AWS Weekly Roundup: New capabilities in Amazon Bedrock, AWS Amplify Gen 2, Amazon RDS and more (May 13, 2024)

AWS Summit is in full swing around the world, with the most recent one being AWS Summit Singapore! Here is a sneak peek of the AWS staff and ASEAN community members at the Developer Lounge booth. It featured AWS Community speakers giving lightning talks on serverless, Amazon Elastic Kubernetes Service (Amazon EKS), security, generative AI, and more.

Last week’s launches
Here are some launches that caught my attention. Not surprisingly, a lot of interesting generative AI features!

Amazon Titan Text Premier is now available in Amazon Bedrock – This is the latest addition to the Amazon Titan family of large language models (LLMs) and offers optimized performance for key features like Retrieval Augmented Generation (RAG) on Knowledge Bases for Amazon Bedrock, and function calling on Agents for Amazon Bedrock.

Amazon Bedrock Studio is now available in public preview – Amazon Bedrock Studio offers a web-based experience to accelerate the development of generative AI applications by providing a rapid prototyping environment with key Amazon Bedrock features, including Knowledge Bases, Agents, and Guardrails.

Agents for Amazon Bedrock now supports Provisioned Throughput pricing model – As agentic applications scale, they require higher input and output model throughput compared to on-demand limits. The Provisioned Throughput pricing model makes it possible to purchase model units for the specific base model.

MongoDB Atlas is now available as a vector store in Knowledge Bases for Amazon Bedrock – With MongoDB Atlas vector store integration, you can build RAG solutions to securely connect your organization’s private data sources to foundation models (FMs) in Amazon Bedrock.

Amazon RDS for PostgreSQL supports pgvector 0.7.0 – You can use the open-source PostgreSQL extension for storing vector embeddings and add retrieval-augemented generation (RAG) capability in your generative AI applications. This release includes features that increase the number of dimensions of vectors you can index, reduce index size, and includes additional support for using CPU SIMD in distance computations. Also Amazon RDS Performance Insights now supports the Oracle Multitenant configuration on Amazon RDS for Oracle.

Amazon EC2 Inf2 instances are now available in new regions – These instances are optimized for generative AI workloads and are generally available in the Asia Pacific (Sydney), Europe (London), Europe (Paris), Europe (Stockholm), and South America (Sao Paulo) Regions.

New Generative Engine in Amazon Polly is now generally available – The generative engine in Amazon Polly is it’s most advanced text-to-speech (TTS) model and currently includes two American English voices, Ruth and Matthew, and one British English voice, Amy.

AWS Amplify Gen 2 is now generally available – AWS Amplify offers a code-first developer experience for building full-stack apps using TypeScript and enables developers to express app requirements like the data models, business logic, and authorization rules in TypeScript. AWS Amplify Gen 2 has added a number of features since the preview, including a new Amplify console with features such as custom domains, data management, and pull request (PR) previews.

Amazon EMR Serverless now includes performance monitoring of Apache Spark jobs with Amazon Managed Service for Prometheus – This lets you analyze, monitor, and optimize your jobs using job-specific engine metrics and information about Spark event timelines, stages, tasks, and executors. Also, Amazon EMR Studio is now available in the Asia Pacific (Melbourne) and Israel (Tel Aviv) Regions.

Amazon MemoryDB launched two new condition keys for IAM policies – The new condition keys let you create AWS Identity and Access Management (IAM) policies or Service Control Policies (SCPs) to enhance security and meet compliance requirements. Also, Amazon ElastiCache has updated it’s minimum TLS version to 1.2.

Amazon Lightsail now offers a larger instance bundle – This includes 16 vCPUs and 64 GB memory. You can now scale your web applications and run more compute and memory-intensive workloads in Lightsail.

Amazon Elastic Container Registry (ECR) adds pull through cache support for GitLab Container Registry – ECR customers can create a pull through cache rule that maps an upstream registry to a namespace in their private ECR registry. Once rule is configured, images can be pulled through ECR from GitLab Container Registry. ECR automatically creates new repositories for cached images and keeps them in-sync with the upstream registry.

