AWS decision-guides documentation change
Summary
Entire documentation content removed and replaced with PDF reference link
Security assessment
The diff shows removal of detailed service documentation without any indication of addressing security vulnerabilities. While original content mentioned security features like Bedrock Guardrails and secure data handling, the removal itself doesn't directly relate to fixing security issues or adding security documentation.
Diff
diff --git a/decision-guides/latest/generative-ai-on-aws-how-to-choose/guide.md b/decision-guides/latest/generative-ai-on-aws-how-to-choose/guide.md index 4852a4656..8b1378917 100644 --- a//decision-guides/latest/generative-ai-on-aws-how-to-choose/guide.md +++ b//decision-guides/latest/generative-ai-on-aws-how-to-choose/guide.md @@ -1 +0,0 @@ -[](/pdfs/decision-guides/latest/generative-ai-on-aws-how-to-choose/generative-ai-on-aws-how-to-choose.pdf#guide "Open PDF") @@ -3,707 +1,0 @@ -[Documentation](/index.html)[AWS Decision Guides](https://aws.amazon.com/getting-started/decision-guides/)[AWS Decision Guide](guide.html) - -IntroductionUnderstandConsiderChooseUseExploreResources - -# Choosing a generative AI service - -**Taking the first step** - -**Purpose** | Determine which AWS generative AI services are the best fit for your organization. ----|--- -**Last updated** | February 14, 2025 -**Covered services** | - - * [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) - * [Amazon Q Business](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/what-is.html) - * [Amazon Q Developer](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html) - * [Amazon SageMaker AI](https://docs.aws.amazon.com/sagemaker/latest/dg/whatis.html.html) - * [Amazon Nova foundation models](https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html) - * [Amazon Titan foundation models](https://docs.aws.amazon.com/bedrock/latest/userguide/titan-models.html) - * [Public foundation models](https://aws.amazon.com/what-is/foundation-models/) - * [AWS Trainium](https://aws.amazon.com/machine-learning/trainium/) - * [AWS Inferentia](https://aws.amazon.com/machine-learning/inferentia/) - - - -## Introduction - -Generative AI is a set of artificial intelligence (AI) systems and models designed to generate content such as code, text, images, music, or other forms of data. These systems can produce new content based on patterns and knowledge learned from existing data. Increasingly, organizations and businesses are using generative AI to: - - * **Automate creative workflows** — Use generative AI services to automate the workflows of time-consuming creative processes such as writing, image or video creation, and graphic design. - - * **Customize and personalize content** — Generate targeted content, product recommendations, and customized offerings for an audience-specific context. - - * **Augment data** — Synthesize large training datasets for other ML models to _unlock_ scenarios where human-labeled data is scarce. - - * **Reduce cost** — Potentially lower costs by using synthesized data, content, and digital assets. - - * **Faster experimentation** — Test and iterate on more content variations and creative concepts than would be possible manually. - - - - -This guide helps you select the AWS generative AI services and tools that are the best fit for your needs and your organization. - -A twelve-minute video about building generative AI applications on AWS, part one of a four-part series. View [part two](https://www.youtube.com/watch?v=HUuO9eJbOTk), [part three](https://www.youtube.com/watch?v=JbizhCFmC20) and [part four](https://www.youtube.com/watch?v=gNY06JM6m8U). - -## Understand - -Amazon offers a range of generative AI services, applications, tools, and supporting infrastructure. Which of these you use depends a lot on the following factors: - - * What you’re trying to do - - * How much choice you need in the foundation models that you use - - * The degree of customization you need in your generative AI applications - - * The expertise within your organization - - - - - - -**Amazon Q Business and Amazon Q Developer— Applications to boost productivity** - -At the top of Amazon's generative AI stack, Amazon Q Business and Amazon Q Developer use large language models (LLMs) and foundation models. However, they don’t require that you explicitly choose a model. Each of these applications support different use cases, and all are powered by [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html). - -Learn more about the primary generative AI–powered assistants currently available: - -Amazon Q Business - - -[Amazon Q Business](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/what-is.html) can answer questions, provide summaries, generate content, and securely complete tasks based on the data in your enterprise systems. It supports the general use case of using generative AI to start making the most of the information in your enterprise. With Amazon Q Business, you