Marqo

Open-source tensor search engine that embeds documents on ingest and serves lexical, tensor and hybrid queries.

Provider: default
Kind: Vector database
Category: Data
Official docs: https://docs.marqo.ai/latest/reference/api/indexes/create-structured-index/

Properties · 5 set by this component

property	type	values	required	kind default	this component
dimensions	integer	—	no	—	inherited
distanceMetric	enum	cosine \| euclidean \| dot-product	no	—	▸ cosine
efConstruction · component property	integer	—	no	512	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
quantization	enum	none \| scalar \| product \| binary	no	none	inherited
replicas	integer	—	no	—	inherited
schemaMode · component property	enum	structured \| unstructured	no	unstructured	inherited
spaceType · component property	enum	prenormalized-angular \| angular \| euclidean \| dotproduct \| hamming	no	prenormalized-angular	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: "marqo", component: "marqo" }

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 Milvusmilvusvector-database MyScalemyscalevector-database pgvectorpgvectorvector-database pgvectorscalepgvectorscalevector-database Pineconepineconevector-database Qdrantqdrantvector-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# Marqo: open-source tensor search engine that embeds documents on ingest and serves lexical, tensor
3# and hybrid queries. "Create structured index": spaceType defaults to prenormalized-angular with
4# HNSW parameters efConstruction 512 and m 16, and the default model is hf/e5-base-v2.
5schemaVersion: "1"
6type: "component"
7id: "marqo"
8kind: "vector-database"
9provider: "default"
10docs: "https://docs.marqo.ai/latest/reference/api/indexes/create-structured-index/"
11defaults:
12  indexType: "hnsw"
13  distanceMetric: "cosine"
14  metadataFiltering: true
15  hybridSearch: true
16  managed: false
17properties:
18  spaceType:
19    type: "enum"
20    values: ["prenormalized-angular", "angular", "euclidean", "dotproduct", "hamming"]
21    default: "prenormalized-angular"
22  efConstruction:
23    type: "integer"
24    default: 512
25  hnswM:
26    type: "integer"
27    default: 16
28  schemaMode:
29    type: "enum"
30    values: ["structured", "unstructured"]
31    default: "unstructured"

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