AWS Resilience Hub expands application resilience drift detection capabilities – This new enhancement detects changes, such as the addition or deletion of resources within the application’s input sources.

For a full list of AWS announcements, be sure to keep an eye on the What’s New at AWS page.

Other AWS news
Here are some additional projects and blog posts that you might find interesting.

Building games with LLMs – Check out this fun experiment by Banjo Obayomi to generate Super Mario levels using different LLMs on Amazon Bedrock!

Troubleshooting with Amazon Q –  Ricardo Ferreira walks us through how he solved a nasty data serialization problem while working with Apache Kafka, Go, and Protocol Buffers.

Getting started with Amazon Q in VS Code – Check out this excellent step-by-step guide by Rohini Gaonkar that covers installing the extension for features like code completion chat, and productivity-boosting capabilities powered by generative AI.

AWS open source news and updates – My colleague Ricardo writes about open source projects, tools, and events from the AWS Community. Check out Ricardo’s page for the latest updates.

Upcoming AWS events
Check your calendars and sign up for upcoming AWS events:

AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Bengaluru (May 15–16), Seoul (May 16–17), Hong Kong (May 22), Milan (May 23), Stockholm (June 4), and Madrid (June 5).

AWS re:Inforce – Explore 2.5 days of immersive cloud security learning in the age of generative AI at AWS re:Inforce, June 10–12 in Pennsylvania.

AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Turkey (May 18), Midwest | Columbus (June 13), Sri Lanka (June 27), Cameroon (July 13), Nigeria (August 24), and New York (August 28).

Browse all upcoming AWS led in-person and virtual events and developer-focused events.

That’s all for this week. Check back next Monday for another Weekly Roundup!

— Abhishek

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

from AWS News Blog https://ift.tt/xp9fhSI
via IFTTT

A new generative engine and three voices are now generally available on Amazon Polly

Today, we are announcing the general availability of the generative engine of Amazon Polly with three voices: Ruth and Matthew in American English and Amy in British English. The new generative engine was trained with publicly available and proprietary data, a variety of voices, languages, and styles. It performs with the highest precision to render context-dependent prosody, pausing, spelling, dialectal properties, foreign word pronunciation, and more.

Amazon Polly is a machine learning (ML) service that converts text to lifelike speech, called text-to-speech (TTS) technology. Now, Amazon Polly includes high-quality, natural-sounding human-like voices in dozens of languages, so you can select the ideal voice and distribute your speech-enabled applications in many locales or countries.

With Amazon Polly, you can select various voice options, including neural, long-form, and generative voices, which deliver ground-breaking improvements in speech quality and produce human-like, highly expressive, and emotionally adept voices. You can store speech output in standard formats like MP3 or OGG, adjust the speech rate, pitch, or volume with Speech Synthesis Markup Language (SSML) tags, and quickly deliver lifelike voices and conversational user experiences with consistently fast response times.

What’s the new generative engine?
Amazon Polly now supports four voice engines: standard, neural, long-form, and generative voices.

Standard TTS voices, introduced in 2016 use traditional concatenative synthesis. This method strings together the phonemes of recorded speech, producing very natural-sounding synthesized speech. However, the inevitable variations in speech and the techniques used to segment the waveforms limit the quality of speech.

Neural TTS (NTTS) voices, introduced in 2019, use a sequence-to-sequence neural network that converts a sequence of phonemes into spectrograms, and a neural vocoder that converts the spectrograms into a continuous audio signal. The NTTS produces even higher quality human-like voices than its standard voices.

Long-form voices, introduced in 2023, are developed with cutting-edge deep learning TTS technology and designed to captivate listeners’ attention for longer content, such as news articles, training materials, or marketing videos.

In February 2024, Amazon scientists introduced a new research TTS model called Big Adaptive Streamable TTS with Emergent abilities (BASE). With this technology, Polly Generative engine is able to create human-like synthetically generated voices. You can use these voices as a knowledgeable customer assistant, a virtual trainer, or an experienced marketer.

