Marqo AI: Marqo | Increase Relevance with Vector Search

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

Visit Website
Marqo | Increase Relevance with Vector Search

Introduction

What is Marqo?

Marqo is a generative AI-powered vector search engine that enables developers to increase relevance and conversions in their product search. It provides a feature-rich developer experience, allowing for multimodal vector search, composite queries, ranking modification, and more.

Features of Marqo

Multimodal Search

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

Context Search

Marqo allows additional context to be added to queries by providing vectors directly, which helps tailor results without the overhead of additional inference.

Custom Model Integration

Marqo supports importing open source models from Hugging Face, bringing your own, or loading private models from AWS S3, GCP, or Hugging Face using authentication.

Bulk Operations

Parts of Marqo's API support bulk operations to improve throughput, enabling 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 while 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.

How to Use Marqo

To get started with Marqo, you can create an index, add documents, and search for results using the Marqo client. You can also fine-tune models to encode relevance and ranking in embeddings, enabling a first-stage retrieval that optimizes core business metrics based on historical interactions data.

Pricing of Marqo

Marqo offers a pricing plan that suits your needs. You can get started with Marqo's cloud pricing or contact their sales team for a custom quote.

Helpful Tips for Using Marqo

  • Use Marqo's multimodal search to create a seamless search experience for your users.
  • Leverage Marqo's composite queries to combine multiple text and image queries together.
  • Use Marqo's ranking modification to influence the ranking of results.
  • Take advantage of Marqo's custom model integration to import open source models or bring your own.

Frequently Asked Questions

What is Marqo used for?

Marqo is used for increasing relevance and conversions in product search.

How does Marqo work?

Marqo uses generative AI-powered vector search to enable developers to increase relevance and conversions in their product search.

Can I use Marqo for multimodal search?

Yes, Marqo supports multimodal indexes, which can seamlessly handle image-to-image, image-to-text, and text-to-image search.

How do I get started with Marqo?

You can get started with Marqo by creating an index, adding documents, and searching for results using the Marqo client.