸ 1
shardNumber · component property	integer	—	no	1	inherited
writeConsistencyFactor · component property	integer	—	no	1	inherited

Rules that apply · 0

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

No rule reads this kind yet. That is a gap, not a guarantee.

Use it in a design

nodes:
  - { id: "qdrant", component: "qdrant" }

Other Vector database products · 23

Alibaba Cloud Milvusalibaba-milvusalibabacloudvector-database Amazon S3 Vectorsaws-s3-vectorsawsvector-database Agent Memorycloudflare-agent-memorycloudflarevector-database Cloudflare Vectorizecloudflare-vectorizecloudflarevector-database Chromachromavector-database Deep Lakedeeplakevector-database Epsillaepsillavector-database KDB.AIkdb-aivector-database LanceDBlancedbvector-database Marqomarqovector-database Milvusmilvusvector-database MyScalemyscalevector-database pgvectorpgvectorvector-database pgvectorscalepgvectorscalevector-database Pineconepineconevector-database turbopufferturbopuffervector-database Valdvaldvector-database Generic vector databasevector-databasevector-database Vespa Cloudvespa-cloudvector-database Weaviateweaviatevector-database Zilliz Cloudzilliz-cloudvector-database DigitalOcean Vector Databasesdigitalocean-vector-databasedigitaloceanvector-database Vertex AI Vector Searchgoogle-vertex-ai-vector-searchgcpvector-database

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Qdrant: open-source vector search engine. "Indexing": HNSW is the only dense vector index, with
3# m 16 and ef_construct 100, and payload indexes make filtered search first class. "Collections":
4# a new collection gets one shard, replication_factor 1, write_consistency_factor 1 and payload in RAM.
5schemaVersion: "1"
6type: "component"
7id: "qdrant"
8kind: "vector-database"
9provider: "default"
10docs: "https://qdrant.tech/documentation/concepts/indexing/"
11defaults:
12  indexType: "hnsw"
13  quantization: "none"
14  metadataFiltering: true
15  hybridSearch: true
16  replicas: 1
17  managed: false
18properties:
19  shardNumber:
20    type: "integer"
21    default: 1
22  writeConsistencyFactor:
23    type: "integer"
24    default: 1
25  onDiskPayload:
26    type: "boolean"
27    default: false
28  hnswM:
29    type: "integer"
30    default: 16
31  hnswEfConstruct:
32    type: "integer"
33    default: 100

The same page as markdown, for an agent: /catalogue/components/qdrant.md