Here are the new generative voices:

Name	Locale	Gender	Language	Sample prompt	NTTS voices	Generative voices
Ruth	en_US	Female	English (US)	Selma was lying on the ground halfway down the steps. 'Selma! Selma!' we shouted in panic.
Matthew	en_US	Male	English (US)	The guards were standing outside with some of our neighbours, listening to a transistor radio. 'Any good news?' I asked. 'No, we're listening to the names of people who were killed yesterday,' Bruno replied.
Amy	en_GB	Female	English (British)	What are you looking at?' he said as he stood over me. They got off the bus and started searching the baggage compartment. The tension on the bus was like a dark, menacing cloud that hovered above us.

You can choose from these voice options to suit your application and use case. To learn more about the generative engine, visit Generative voices in the AWS documentation.

Get started with using generative voices
You can access the new voices using the AWS Management Console, AWS Command Line Interface (AWS CLI), or the AWS SDKs.

To get started, go to the Amazon Polly console in the US (N. Virginia) Region and choose Text-to-Speech menu in the left pane. If you select the voice of Ruth or Matthew in the language of English, US or Amy in English, UK, you can choose Generative engine. Input your text and listen to or download the generated voice output.

Using the CLI, you can list the voices that use the new generative engine:

$ aws polly describe-voices --output json --region us-east-1 \
| jq -r '.Voices[] | select(.SupportedEngines | index("generative")) | .Name'

Matthew
Amy
Ruth

Now, run the synthesize-speech CLI command to synthesize sample text to an audio file (hello.mp3) with the parameters of generative engine and a supported voice ID.

$ aws polly synthesize-speech --output-format mp3 --region us-east-1 \
  --text "Hello. This is my first generative voices!" \
  --voice-id Matthew --engine generative hello.mp3

To learn more code examples using AWS SDKs, visit Code and Application Examples in the AWS documentation. You can use Java and Python code examples, application examples such as web applications using Java or Python, or iOS and Android applications.

Now available
The new generative voices of Amazon Polly are now available today in the US East (N. Virginia) Region. You only pay for what you use based on the number of characters of text that you convert to speech. To learn more, visit our Amazon Polly Pricing page.

Give new generative voices a try in the Amazon Polly console today and send feedback to AWS re:Post for Amazon Polly or through your usual AWS Support contacts.

— Channy

from AWS News Blog https://ift.tt/7kzRpxy
via IFTTT

Feed retention policy change from 90 days to 30 days

via Ecommerce Data Analytics

Build RAG and agent-based generative AI applications with new Amazon Titan Text Premier model, available in Amazon Bedrock

Today, we’re happy to welcome a new member of the Amazon Titan family of models: Amazon Titan Text Premier, now available in Amazon Bedrock.

Following Amazon Titan Text Lite and Titan Text Express, Titan Text Premier is the latest large language model (LLM) in the Amazon Titan family of models, further increasing your model choice within Amazon Bedrock. You can now choose between the following Titan Text models in Bedrock:

• Titan Text Premier is the most advanced Titan LLM for text-based enterprise applications. With a maximum context length of 32K tokens, it has been specifically optimized for enterprise use cases, such as building Retrieval Augmented Generation (RAG) and agent-based applications with Knowledge Bases and Agents for Amazon Bedrock. As with all Titan LLMs, Titan Text Premier has been pre-trained on multilingual text data but is best suited for English-language tasks. You can further custom fine-tune (preview) Titan Text Premier with your own data in Amazon Bedrock to build applications that are specific to your domain, organization, brand style, and use case. I’ll dive deeper into model highlights and performance in the following sections of this post.
• Titan Text Express is ideal for a wide range of tasks, such as open-ended text generation and conversational chat. The model has a maximum context length of 8K tokens.
• Titan Text Lite is optimized for speed, is highly customizable, and is ideal to be fine-tuned for tasks such as article summarization and copywriting. The model has a maximum context length of 4K tokens.

Now, let’s discuss Titan Text Premier in more detail.

Amazon Titan Text Premier model highlights
Titan Text Premier has been optimized for high-quality RAG and agent-based applications and customization through fine-tuning while incorporating responsible artificial intelligence (AI) practices.

Optimized for RAG and agent-based applications – Titan Text Premier has been specifically optimized for RAG and agent-based applications in response to customer feedback, where respondents named RAG as one of their key components in building generative AI applications. The model training data includes examples for tasks like summarization, Q&A, and conversational chat and has been optimized for integration with Knowledge Bases and Agents for Amazon Bedrock. The optimization includes training the model to handle the nuances of these features, such as their specific prompt formats.