can make English-language queries about that information. It provides responses in a manner appropriate to your team’s needs. In addition, you can create lightweight, purpose-built [Amazon Q Apps](https://docs.aws.amazon.com/amazonq/latest/qbusiness-ug/purpose-built-qapps.html) within your Amazon Q Business Pro subscription. - -Amazon Q Developer - - -With [Amazon Q Developer](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/what-is.html), you can understand, build, extend, and operate AWS applications. The supported use cases include tasks that range from coding, testing, and upgrading applications, to diagnosing errors, performing security scanning and fixes, and optimizing AWS resources. The advanced, multistep planning and reasoning capabilities in Amazon Q Developer are aimed at reducing the work involved in common tasks (such as performing Java version upgrades). These capabilities can also help implement new features generated from developer requests. - -Amazon Q Developer features are available as part of your workflows in [other AWS services](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/features.html), including Amazon Q Developer in chat applications, Amazon CodeCatalyst, Amazon EC2, AWS Glue, and VPC Reachability Analyzer. - -[Chat with Amazon Q Developer](https://aws.amazon.com/blogs/devops/chat-about-your-aws-account-resources-with-amazon-q-developer/) to query and explore your AWS infrastructure directly from the AWS Management Console. Using natural language prompts to interact with your AWS account, you can get specific resource details and ask about relationships between resources. - -Amazon Q in QuickSight - - -[Amazon Q in QuickSight](https://docs.aws.amazon.com/quicksight/latest/user/quicksight-gen-bi.html) is aimed at meeting the needs of a specific use case: getting actionable insights from your data by connecting Amazon Q to the Amazon Q QuickSight business intelligence (BI) service. You can use it to build visualizations of your data, summarize insights, answer data questions, and build data stories using natural language. - -Amazon Q in Connect - - -[Amazon Q in Connect](https://docs.aws.amazon.com/connect/latest/adminguide/amazon-q-connect.html) can automatically detect customer issues. It provides your customer service agents with contextual customer information along with suggested responses and actions for faster resolution of issues. It combines the capabilities of the [Amazon Connect](https://docs.aws.amazon.com/connect/latest/adminguide/what-is-amazon-connect.html) cloud contact center service with Amazon Q. Amazon Q in Connect can use your real-time conversations with your customers, along with relevant company content, to recommend what to say or what actions an agent should take to assist customers. - -**Amazon Bedrock — Build and scale your generative AI application with FMs** - -If you're developing custom AI applications, need access to multiple foundation models, and want more control over the AI models and outputs, then [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) could be the service that meets your needs. Amazon Bedrock is a fully managed service for building generative AI applications, with support for [popular foundation models](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html), including [Amazon Nova](https://docs.aws.amazon.com/nova/latest/userguide/what-is-nova.html), [Amazon Titan](https://docs.aws.amazon.com/bedrock/latest/userguide/titan-models.html), [Anthropic Claude](https://aws.amazon.com/bedrock/claude/), [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1), [Cohere Command & Embed](https://aws.amazon.com/bedrock/cohere-command-embed/), [AI21 Labs Jurassic](https://aws.amazon.com/bedrock/jurassic/), [Meta Llama](https://aws.amazon.com/bedrock/llama/), [Mistral AI](https://aws.amazon.com/bedrock/mistral/), and [Stable Diffusion XL](https://aws.amazon.com/bedrock/stable-diffusion/). - -Use the [ Amazon Bedrock Marketplace](https://docs.aws.amazon.com/bedrock/latest/userguide/amazon-bedrock-marketplace.html) to discover, test, and use over 100 popular, emerging, and specialized FMs. [Supported FMs](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) are updated on a regular basis. - - - -In addition, Amazon Bedrock provides what you need to build generative AI applications with security, privacy, and responsible AI—regardless of the foundation model you choose. It also offers model-independent, single API access and the flexibility to use different foundation models and upgrade to the latest model versions, with minimal code changes. - -Learn more about the key features of Amazon Bedrock: - -Model customization - - -[Model customization](https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html) can deliver differentiated and personalized user experiences. To customize models for specific tasks, you can privately fine-tune FMs using your own labeled datasets. Custom models include capabilities such as