Marqo

aid: marqo
name: Marqo
description: >-
  Marqo is an open-source, multimodal vector search engine that lets developers
  index text and images, generate embeddings on the fly, and run tensor, lexical,
  and hybrid search through a single REST API. Built on Vespa for storage and
  retrieval and FastAPI for the HTTP surface, Marqo bundles model inference
  (Sentence Transformers, OpenCLIP, ONNX) inside the engine so a single
  `docker run` produces a working semantic search stack. The Apache 2.0
  open-source engine has been marked deprecated by the maintainers as Marqo
  pivots to a hosted ecommerce search product, but the project remains widely
  forked, downloaded, and self-hosted, with active sibling repositories for the
  Python client, Terraform provider, InstantSearch client, ecommerce embedding
  models, and Generalised Contrastive Learning research.
type: Index
position: Consumer
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
  - Vector Database
  - Vector Search
  - Multimodal
  - Semantic Search
  - Embeddings
  - AI
  - Machine Learning
  - Open Source
  - Ecommerce Search
url: https://raw.githubusercontent.com/api-evangelist/marqo/refs/heads/main/apis.yml
created: '2026-05-08'
modified: '2026-05-25'
specificationVersion: '0.19'
apis:
  - aid: marqo:marqo-rest-api
    name: Marqo REST API
    description: >-
      The Marqo REST API is the HTTP surface exposed by the open-source engine
      (default `http://localhost:8882`). It provides index lifecycle management,
      document add/update/get/delete, lexical/tensor/hybrid search, recommendations,
      embedding generation, model lifecycle, telemetry, and health endpoints. The
      same surface is served by Marqo Cloud at `https://api.marqo.ai`, and the
      live OpenAPI schema is published by the running engine at `/openapi.json`
      with Swagger UI at `/docs`.
    humanURL: https://docs.marqo.ai/
    baseURL: http://localhost:8882
    tags:
      - REST
      - Indexes
      - Documents
      - Search
      - Embeddings
      - Models
      - Multimodal
    properties:
      - type: Documentation
        url: https://docs.marqo.ai/
      - type: OpenAPI
        url: openapi/marqo-openapi.yml
      - type: APIReference
        url: https://docs.marqo.ai/latest/
      - type: GettingStarted
        url: https://github.com/marqo-ai/marqo#getting-started
      - type: SourceCode
        url: https://github.com/marqo-ai/marqo
      - type: Deprecation
        url: https://github.com/marqo-ai/marqo
common:
  - type: Website
    url: https://www.marqo.ai/
  - type: GitHubOrganization
    url: https://github.com/marqo-ai
  - type: GitHubRepository
    url: https://github.com/marqo-ai/marqo
  - type: LinkedIn
    url: https://www.linkedin.com/company/marqo-ai
  - type: Documentation
    url: https://docs.marqo.ai/
  - type: GettingStarted
    url: https://github.com/marqo-ai/marqo#getting-started
  - type: License
    url: https://github.com/marqo-ai/marqo/blob/mainline/LICENSE
  - type: Blog
    url: https://www.marqo.ai/blog/
  - type: Pricing
    url: https://www.marqo.ai/pricing
  - type: Plans
    url: plans/marqo-plans-pricing.yml
  - type: RateLimits
    url: rate-limits/marqo-rate-limits.yml
  - type: FinOps
    url: finops/marqo-finops.yml
  - type: SDK
    name: py-marqo (Python client)
    url: https://github.com/marqo-ai/py-marqo
  - type: SDK
    name: marqo-instantsearch-client (TypeScript)
    url: https://github.com/marqo-ai/marqo-instantsearch-client
  - type: Tools
    name: terraform-provider-marqo
    url: https://github.com/marqo-ai/terraform-provider-marqo
  - type: Tools
    name: marqo-base (Docker base image)
    url: https://github.com/marqo-ai/marqo-base
  - type: Tools
    name: ingrain_server (Sentence Transformers / CLIP serving)
    url: https://github.com/marqo-ai/ingrain_server
  - type: Models
    name: marqo-ecommerce-embeddings
    url: https://github.com/marqo-ai/marqo-ecommerce-embeddings
  - type: Models