• High-quality RAG through integration with Knowledge Bases for Amazon Bedrock – With a knowledge base, you can securely connect foundation models (FMs) in Amazon Bedrock to your company data for RAG. You can now choose Titan Text Premier with Knowledge Bases to implement question-answering and summarization tasks over your company’s proprietary data.
  
• Automating tasks through integration with Agents for Amazon Bedrock – You can also create custom agents that can perform multistep tasks across different company systems and data sources using Titan Text Premier with Agents for Amazon Bedrock. Using agents, you can automate tasks for your internal or external customers, such as managing retail orders or processing insurance claims.
  

We already see customers exploring Titan Text Premier to implement interactive AI assistants that create summaries from unstructured data such as emails. They’re also exploring the model to extract relevant information across company systems and data sources to create more meaningful product summaries.

Here’s a demo video created by my colleague Brooke Jamieson that shows an example of how you can put Titan Text Premier to work for your business.

Custom fine-tuning of Amazon Titan Text Premier (preview) – You can fine-tune Titan Text Premier with your own data in Amazon Bedrock to increase model accuracy by providing your own task-specific labeled training dataset. Customizing Titan Text Premier helps to further specialize your model and create unique user experiences that reflect your company’s brand, style, voice, and services.

Built responsibly – Amazon Titan Text Premier incorporates safe, secure, and trustworthy practices. The AWS AI Service Card for Amazon Titan Text Premier documents the model’s performance across key responsible AI benchmarks from safety and fairness to veracity and robustness. The model also integrates with Guardrails for Amazon Bedrock so you can implement additional safeguards customized to your application requirements and responsible AI policies. Amazon indemnifies customers who responsibly use Amazon Titan models against claims that generally available Amazon Titan models or their outputs infringe on third-party copyrights.

Amazon Titan Text Premier model performance
Titan Text Premier has been built to deliver broad intelligence and utility relevant for enterprises. The following table shows evaluation results on public benchmarks that assess critical capabilities, such as instruction following, reading comprehension, and multistep reasoning against price-comparable models. The strong performance across these diverse and challenging benchmarks highlights that Titan Text Premier is built to handle a wide range of use cases in enterprise applications, offering great price performance. For all benchmarks listed below, a higher score is a better score.

Capability	Benchmark	Description	Amazon	Google	OpenAI
			Titan Text Premier	Gemini Pro 1.0	GPT-3.5
General	MMLU (Paper)	Representation of questions in 57 subjects	70.4% (5-shot)	71.8% (5-shot)	70.0% (5-shot)
Instruction following	IFEval (Paper)	Instruction-following evaluation for large language models	64.6% (0-shot)	not published	not published
Reading comprehension	RACE-H (Paper)	Large-scale reading comprehension	89.7% (5-shot)	not published	not published
Reasoning	HellaSwag (Paper)	Common-sense reasoning	92.6% (10-shot)	84.7% (10-shot)	85.5% (10-shot)
	DROP, F1 score (Paper)	Reasoning over text	77.9 (3-shot)	74.1 (Variable Shots)	64.1 (3-shot)
	BIG-Bench Hard (Paper)	Challenging tasks requiring multistep reasoning	73.7% (3-shot CoT)	75.0% (3-shot CoT)	not published
	ARC-Challenge (Paper)	Common-sense reasoning	85.8% (5-shot)	not published	85.2% (25-shot)

Note: Benchmarks evaluate model performance using a variation of few-shot and zero-shot prompting. With few-shot prompting, you provide the model with a number of concrete examples (three for 3-shot, five for 5-shot, etc.) of how to solve a specific task. This demonstrates the model’s ability to learn from example, called in-context learning. With zero-shot prompting on the other hand, you evaluate a model’s ability to perform tasks by relying only on its preexisting knowledge and general language understanding without providing any examples.

Get started with Amazon Titan Text Premier
To enable access to Amazon Titan Text Premier, navigate to the Amazon Bedrock console and choose Model access on the bottom left pane. On the Model access overview page, choose the Manage model access button in the upper right corner and enable access to Amazon Titan Text Premier.

