Aug. 16, 2024 — Cohere has introduce its newest module: Cohere on AWS. The company is committed to empowering users with the tools and knowledge to unlock the full potential of large language models (LLMs). Guided by this goal, Cohere’s LLM University offers a comprehensive suite of modules to help users master Enterprise AI technologies.
This eight-chapter course will guide you through building generative AI applications on Amazon’s cloud computing platform.
Course Outline
The Cohere on AWS module will guide you through the following chapters:
- Introduction to Amazon Bedrock: Get to know Amazon Bedrock and its fully managed service enables enterprises to build generative AI applications.
- Introduction to Amazon SageMaker: Learn about Amazon SageMaker and its features for building, training, and deploying machine learning models.
- Text Generation on Bedrock: Use Cohere Command R+ for various tasks such as text generation, summarization, rewriting, and extraction.
- Semantic Search on Bedrock: Use Cohere Embed to build semantic search applications enabled by text embeddings.
- Reranking on SageMaker: Use Cohere Rerank to boost the accuracy of search results.
- Retrieval-Augmented Generation on Bedrock and SageMaker: Create a RAG application using Cohere’s Chat, Embed, and Rerank endpoints.
- Tool Use and Agents on Bedrock: Build agentic applications that automate tasks and workflows by leveraging Command R+’s tool use capabilities.
- Fine-Tuning Models on SageMaker: Perform fine-tuning to customize and enhance a model’s performance on specific tasks and domains.
Start learning today.
A range of Cohere models are available on AWS through two services: Amazon Bedrock and Amazon SageMaker. To access you will need to be a registered user.
About Amazon Bedrock
Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs). Using Amazon Bedrock, you can customize Cohere models with your data using techniques such as fine-tuning and retrieval-augmented generation (RAG), and build agents that execute tasks with (tool use) using your enterprise systems and data sources.
Amazon Bedrock is serverless, which means that you don’t have to manage any infrastructure. You can securely integrate generative AI capabilities into your applications using the AWS services that you are already familiar with.
About Amazon SageMaker
Amazon SageMaker is a fully managed service where you can build, train, and deploy ML models at scale using tools like notebooks, debuggers, profilers, pipelines, MLOps, and more — all in one integrated development environment (IDE).
While Bedrock is a platform focused on foundational models (FMs), SageMaker caters to a much broader range of machine learning (ML) models. Additionally, SageMaker offers greater control over the underlying infrastructure hosting the models.
Source: Cohere
