Use your data to increase relevanceorder valuedownloadsconversionsconversions with vector search.

Fine tune embedding models with interaction data to increase conversions, order value, downloads, clicks. Get started in minutes, not months.

Get StartedBook A Demo

AI search that understands the way your customers search think

Choose from hundreds of embedding models, or bring your own

Accelerate your development cycle with Marqo. Index documents and begin searching in just a few lines of code.

Multimodal search

Create multimodal indexes and search combinations of images and text with ease. Choose from a range of open source models or bring your own.

Train embedding models

Marqo can fine-tune models to encode relevance and ranking in embeddings. This enables a first stage retrieval which optimises core business metrics based off of historical interactions data. Request access to the preview.

mq = marqo.Client()

mq.create_index("my-first-index", model="hf/all_datasets_v4_MiniLM-L6")

mq.index("my-first-index").add_documents(
    [{"title": "The Travels of Marco Polo"}],
    tensor_fields=["title"]
)

results = mq.index("my-first-index").search("Marqo Polo")

mq = marqo.Client()

mq.create_index(
    "my-multimodal-index", 
    treat_urls_and_pointers_as_images=True, 
    model="ViT-L/14"
)

mq.index("my-multimodal-index").add_documents(
    [{
        "description": "Marqo Vector Search",
        "image": "https://docs.marqo.ai/1.4.0/assets/logo.png"
    }],
    tensor_fields=["image"]
)

results = mq.index("my-multimodal-index").search("Marqo Polo")

model_details = marqtune_client.train(
    method="weighted_clip",
    model="open_clip/ViT-L-14/laion2b_s32b_b82k",
    data={
        "id": "your_data_uuid", 
        "bucket_path": "path_in_bucket"
    },
    params={
        "param1": "value1", 
        "param2": "value2"
    }
)
Vector search has become a must have component of generative AI. Marqo is instrumental in making AI useful to businesses by enabling developers to use the best technology with little effort.
Aidan Gomez
CEO and co-founder of Cohere
With Marqo, we were able to deploy advanced vector search quickly and easily and see results instantly. We went from sign-up to production A/B testing in five days and, within the next week, had rolled out a new feature to 100% of our traffic after we saw an improvement in key metrics.
Testimonial from Anthony Ziebell for Marqo
Anthony Ziebell
Head of AI at Temple & Webster

Easily integrates as an additional retriever

No need to replace re-rankers, Marqo can slot into your existing pipeline

Scalable

Run Marqo in a docker image on your laptop or scale it up to dozens of GPU inference nodes in the cloud. Marqo can be scaled to provide low latency searches against multi-terabyte indexes.

Multimodal

Marqo helps you configure deep-learning models like CLIP to pull semantic meaning from images. You can seamlessly search any combination of text and images and even combine text and images into a single vector.

End-to-end AI search

Marqo has you covered from inference to storage. With Marqo you don't need to calculate the vectors yourself, simply select the model you want to use and pass the text and/or image URLs directly to the API.

Multilingual

Search in over 100 languages. Marqo provides access to state of the art multilingual models. Expand your search to new localities with zero manual language configuration changes.

Customer Stories

Ecommerce Search

A global e-commerce company with a highly optimised and ingrained BM25 Opensearch index implemented Marqo to improve search performance.


Marqo fine-tuned a multimodal CLIP model to encapsulate the existing ranking logic and delivered a 17% increase in ATC rate. Queries that previously would not match anything due to a lack of shared text with the query now return relevant results with better capture of semantics.

The existing system relied upon complex business logic for score modification optimised over 15 years by countless data scientists.

Online Retail Recommendation

A major Australian retailer implemented Marqo for search and recommendations. In a period of 5 days a single developer was able to have Marqo serving 20% of website search traffic in an A/B test. In the subsequent 5 days the team also implemented a recommendation system with the same Marqo index.

The recommendation system provided a statistically significant increase in average order value and cart size within 3 days and is now used for 100% of on page complementary product recommendations.

 Enhance your search with Marqo's feature-rich developer experience.

Marqo provides a feature rich developer experience - it lets you perform multimodal vector search without having to sacrifice on features like filtering and highlighting.

Multimodal search

Marqo can be used with text and/or image data. Multimodal indexes seamlessly handle image-to-image, image-to-text and text-to-image search.

Composite Queries

Marqo supports weighted queries which can combine multiple text and image queries together. Negative weights can be added to query terms to push certain items out of your result set.

Ranking Modification

Marqo supports score modifiers, numeric fields in your documents can be used to manipulate the score and influence the ranking of results.

Context search

Additional context can be added to queries by providing vectors directly, this helps tailor results without the overhead of additional inference.

Custom model integration

Import open source models from Hugging Face, bring your own, or load private models from AWS S3, GCP or Hugging Face using authentication.

Bulk operations

Parts of Marqo's API support bulk operations to improve throughput. These bulk operations enable use cases such as bulk changes to multiple indexes or coalescing of queries.

Horizontal scalability

Marqo is horizontally scalable and can be run at million document scale whilst maintaining lightning-fast search times.

Highlighting

Marqo provides search highlighting functionality which allows you to transparently understand where and why a match occurred.

Filtering

Marqo offers a powerful query DSL (Domain Specific Language), which can be applied as a prefilter ahead of approximate k-NN search.

Join the community.

Get involved with building the future of Marqo or access support from Marqo's vast community by joining us on Slack and Github.

GitHub

Discuss issues, PRs, and what features to add. Vote on your favorite features. Let us know!

Start contributing

Slack

Join the group discussion and let any head-scratchers be answered by the community.

Join our Slack

Discourse

Join our discourse forum to keep up with the latest announcements, troubleshoot with the community, or show off something you have built with Marqo!

Community Forum

Releases

Have a look at Marqo's release notes to keep up-to-date with development.

Release Notes

Request Your Marqo Demo Today!

Discover the transformative capabilities of Marqo. Schedule your personalized demo now and elevate your workflow.

Book Demo

Subscribe to our mailing list.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Marqo is more than a vector database, it's an end-to-end vector search engine.

For media inquiries, please email press@marqo.ai

RESOURCES

PricingDocumentationBlogAPI ReferenceStatus Page

CONNECT

SupportGitHubSlackCommunity

COMPANY

Contact usCareersTerms and ConditionsSLA and Support PolicyPrivacy Policy
© Copyright Marqo.ai 2024. All Rights Reserved.