To use Amazon Titan Text Premier in the Bedrock console, choose Text or Chat under Playgrounds in the left menu pane. Then choose Select model and select Amazon as the category and Titan Text Premier as the model. To explore the model, you can load examples. The following screenshot shows one of those examples that demonstrates the model’s chain of thought (CoT) and reasoning capabilities.

By choosing View API request, you can get a code example of how to invoke the model using the AWS Command Line Interface (AWS CLI) with the current example prompt. You can also access Amazon Bedrock and available models using the AWS SDKs. In the following example, I will use the AWS SDK for Python (Boto3).

Amazon Titan Text Premier in action
For this demo, I ask Amazon Titan Text Premier to summarize one of my previous AWS News Blog posts that announced the availability of Amazon Titan Image Generator and the watermark detection feature.

For summarization tasks, a recommended prompt template looks like this:

The following is text from a :

Summarize the  in 

For more prompting best practices, check out the Amazon Titan Text Prompt Engineering Guidelines.

I adapt this template to my example and define the prompt. In preparation, I saved my News Blog post as a text file and read it into the post string variable.

prompt = """
The following is text from a AWS News Blog post:

<text>
%s
</text>

Summarize the above AWS News Blog post in a short paragraph.
""" % post

Similar to previous Amazon Titan Text models, Amazon Titan Text Premier supports temperature and topP inference parameters to control the randomness and diversity of the response, as well as maxTokenCount and stopSequences to control the length of the response.

import boto3
import json

bedrock_runtime = boto3.client(service_name="bedrock-runtime")

body = json.dumps({
    "inputText": prompt, 
    "textGenerationConfig":{  
        "maxTokenCount":256,
        "stopSequences":[],
        "temperature":0,
        "topP":0.9
    }
})

Then, I use the InvokeModel API to send the inference request.

response = bedrock_runtime.invoke_model(
    body=body,
        modelId="amazon.titan-text-premier-v1:0",
    accept="application/json", 
    contentType="application/json"
)

response_body = json.loads(response.get('body').read())
print(response_body.get('results')[0].get('outputText'))

And here’s the response:

Amazon Titan Image Generator is now generally available in Amazon Bedrock, giving you an easy way to build and scale generative AI applications with new image generation and image editing capabilities, including instant customization of images. Watermark detection for Titan Image Generator is now generally available in the Amazon Bedrock console. Today, we’re also introducing a new DetectGeneratedContent API (preview) in Amazon Bedrock that checks for the existence of this watermark and helps you confirm whether an image was generated by Titan Image Generator.

For more examples in different programming languages, check out the code examples section in the Amazon Bedrock User Guide.

More resources
Here are some additional resources that you might find helpful:

Intended use cases and more — Check out the AWS AI Service Card for Amazon Titan Text Premier to learn more about the models’ intended use cases, design, and deployment, as well as performance optimization best practices.

AWS Generative AI CDK Constructs — Amazon Titan Text Premier is supported by the AWS Generative AI CDK Constructs, an open source extension of the AWS Cloud Development Kit (AWS CDK), providing sample implementations of AWS CDK for common generative AI patterns.

Amazon Titan models — If you’re curious to learn more about Amazon Titan models in general, check out the following video. Dr. Sherry Marcus, Director of Applied Science for Amazon Bedrock, shares how the Amazon Titan family of models incorporates the 25 years of experience Amazon has innovating with AI and machine learning (ML) across its business.

Now available
Amazon Titan Text Premier is available today in the AWS US East (N. Virginia) Region. Custom fine-tuning for Amazon Titan Text Premier is available today in preview in the AWS US East (N. Virginia) Region. Check the full Region list for future updates. To learn more about the Amazon Titan family of models, visit the Amazon Titan product page. For pricing details, review the Amazon Bedrock pricing page.

Give Amazon Titan Text Premier a try in the Amazon Bedrock console today, send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS contacts, and engage with the generative AI builder community at community.aws.

