A tensor-based search and analytics engine that seamlessly integrates with your applications, websites, and workflows.
Marqo is a versatile and robust search and analytics engine which can be integrated into any website or application.
Due to horizontal scalability, Marqo provides lightning fast query times, even with millions of documents.
Marqo helps you configure deep-learning models like CLIP to pull semantic meaning from images. It can seamlessly handle image-to-image, image-to-text and text-to-image search and analytics.
Marqo adapts and stores your data in a fully schemaless manner. It combines tensor search with a query DSL that provides efficient pre-filtering.
Tensor search allows you to go beyond keyword matching and search based on the meaning of text, images and other unstructured data.
Be a part of the tribe and help us revolutionise the future of search. Whether you are a contributor, a user, or simply have questions about Marqo, we got your back.
Jumpstart your search experience in a couple of minutes. Marqo has libraries available in a number of languages.
On top of our zero-configuration deployment with Docker, you can choose to tailor settings to suit the nature of your deployment and search experience.
Get up to speed and sustain undivided focus on your priorities - Marqo Cloud unlocks a fully managed, multi AZ and serverless user experience, with accelerated inference servers coming soon. Join our Cloud beta waiting list below!
Marqo provides a feature rich developer experience - it lets you use tensor search and analytics without having to sacrifice on features like filtering and highlighting.
Marqo automatically chunks and converts text into tensors, meaning that the search identifies the semantic meaning of sentences rather than blindly matching keywords.
Integrate image based machine learning models for search and analytics using Marqo's end-to-end image search functionality.
Marqo is horizontally scalable and can be run at million document scale whilst maintaining lightning-fast search times.
Import models from Huggingface and other shared repositories for use in Marqo.
Marqo provides search highlighting functionality which allows you to transparently understand where and why a match occurred.
Marqo offers a powerful query DSL (Domain Specific Language), which can be applied as a prefilter ahead of approximate k-NN search.
Marqo was made by developers, for developers. We work with contributors to help shape the development experience.
Get the assistance you need, here and now.
Marqo is accessible to everyone, down to the very core.
Marqo's integration with Docker allows you to deploy on any cloud provider you prefer. Be it AWS, GCP, Azure or Marqo Cloud.
Get involved with building the future of Marqo or access support from Marqo's vast community by joining us on Slack and Github. To see what we are up to, check out our roadmap!
Discuss issues, PRs, and what features to add. Vote on your favorite features. Let us know!
Join the group discussion and let any head-scratchers be answered by the community!
Have a look at Marqo's work plan for the near future!