fine-tuning and continued pre-training using unlabeled datasets. The list of FMs for which Amazon Bedrock supports fine-tuning includes Amazon Nova Micro, Lite, and Pro, Anthropic Claude 3 Haiku, Cohere Command, Meta Llama 2, Amazon Titan Text Lite and Express, Amazon Titan Multimodal Embeddings, and Amazon Titan Image Generator. The list of supported FMs is updated on an ongoing basis. - -In addition, you can use [Amazon Bedrock Custom Model Import](https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html) to bring your own custom models and use them within Amazon Bedrock. - -Knowledge Bases - - -[Amazon Bedrock Knowledge Bases ](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html) is a fully managed capability that you can use to implement the entire Retrieval Augmented Generation (RAG) workflow—from ingestion to retrieval and prompt augmentation—without having to build custom integrations to data sources, and manage data flows. Session context management is built in, so your application can support multi-turn conversations. You can use the Retrieve API to fetch relevant results for a user query from knowledge bases. - -With RAG, you can provide a model with new knowledge or up-to-date info from multiple sources, including document repositories, databases, and APIs. For example, the model might use RAG to retrieve search results from Amazon OpenSearch Service or documents from Amazon Simple Storage Service. Amazon Bedrock Knowledge Bases fully manages this experience by connecting to your private data sources, including [Amazon Aurora](https://aws.amazon.com/rds/aurora/), [Amazon OpenSearch Serverless](https://aws.amazon.com/opensearch-service/features/serverless/), MongoDB, Pinecone, and Redis Enterprise Cloud. This list includes connectors for Salesforce, Confluence, and SharePoint (in preview), so you can access more business data to customize models for your specific needs. - -Agents - - -[Amazon Bedrock Agents ](https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html) helps you plan and create multistep tasks using company systems and data sources—from answering customer questions about your product availability to taking their orders. You can create an agent by first selecting an FM and then providing it access to your enterprise systems, knowledge bases, and AWS Lambda functions to run your APIs securely. An agent analyzes the user request, and a Lambda function or your application can automatically call the necessary APIs and data sources to fulfill the request. - -Agents [can retain memory](https://aws.amazon.com/blogs/aws/agents-for-amazon-bedrock-now-support-memory-retention-and-code-interpretation-preview/) across multiple interactions to remember where you last left off and provide better recommendations based on prior interactions. Agents can also interpret code to tackle complex data-driven use cases, such as data analysis, data visualization, text processing, solving equations, and optimization problems. - -Guardrails - - -[Amazon Bedrock Guardrails ](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html) evaluates user inputs and FM responses based on use case specific policies, and provides an additional layer of safeguards, regardless of the underlying FM. Using a short natural language description, you can use Amazon Bedrock Guardrails to define a set of topics to avoid within the context of your application. Guardrails detects and blocks user inputs and FM responses that fall into the restricted topics. - -Guardrails supports [contextual grounding checks](https://aws.amazon.com/blogs/aws/guardrails-for-amazon-bedrock-can-now-detect-hallucinations-and-safeguard-apps-built-using-custom-or-third-party-fms/), to detect hallucinations in model responses for applications using Retrieval Augmented Generation (RAG) and summarization applications. Contextual grounding checks add to the safety protection in Guardrails to make sure the LLM response is based on the right enterprise source data, and evaluates the LLM response to confirm that it’s relevant to the user’s query or instruction. Contextual grounding checks can detect and filter over 75% hallucinated responses for RAG and summarization workloads. - -Converse API - - -Use the [Amazon Bedrock Converse API](https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html) to create conversational applications that send and receive messages to and from an Amazon Bedrock model. For example, you can create a chatbot that maintains a conversation over many turns and uses a persona or tone customization that is unique to your needs, such as a helpful technical support assistant. - -Tool use (function calling) - - -[Tool use (function calling)](https://docs.aws.amazon.com/bedrock/latest/userguide/tool-use.html) gives a model access to tools that can help it generate responses for messages that you send to the model. For example, you might have a chat application that lets users find out the most popular song played on a radio