— Antje

from AWS News Blog https://ift.tt/OLKMuT6
via IFTTT

Build generative AI applications with Amazon Bedrock Studio (preview)

Today, we’re introducing Amazon Bedrock Studio, a new web-based generative artificial intelligence (generative AI) development experience, in public preview. Amazon Bedrock Studio accelerates the development of generative AI applications by providing a rapid prototyping environment with key Amazon Bedrock features, including Knowledge Bases, Agents, and Guardrails.

As a developer, you can now use your company’s single sign-on credentials to sign in to Bedrock Studio and start experimenting. You can build applications using a wide array of top performing models, evaluate, and share your generative AI apps within Bedrock Studio. The user interface guides you through various steps to help improve a model’s responses. You can experiment with model settings, and securely integrate your company data sources, tools, and APIs, and set guardrails. You can collaborate with team members to ideate, experiment, and refine your generative AI applications—all without requiring advanced machine learning (ML) expertise or AWS Management Console access.

As an Amazon Web Services (AWS) administrator, you can be confident that developers will only have access to the features provided by Bedrock Studio, and won’t have broader access to AWS infrastructure and services.

Now, let me show you how to get started with Amazon Bedrock Studio.

Get started with Amazon Bedrock Studio
As an AWS administrator, you first need to create an Amazon Bedrock Studio workspace, then select and add users you want to give access to the workspace. Once the workspace is created, you can share the workspace URL with the respective users. Users with access privileges can sign in to the workspace using single sign-on, create projects within their workspace, and start building generative AI applications.

Create Amazon Bedrock Studio workspace
Navigate to the Amazon Bedrock console and choose Bedrock Studio on the bottom left pane.

Before creating a workspace, you need to configure and secure the single sign-on integration with your identity provider (IdP) using the AWS IAM Identity Center. For detailed instructions on how to configure various IdPs, such as AWS Directory Service for Microsoft Active Directory, Microsoft Entra ID, or Okta, check out the AWS IAM Identity Center User Guide. For this demo, I configured user access with the default IAM Identity Center directory.

Next, choose Create workspace, enter your workspace details, and create any required AWS Identity and Access Management (IAM) roles.

If you want, you can also select default generative AI models and embedding models for the workspace. Once you’re done, choose Create.

Next, select the created workspace.

Then, choose User management and Add users or groups to select the users you want to give access to this workspace.

Back in the Overview tab, you can now copy the Bedrock Studio URL and share it with your users.

Build generative AI applications using Amazon Bedrock Studio
As a builder, you can now navigate to the provided Bedrock Studio URL and sign in with your single sign-on user credentials. Welcome to Amazon Bedrock Studio! Let me show you how to choose from industry leading FMs, bring your own data, use functions to make API calls, and safeguard your applications using guardrails.

Choose from multiple industry leading FMs
By choosing Explore, you can start selecting available FMs and explore the models using natural language prompts.

If you choose Build, you can start building generative AI applications in a playground mode, experiment with model configurations, iterate on system prompts to define the behavior of your application, and prototype new features.

Bring your own data
With Bedrock Studio, you can securely bring your own data to customize your application by providing a single file or by selecting a knowledge base created in Amazon Bedrock.

Use functions to make API calls and make model responses more relevant
A function call allows the FM to dynamically access and incorporate external data or capabilities when responding to a prompt. The model determines which function it needs to call based on an OpenAPI schema that you provide.

Functions enable a model to include information in its response that it doesn’t have direct access to or prior knowledge of. For example, a function could allow the model to retrieve and include the current weather conditions in its response, even though the model itself doesn’t have that information stored.

Safeguard your applications using Guardrails for Amazon Bedrock
You can create guardrails to promote safe interactions between users and your generative AI applications by implementing safeguards customized to your use cases and responsible AI policies.

When you create applications in Amazon Bedrock Studio, the corresponding managed resources such as knowledge bases, agents, and guardrails are automatically deployed in your AWS account. You can use the Amazon Bedrock API to access those resources in downstream applications.

Here’s a short demo video of Amazon Bedrock Studio created by my colleague Banjo Obayomi.

Join the preview
Amazon Bedrock Studio is available today in public preview in AWS Regions US East (N. Virginia) and US West (Oregon). To learn more, visit the Amazon Bedrock Studio page and User Guide.

