
Cohere has launched Command-R, a 35 billion parameter model optimized for scalability and Tool Use, designed for generative AI breakthroughs. Command-R boasts a 128K context window, supports 10 languages, and is open-source for research purposes. It outperforms GPT 3.5 in speed and accuracy, excelling in reasoning, question answering, and summarization. Enterprises can evaluate Command-R on the Scale GenAI Platform. The model is lauded for its strong accuracy on RAG and Tool Use, low latency, high throughput, and capabilities across 10 languages.









We have dozens of advanced retrieval techniques and hundreds of notebooks showing you how to build different RAG pipelines in @llama_index. @mendableai's RAG arena now lets you try some of our most exciting retrievers in a UI: - GraphRAG with @neo4j - Auto-merging retriever -… https://t.co/E8hO65Arhg
A way you can make your RAG pipeline handle more complex queries 💡: don’t just retrieve document as text, treat each document as a tool that the agent can interact with 🛠️ If you’re retrieving large documents, this allows you to have way more interesting/complex interactions on… https://t.co/JlU9zUZo1P
In Knowledge Graphs for RAG, our latest short course, you’ll explore how knowledge graphs work, how to build with them, and create better retrieval augmented generation applications. Start today for free: https://t.co/7gWi0SAGwO https://t.co/Df15VSI6qe