We are thrilled to announce that Rerank 3 is now available on Microsoft Azure AI Studio. Rerank 3 is a foundation model that enhances existing search systems by reranking the initial search results to prioritize the most relevant documents.

Accessing Cohere’s enterprise-ready language models on Azure AI’s robust infrastructure enables businesses to seamlessly, reliably, and safely incorporate cutting-edge semantic search technology into their applications. This integration allows users to leverage Azure's flexibility and scalability, combined with Cohere's highly performant and efficient language models, to deliver superior search results in production. Using Azure AI model catalog and with just a few lines of code, developers can implement Rerank 3 to enhance their existing search systems.

Rerank 3 offers state-of-the-art capabilities for enterprise search, including:

4k context length to significantly improve search quality for longer documents
Ability to search over multi-aspect and semi-structured data like emails, invoices, JSON documents, code, and tables
Multilingual coverage of 100+ languages
Improved latency and lower total cost of ownership (TCO)

How Azure Customers Can Enhance Search with Rerank 3

Rerank 3 - English and Rerank 3 - Multilingual serve two primary purposes,

It can be added to existing search systems after an initial dense retrieval stage to improve the relevancy of results, or
it can be added to retrieval-augmented generation (RAG) systems to increase the relevance of documents and lowering the number of documents being passed to the generative model (and therefore reduce operating costs).

Atomicwork, a digital workplace experience platform and longtime Azure customer, has significantly enhanced its IT service management platform with Rerank. By integrating the model into their AI digital assistant, Atom AI, Atomicwork saw over 20% in improved search accuracy and relevance, providing faster, more precise answers to complex IT support queries. This integration has streamlined IT operations and boosted productivity across the enterprise.

TD Bank Group, one of the largest banks in North America, recently signed an agreement with Cohere to explore its full suite of large language models (LLMs), including Rerank 3.

Enterprises of any size and in any industry can leverage Rerank to significantly enhance their search capabilities across countless scenarios, including:

Legacy search improvement: Improve results from legacy lexical or semantic tools
Customer support search: Enable self-serve across complex customer support docs
Multilingual search: Understand meaning and relevance across over 100 languages
RAG: Retrieve most relevant answers across heterogenous enterprise data sources

Command R+, Cohere’s flagship generative model which is also available on Azure AI, is purpose-built to work well with Rerank within a RAG system. Together, they are capable of serving the most demanding enterprise workloads in production.

Boosting Search Quality for 100+ Languages with a Single Line of Code

Established keyword-based search systems are deeply ingrained within a company’s information architecture, and switching to a vector database for embedding-based search is often impractical. This is where Rerank 3 can help, providing a seamless bridge between traditional keyword-based search and the power of semantic search. The model works for 100+ languages and enables great search quality across languages.

Accessible through Azure AI Studio, our model computes a relevance score for a set of text documents compared to a given user query. This approach consistently yields superior search results, especially for complex and domain-specific queries, when compared to traditional, embedding-based semantic search.

Demonstrated Improvements in Multilingual Retrieval

Global organizations also deal with multilingual data sources, and historically, multilingual retrieval has been a challenge with keyword-based methods. Our Rerank 3 model offers strong multilingual performance in over 100+ languages, simplifying retrieval for non-English-speaking customers.

*Multilingual retrieval accuracy based nDCG@10 on MIRACL (higher is better).*

Start Building with Rerank 3 on Azure AI

To recap, here are the key benefits:

Practical integration: Augment your existing search systems effortlessly
Enhanced performance: Achieve state-of-the-art search performance, particularly for complex queries
Broad enterprise use cases: Significantly enhance search capabilities across various scenarios for any department
Simplicity: Implement with a single line of code
Federated search: Merge and sort results from diverse search systems

To access Rerank 3 on Azure AI Studio, follow these steps:

Prerequisites: 

Get an Azure subscription if you don’t already have one. 
Familiarize yourself with Azure AI Model Catalog. 
Create an Azure  AI Studio hub and project. Make sure you pick East US, West US3, South Central US, West US, North Central US, East US 2, or Sweden Central as the Azure region for the hub.

Create a deployment to obtain the inference API and key: 

Open the model card in the model catalog on Azure AI Studio. 
Click on Deploy and select the Pay-as-you-go option. 
Subscribe to the Marketplace offer and deploy. You can also review the API pricing at this step. 
You should land on the deployment page that shows you the API and key in less than a minute.

These steps are outlined in detail in the Azure AI Studio product documentation. Please check some samples to get started: LangChain, Web Requests, Cohere Client.

For more information on how to integrate Rerank 3 into your applications, explore our API documentation and blog for detailed instructions and code samples.

Whether you’re enhancing an existing search system or building new applications, Rerank 3 offers a practical, powerful solution.

To understand how your company can start deploying with Rerank 3 at production-scale, reach out to our sales team. If you are a developer with feedback about your experience using Cohere Rerank, we would love to hear from you. Please send us an email at support@cohere.com.

Introducing Rerank 3 on Microsoft Azure AI