Give Amazon Bedrock Studio a try today and let us know what you think! Send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS contacts, and engage with the generative AI builder community at community.aws.

— Antje

from AWS News Blog https://ift.tt/OtWxPw8
via IFTTT

AWS Weekly Roundup: Amazon Q, Amazon QuickSight, AWS CodeArtifact, Amazon Bedrock, and more (May 6, 2024)

April has been packed with new releases! Last week continued that trend with many new releases supporting a variety of domains such as security, analytics, devops, and many more, as well as more exciting new capabilities within generative AI.

If you missed the AWS Summit London 2024, you can now watch the sessions on demand, including the keynote by Tanuja Randery, VP & Marketing Director, EMEA, and many of the break-out sessions which will continue to be released over the coming weeks.

Last week’s launches
Here are some of the highlights that caught my attention this week:

Manual and automatic rollback from any stage in AWS CodePipeline – You can now rollback any stage, other than Source, to any previously known good state in if you use a V2 pipeline in AWS CodePipeline. You can configure automatic rollback which will use the source changes from the most recent successful pipeline execution in the case of failure, or you can initiate a manual rollback for any stage from the console, API or SDK and choose which pipeline execution you want to use for the rollback.

AWS CodeArtifact now supports RubyGems – Ruby community, rejoice, you can now store your gems in AWS CodeArtifact! You can integrate it with RubyGems.org, and CodeArtifact will automatically fetch any gems requested by the client and store them locally in your CodeArtifact repository. That means that you can have a centralized place for both your first-party and public gems so developers can access their dependencies from a single source.

Create a repository in AWS CodeArtifact and choose “rubygems-store” to connect your repository to RubyGems.org on the “Public upstream repositories” dropdown.

Amazon EventBridge Pipes now supports event delivery through AWS PrivateLink – You can now deliver events to an Amazon EventBridge Pipes target without traversing the public internet by using AWS PrivateLink. You can poll for events in a private subnet in your Amazon Virtual Private Cloud (VPC) without having to deploy any additional infrastructure to keep your traffic private.

Amazon Bedrock launches continue. You can now run scalable, enterprise-grade generative AI workloads with Cohere Command R & R+. And Amazon Titan Text V2 is now optimized for improving Retrieval-Augmented Generation (RAG).

AWS Trusted Advisor – last year we launched Trusted Advisor APIs enabling you to programmatically consume recommendations. A new API is available now that you can use to exclude resources from recommendations.

Amazon EC2 – there have been two new great launches this week for EC2 users. You can now mark your AMIs as “protected” to avoid them being deregistered by accident. You can also now easily discover your active AMIs by simply describing them.

Amazon CodeCatalyst – you can now view your git commit history in the CodeCatalyst console.

General Availability
Many new services and capabilities became generally available this week.

Amazon Q in QuickSight – Amazon Q has brought generative BI to Amazon QuickSight giving you the ability to build beautiful dashboards automatically simply by using natural language and it’s now generally available. To get started, head to the Quicksight Pricing page to explore all options or start a 30-day free trial which allows up to 4 users per QuickSight account to use all the new generative AI features.

With the new generative AI features enabled by Amazon Q in Amazon QuickSight you can use natural language queries to build, sort and filter dashboards. (source: AWS Documentation)

Amazon Q Business (GA) and Amazon Q Apps (Preview) – Also generally available now is Amazon Q Business which we launched last year at AWS re:Invent 2023 with the ability to connect seamlessly with over 40 popular enterprise systems, including Microsoft 365, Salesforce, Amazon Simple Storage Service (Amazon S3), Gmail, and so many more. This allows Amazon Q Business to know about your business so your employees can generate content, solve problems, and take actions that are specific to your business.

We have also launched support for custom plug-ins, so now you can create your own integrations with any third-party application.

With general availability of Amazon Q Business we have also launched the ability to create your own custom plugins to connect to any third-party API.

Another highlight of this release is the launch of Amazon Q Apps, which enables you to quickly generate an app from your conversation with Amazon Q Business, or by describing what you would like it to generate for you. All guardrails from Amazon Q Business apply, and it’s easy to share your apps with colleagues through an admin-managed library. Amazon Q Apps is in preview now.

