Marqo

Active
GitHub Python Apache-2.0

Description

Marqo is an end-to-end vector search and discovery platform, ready out of the box for ecommerce search and RAG.

Key Features

  • Unified API — vectors + filters + ranking
  • Built-in models — multimodal and text embedders bundled
  • High-performance — Rust core with ANN indexing
  • Horizontally scalable — distributed clusters
  • Document store — metadata and document storage
  • Cloud-native — one-line Docker deploy

Use Cases

💡 End-to-end ecommerce search
💡 Fast vector backend for RAG applications
💡 Multimodal image+text retrieval
💡 Replacing ElasticSearch with vector search

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (5.0k stars)
  • Permissive open-source license (Apache-2.0)
  • Established track record (4 years in production)

Quick Start

docker run -d --name marqo -p 8882:8882 marqoai/marqo:latest
pip install marqo
import marqo; mq = marqo.Client()
mq.index("my-index").add_documents([{"title":"hello"}])

Related Projects

Meilisearch

59.0k · Rust
Active A

Meilisearch is a lightweight open-source search engine with typo tolerance, native vector search and instant indexing, commonly used as the retrieval layer for agents and RAG.

search-enginefull-text-searchvector-search +2
  • · Typo-tolerant — forgiving search out of the box
  • · Instant indexing — new or updated docs are searchable within milliseconds
  • · Native vector search — built-in ANN vector index, hybrid with full-text

Apache Doris

15.8k · Java
Active A

Apache Doris is a real-time analytics MPP database for AI agent workloads, delivering millisecond queries with hybrid search.

olapreal-time-analyticsvector-search +3
  • · Real-time analytics — Columnar MPP architecture delivers sub-second aggregation queries at scale
  • · Vector search — Built-in ANN index supports hybrid structured and unstructured search
  • · MySQL compatible — Standard MySQL protocol and SQL syntax