We’re pleased to announce the newest foundation model in our Cohere Rerank model series, Rerank 3 Nimble (available on Amazon SageMaker).

Cohere's Command family of models are instruction-following conversational models that excel at a wide variety of language tasks, especially those resting on complex RAG functionality and multi-step tool use.

Developers are now able to force Command R and Command R+ to generate outputs as JSON objects by setting the response_format parameter in the Chat API.

Cohere's dashboard now supports a much broader range of data-based workflows. Users can upload, download, manage, and interface with their fine-tuning datasets, in addition to being able to perform batch embedding with the embed jobs endpoint -- all directly in the UI.

Multi-step tool use now default in Chat API

We're pleased to announce the release of Rerank 3 our newest and most performant foundational model for ranking. Rerank 3 boast a context length of 4096, SOTA performance on Code Retrieval, Long Document, and Semi-Structured Data. In addition to quality improvements, we've improved inference speed by a factor of 2x for short documents (doc length < 512 tokens) and 3x for long documents (doc length ~4096 tokens).

We're pleased to announce the release of Command R+, our newest and most performant large language model. Command R+ is optimized for conversational interaction and long-context tasks, and it is the recommended model for use cases requiring high performance and accuracy.

We've released an additional update for our Python SDK! Here are the highlights.

Today, we are introducing Command R, a new LLM aimed at large-scale production workloads. Command R targets the emerging “scalable” category of models that balance high efficiency with strong accuracy, enabling companies to move beyond proof of concept, and into production.

In place of custom_models, fine_tuning has been added to the Python SDK. See this Python github repository for the full list of supported functions!