
Cohere AI has launched a new state-of-the-art model named Command R Plus, marking a significant advancement in the field of artificial intelligence. This model introduces an advanced Retrieval-Augmented Generation (RAG) system with citations to minimize hallucinations, supports 10 languages, and boasts a context length of 128K. It is available for free testing, highlighting its open-source nature and the company's commitment to research and safety in AI. The development team, including notable figures such as Aidan Gomez and Sarah Hooker, has received widespread acclaim for their work, with the AI community hailing Command R Plus as a groundbreaking achievement in open-source AI. The model's capabilities in RAG, tool use, and multilingual support are particularly emphasized, alongside its cost-effectiveness and the dedication of the team behind it. The release of state-of-art weights for research use aims to power exciting research and critical safety work across the ecosystem. Command R Plus is described as the world's best and most capable open weight model, with its open weights being a key feature. Pat Verga announced he joined Cohere seven months ago, contributing to the development of this great model.

Building RAG with Command R+ from Cohere, DSPy, and Weaviate! https://t.co/PCniHMFftA via @YouTube
Working on local RAG using great open models and easy touchpoints command-r by @cohere via @ollama for generation (great prompt docs too: https://t.co/jaUdXkI0a3) nomic-embed-text by @nomic_ai via @ollama for embedding retrieval with @trychroma https://t.co/9Hldx2hhGG
Command-R+ is currently the most prominent & hottest release in Technology around the world! Congratulations team @cohere! 🪅🥳