Exploring AWS Bedrock: Data Storage, Security and AI Models
Amazon Web Services (AWS), a global leader in cloud computing, has recently launched a new service known as Amazon Bedrock. This service is fully managed and designed to streamline the process of developing generative AI applications.
Amazon Bedrock provides access to a selection of high-performance foundation models (FMs). These models are the product of collaboration with leading AI companies such as AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon itself. The service offers a unified API, making it easier for developers to leverage these models in their applications.
Despite simplifying the development of generative AI application process, it does not compromise on privacy and security aspects. This ensures that developers can create powerful AI applications while maintaining the integrity and confidentiality of their data.
In this article, we delve into the fundamental aspects of AWS’s security measures, and the availability and pricing overview of the models.
Security Implications
Security is a chief concern when it comes to AWS Bedrock. The platform is designed with security and privacy at its core, leveraging the robust security features of other AWS services. This ensures the safety and privacy of data, with comprehensive data encryption guaranteeing the secure management and protection of sensitive information.
Amazon Bedrock employs rigorous encryption measures and storage practices within the AWS Region where it operates, safeguarding user data at rest. Crucially, data inputs and model outputs are not disclosed to third-party model providers for training, ensuring confidentiality like Microsoft Azure.
Amazon Bedrock empowers users to engage in private customisation of only Titan Text Lite and Titan Text Express FMs, granting them control over how their data is utilised and encrypted. The system creates an isolated copy of the base FM, on which private model training takes place. Notably, user data such as prompts, supplementary information, FM responses, and customised FMs are retained within the region where the API requests are processed.
What sets Amazon Bedrock apart is its ability to refine and fine-tune models for specific tasks without the need for extensive data annotation. It then generates a distinct private version of the FM, accessible exclusively by the user, and trains it independently. Importantly, none of the user data contributes to the training of the original base models. Amazon Bedrock can be configured with Amazon Virtual Private Cloud (VPC) and AWS Identity and Access Management (IAM).
Moreover, users do not have to manage any infrastructure as Amazon Bedrock is serverless. This means that the integration and implementation of generative AI capabilities into desired applications can be done securely using established AWS services.
Bedrock’s abuse detection systems are automated, ensuring no human oversight is involved in reviewing or accessing user inputs or model outputs. However, as of now, there is no available information about opting out of data usage. In contrast, Azure’s abuse monitoring processes are similarly automated, but they do offer their customers the option to opt-out.
Models Availability
You’ll find a summary table of AWS Bedrock FMs at the end for reference. If you’re keen on delving deeper into the FMs (Amazon Titan, AI21 Labs Jurassic, Anthropic Claude, Cohere Command, Meta Llama 2, and Stable Diffusion XL), the section below provides more details.
Amazon Titan
There are three versions of Amazon Titan.
Titan Text Express (preview) offers an offset between price and performance. It supports a maximum of 8K tokens and over 100 languages. The supported use cases include retrieval augmented generation, open-ended text generation, brainstorming, summarisation, code generation, table creation, data formatting, paraphrasing, chain of thought, rewrite, extraction, Q&A, and chat.
Titan Text Lite (preview) is reasonably priced and small, ideal for basic tasks and fine-tuning. It supports English and has a maximum of 4K tokens. The supported use cases include open-ended text generation, brainstorming, summarisation, code generation, table creation, data formatting, paraphrasing, chain of thought, rewrite, extraction, Q&A, and chat.
Titan Embeddings (generally available) that translates text into a numerical representation. It supports a maximum of 8K tokens, over 25 languages, and 1536 embeddings. This is the only embedding model available on AWS Bedrock presently. The supported use cases include text retrieval, semantic similarity, and clustering.
AI21 Labs Jurassic
There are two versions of the Jurassic model optimised for zero-shot. It can be accessed through Amazon Bedrock to build generative AI applications and is available through AI21 Studio. It is the world’s most customisable model with 5 APIs i.e. APIs are designed for effortless customisation, in stark contrast to other models that rely solely on the base API and prompt engineering. It supports a maximum of 8192 tokens and languages including English, Spanish, French, German, Portuguese, Italian, and Dutch.