    name: marqo-FashionCLIP
    url: https://github.com/marqo-ai/marqo-FashionCLIP
  - type: Research
    name: Generalised Contrastive Learning (GCL)
    url: https://github.com/marqo-ai/GCL
  - type: Examples
    name: local-image-search-demo
    url: https://github.com/marqo-ai/local-image-search-demo
  - type: Course
    name: Fine-Tuning Embedding Models for Semantic Search
    url: https://github.com/marqo-ai/fine-tuning-embedding-models-course
  - type: Features
    data:
      - Open-source Apache 2.0 vector search engine (project marked deprecated by maintainers; still 5,000+ stars and actively forked)
      - Single `docker run` install bundling Vespa storage and embedding model inference
      - Tensor, lexical, and hybrid search through a unified REST API
      - Multimodal indexing of text and images with on-engine inference
      - Embedding generation via Sentence Transformers, OpenCLIP, and ONNX models
      - Generalised Contrastive Learning (GCL) framework for fine-tuned retrieval
      - Marqo-FashionCLIP and marqo-ecommerce-embeddings open-weight models
      - Recommendations, filters, and structured + unstructured fields
      - FastAPI runtime exposing live `/openapi.json` and Swagger UI at `/docs`
      - Compose files for inference, model management, and Triton-backed serving
      - Python client (py-marqo), Terraform provider, and InstantSearch client
      - Hosted Marqo Cloud surface preserves API parity for legacy users
    sources:
      - https://github.com/marqo-ai/marqo
      - https://github.com/marqo-ai
    updated: '2026-05-25'
  - type: UseCases
    data:
      - name: Multimodal Semantic Search
        description: Index text and images into a single tensor store and query with natural-language or image inputs, with embedding inference running inside the engine.
      - name: Retrieval-Augmented Generation
        description: Power RAG pipelines by serving the nearest-neighbor retrieval layer for LLM context windows over private corpora.
      - name: Ecommerce Product Discovery
        description: Drive product search, recommendations, and merchandising-aware ranking using semantic relevance plus structured filters and boosts.
      - name: Visual Search
        description: Search product catalogs and image libraries using image-to-image and text-to-image similarity through OpenCLIP / Marqo-FashionCLIP.
      - name: Self-Hosted Vector Backend
        description: >-
          Stand up an Apache 2.0 vector search service alongside your application stack with `docker run`, no
          separate embedding service required.
  - type: Integrations
    data:
      - name: Vespa
        description: Vespa is the underlying storage and retrieval engine that backs every Marqo index.
      - name: Sentence Transformers
        description: Default text embedding model family loaded by the engine for tensor search.
      - name: OpenCLIP
        description: Multimodal text-and-image embedding family used for visual and cross-modal search.
      - name: Hugging Face
        description: Models are pulled from Hugging Face hubs at first use unless preloaded.
      - name: NVIDIA Triton
        description: >-
          `compose-triton.yaml` ships a Triton-backed model server profile for GPU inference.
      - name: Terraform
        description: terraform-provider-marqo manages Marqo Cloud indexes as infrastructure-as-code.
      - name: Algolia InstantSearch
        description: marqo-instantsearch-client adapts Marqo to the InstantSearch.js front-end conventions.
      - name: Shopify
        description: Hosted Marqo product offers one-click integration for Shopify catalogs.
      - name: Adobe Commerce
        description: Hosted Marqo product offers Adobe Commerce / Magento connector.
      - name: Salesforce Commerce Cloud
        description: Hosted Marqo product offers Salesforce Commerce Cloud connector.
maintainers:
  - FN: Kin Lane
    email: kin@apievangelist.com