Cohere’s Command R model is now available as an option to power Tabnine Chat

We’re excited to announce that the Cohere Command R model is now available as one of the underlying LLMs that powers Tabnine Chat. Tabnine is partnering with Cohere, the enterprise-focused AI platform to bring the Command R model to Tabnine via Oracle Cloud Infrastructure (OCI) Generative AI service. You get the full capability of Tabnine’s AI chat with the Command R model — including code generation, code explanations, documentation generation, and AI-created tests — as well as highly personalized recommendations by utilizing the context from locally available data in your IDE and your organization’s global codebases. 

Command R: The powerful new model from Cohere for enterprise use 

Released in March 2024, Cohere’s Command R model is ideal for large-scale production workloads and balances high efficiency with strong accuracy. The model is optimized for long context tasks such as retrieval-augmented generation (RAG) and using external APIs and tools. RAG has become a crucial pattern in the deployment of LLM as it enables enterprises to give the model access to private knowledge that it otherwise wouldn’t have. The Command R model provides best-in-class integration for RAG applications and offers low latency, high throughput, and excels at enterprise use cases.

Partnership with Cohere

Tabnine is partnering with Cohere to provide the Command R model as one of the underlying LLMs to support Tabnine Chat. Tabnine Chat accesses the Command R model using the API from Oracle Cloud Infrastructure (OCI) Generative AI service instead of accessing the model via third-party APIs. Since the Command R model is hosted on OCI Generative AI, Tabnine sends data to the service for computing responses to user prompts. OCI helps ensure that the data transferred between your IDE and the OCI API endpoint is encrypted in transit to prevent eavesdropping or person-in-the-middle attacks. Additionally, the data at rest is encrypted. 

OCI Generative AI offers the ability for customers to host and manage Command R models on dedicated clusters that are exclusive to those customers.

“OCI helps ensure that enterprise applications—including AI and data-driven, resource intensive apps—run in a way that makes business sense, at scale,” said Vinod Mamtani, vice president, Generative AI Services, Oracle Cloud Infrastructure. “We’re excited to see Tabnine Chat in action with OCI Generative AI, providing private, protected, and fast time to value for any organization looking to innovate.”

Extending the switchable models functionality with cutting-edge models

Earlier this year, we launched the switchable models capability for Tabnine Chat that allows users to switch the model that underpins Tabnine Chat in real time. With today’s announcement, we’re extending that capability to include support for Cohere’s Command R model. 

You can now choose from 8 different models with Tabnine’s AI software development chat tools: two custom-built, fully private models from Tabnine plus popular LLMs from third-party vendors. 

More importantly, you’re not locked into any one of these models. Switch instantly between them for specific projects, use cases, or to meet the requirements of specific teams. We plan to make more models available for Tabnine Chat in the near future. This eliminates any worry about missing out on LLM innovations and makes it simple to use new models as they emerge. It also future-proofs your investment in AI and enables your team to focus on accelerating the software development life cycle using Tabnine.

During model selection, Tabnine provides transparency into the behaviors and characteristics of each of the available models to help you decide which one is right for your situation. For example, for projects where data privacy and legal risks are less important, you can use a model optimized for performance over compliance such as Cohere Command R. As you switch to working on projects that have stricter requirements for privacy and protection, you can change to a model like Tabnine Protected that’s built for that purpose. The underlying LLM can be changed with just a few clicks — and Tabnine Chat adapts instantly. Check out this short video that shows the Cohere Command R model in action. 

As Tabnine users, there’s no additional cost to use the Command R model. We provide complete control when selecting models that power Tabnine Chat. All the models are available to Tabnine Pro users who can pick the model that fits their use case. 

For enterprise SaaS users, only the Tabnine Protected model is available by default. Any Tabnine administrators who need access to the Cohere Command R model or any additional models can contact our Support Team, and we’ll enable the specific models on your account. 

Check out our Docs to learn more about this functionality. If you’re not yet a customer, you can sign up for Tabnine Pro today — it’s free for 90 days.