Jurassic-2 Ultra is AI21’s most powerful model, offering remarkable quality. The supported use cases include question-answering, summarisation, draft generation, advanced information extraction, and ideation for tasks requiring intricate reasoning and logic.
Jurassic-2 Mid is a mid-sized model that strikes the true balance between remarkable quality and affordability. The supported use cases include question-answering, summarisation, draft generation, advanced information extraction, and ideation. It is also available on the AWS Marketplace and optimised to follow natural language instructions and context without requiring any instances. It’s a pinnacle in Stanford’s Holistic Evaluation of Language Models (HELM), standing notably advanced than models up to 30x bigger in size. This allows users to optimise production costs and speed without forgoing quality.
Anthropic Claude
There are three versions of Anthropic Claude. It supports a maximum of 100K tokens and multiple languages including English.
Claude 1.3 is an earlier version of their general-purpose model. The supported use cases include searching, writing, editing, outlining, and summarising text; coding; and providing helpful advice about a broad range of subjects.
Claude Instant is their faster, reasonably priced yet very efficient model. The supported use cases include casual dialogue, text analysis, summarisation, and document comprehension.
Claude 2 is the most efficient system released up to date. The supported use cases include thoughtful dialogue, content creation, complex reasoning, creativity, and coding. Claude 2 excels at the core capabilities of Claude 1.3 and Claude Instant.
We have an upcoming blog on this with our analysis.
Cohere Command
Command is Cohere’s only model with 52B parameters. It supports a maximum of 4K tokens and English language. The supported use cases include chat, text generation, and text summarisation. According to the HELM benchmark, Command stands midst the world’s finest language models. It is also available through Cohere’s subscription for enterprises. They have a partnership with Oracle.
Meta Llama 2
There are two versions of the fine-tuned Meta Llama 2. It supports a maximum of 4K tokens and English. The supported use case is an assistant-like chat. The only difference between Llama-2–13b-chat and Llama-2–70b-chat is that the former has a parameter size of 13B while the latter parameter size of 70B.
Stable Diffusion XL
There are two versions of Stable Diffusion XL with a 3.5B parameter base model and a 6.6B parameter model ensemble pipeline. It supports English and has a maximum of 77 tokens. The supported use cases include advertising and marketing, media and entertainment, gaming and metaverse. It’s also available through Stability AI API, Stability AI’s Github page and its Clipdrop and DreamStudio consumer applications.
Stable Diffusion XL 1.0 (preview) is the most advanced text-to-image model from Stability AI while Stable Diffusion XL 0.8 (preview) is an earlier version of the text-to-image model from Stability AI.
All these models are pre-trained on large datasets making them powerful tools for a wide range of applications.
Models Pricing
There are two pricing consumption plans for inference:
On-Demand: With this plan, access to FMs is on a flexible pay-as-you-go basis without the need for long-term commitments.
Provisioned Throughput: This plan enables the allocation of the necessary throughput resources to meet your application’s performance needs in exchange for committing to a specific time-based term.
Conclusion
Amazon Web Services’ Bedrock represents an immense advancement in the orbit of generative AI. It provides a secure environment for deploying generative AI models, with robust data encryption, secure access management via IAM, and a serverless architecture that eliminates the need for users to manage infrastructure. Importantly, user inputs and model results are kept confidential and not shared with third-party model providers. However, there is currently abuse monitoring is automated, and there is currently no information available about the ability to opt out of data usage.
The service’s rigorous security protocols are designed to uphold data privacy, a feature that is increasingly important in today’s digital age. Furthermore, Bedrock provides access to an array of potent foundation models. These models, developed by leading AI companies, can address a wide range of use cases.
Given these features, AWS Bedrock emerges as an optimal choice for businesses aiming to harness the power of AI. It offers a comprehensive solution that balances ease of use with advanced capabilities, making it an invaluable tool in the modern business landscape.
This article was written with the help of ChatGPT and Bing Chat.
About the author
Rosemary J Thomas, PhD, is a Senior Technical Researcher at the Version 1 AI Labs.