station. To answer a request for the most popular song, a model needs a tool that can query and return the song information. - -Amazon Bedrock IDE - - -Use [Amazon Bedrock IDE](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/bedrock.html), a development experience in Amazon SageMaker Unified Studio (in preview), that lets you discover Amazon Bedrock models and build generative AI apps that use Amazon Bedrock models and features. For example, you can use a chat playground to try a [prompt](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/explore-prompts.html) with an Anthropic Claude model without having to write any code. Later, you can use Amazon Bedrock IDE to create a generative AI app that uses an Amazon Bedrock model and features, such as a knowledge base or a guardrail, again without having to write any code. - -Prompt management - - -Use Amazon Bedrock to create and save your own prompts using [Prompt management](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-management.html), so that you can save time by applying the same prompt to different workflows. When you create a prompt, you can select a model to run inference on it and modify the inference parameters to use. You can include variables in the prompt so that you can adjust the prompt for different use case. - -Prompt flows - - -[Prompt flows](https://docs.aws.amazon.com/bedrock/latest/userguide/flows.html) for Amazon Bedrock offers the ability for you to use supported FMs to build workflows by linking prompts, foundational models, and other AWS services to create comprehensive solutions. - -With prompt flows, you can quickly build complex generative AI workflows using a visual builder. You can integrate with Amazon Bedrock offerings such as FMs, knowledge bases, and other AWS services such as AWS Lambda by transferring data between them. You can also deploy immutable workflows to move from testing to production in few clicks. - -**Amazon SageMaker AI (formerly Amazon SageMaker) — Build custom models and control the full ML lifecycle, from data preparation to model deployment and monitoring** - -With [Amazon SageMaker AI](https://docs.aws.amazon.com/sagemaker/latest/dg/whatis.html), you can build, train, and deploy machine learning models, including FMs, at scale. Consider this option when you have use cases that can benefit from extensive training, fine-tuning, and customization of foundation models. It also streamlines the sometimes-challenging task of evaluating which FM is the best fit for your use case. - -Amazon SageMaker AI also provides infrastructure and purpose-built tools for use throughout the ML lifecycle, including integrated development environments (IDEs), distributed training infrastructure, governance tools, machine learning operations (MLOps) tools, inference options and recommendations, and model evaluation. - - - -Use [Amazon SageMaker Partner AI Apps](https://docs.aws.amazon.com/sagemaker/latest/dg/partner-apps.html) to access generative AI and machine learning (ML) development applications built, published, and distributed by industry-leading application providers. Partner AI Apps are certified to run on SageMaker AI. With Partner AI Apps, you can improve how you build solutions based on foundation models (FM) and classic ML models without compromising the security of your sensitive data. The data stays completely within your trusted security configuration and is never shared with a third party. - -SageMaker AI is part of the next generation of Amazon SageMaker, which includes: - - * [Amazon SageMaker Unified Studio ](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/what-is-sagemaker-unified-studio.html) (in preview), a unified development experience that brings together AWS data, analytics, artificial intelligence (AI), and machine learning (ML) services. - - * AWS tools for complete development workflows, including model development, generative AI app development, data processing, and SQL analytics, in a single governed environment. Create or join projects to collaborate with your teams, securely share AI and analytics artifacts, and access your data stored in Amazon Simple Storage Service (Amazon S3), Amazon Redshift, and more data sources through the [Amazon SageMaker Lakehouse](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/lakehouse.html). - - - - -Explore key features of SageMaker AI that may help you determine when to use it: - -Amazon SageMaker JumpStart - - -[Amazon SageMaker JumpStart ](https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html) is an ML hub that provides access to publicly available foundation models. Those models include Mistral, Llama 3, CodeLlama, and Falcon 2. They can be customized with advanced fine-tuning and deployment techniques such as Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA). - -This following screenshot shows some of the available models in Amazon SageMaker JumpStart within the AWS Management Console. - - - -Amazon SageMaker Clarify - -