Check out Channy Yun’s post for a deeper dive into Amazon Q Business and Amazon Q Apps, which guides you through these new features.

Amazon Q Developer – you can use Q Developer to completely change your developer flow. It has all the capabilities of what was previously known as Amazon CodeWhisperer, such as Q&A, diagnosing common errors, generating code including tests, and many more. Now it has expanded, so you can use it to generate SQL, and build data integration pipelines using natural language. In preview, it can describe resources in your AWS account and help you retrieve and analyze cost data from AWS Cost Explorer.

For a full list of AWS announcements, be sure to keep an eye on the ‘What’s New with AWS?‘ page.

Other AWS news
Here are some additional projects, blog posts, and news items that you might find interesting:

AWS open source news and updates – My colleague Ricardo writes about open source projects, tools, and events from the AWS Community.

Discover Claude 3 – If you’re a developer looking for a good source to get started with Claude 3 them I recommend this great post from my colleague Haowen Huang: Mastering Amazon Bedrock with Claude 3: Developer’s Guide with Demos.

Upcoming AWS events
Check your calendars and sign up for upcoming AWS events:

AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Singapore (May 7), Seoul (May 16–17), Hong Kong (May 22), Milan (May 23), Stockholm (June 4), and Madrid (June 5).

AWS re:Inforce – Explore 2.5 days of immersive cloud security learning in the age of generative AI at AWS re:Inforce, June 10–12 in Pennsylvania.

AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Turkey (May 18), Midwest | Columbus (June 13), Sri Lanka (June 27), Cameroon (July 13), Nigeria (August 24), and New York (August 28).

GOTO EDA Day London – Join us in London on May 14 to learn about event-driven architectures (EDA) for building highly scalable, fault tolerant, and extensible applications. This conference is organized by GOTO, AWS, and partners.

Browse all upcoming AWS led in-person and virtual events and developer-focused events.

That’s all for this week. Check back next Monday for another Weekly Roundup!

— Matheus Guimaraes

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

from AWS News Blog https://ift.tt/tGO8NiS
via IFTTT

Build RAG applications with MongoDB Atlas, now available in Knowledge Bases for Amazon Bedrock

Foundational models (FMs) are trained on large volumes of data and use billions of parameters. However, in order to answer customers’ questions related to domain-specific private data, they need to reference an authoritative knowledge base outside of the model’s training data sources. This is commonly achieved using a technique known as Retrieval Augmented Generation (RAG). By fetching data from the organization’s internal or proprietary sources, RAG extends the capabilities of FMs to specific domains, without needing to retrain the model. It is a cost-effective approach to improving model output so it remains relevant, accurate, and useful in various contexts.

Knowledge Bases for Amazon Bedrock is a fully managed capability that helps you implement the entire RAG workflow from ingestion to retrieval and prompt augmentation without having to build custom integrations to data sources and manage data flows.

Today, we are announcing the availability of MongoDB Atlas as a vector store in Knowledge Bases for Amazon Bedrock. With MongoDB Atlas vector store integration, you can build RAG solutions to securely connect your organization’s private data sources to FMs in Amazon Bedrock. This integration adds to the list of vector stores supported by Knowledge Bases for Amazon Bedrock, including Amazon Aurora PostgreSQL-Compatible Edition, vector engine for Amazon OpenSearch Serverless, Pinecone, and Redis Enterprise Cloud.

Build RAG applications with MongoDB Atlas and Knowledge Bases for Amazon Bedrock
Vector Search in MongoDB Atlas is powered by the vectorSearch index type. In the index definition, you must specify the field that contains the vector data as the vector type. Before using MongoDB Atlas vector search in your application, you will need to create an index, ingest source data, create vector embeddings and store them in a MongoDB Atlas collection. To perform queries, you will need to convert the input text into a vector embedding, and then use an aggregation pipeline stage to perform vector search queries against fields indexed as the vector type in a vectorSearch type index.

Thanks to the MongoDB Atlas integration with Knowledge Bases for Amazon Bedrock, most of the heavy lifting is taken care of. Once the vector search index and knowledge base are configured, you can incorporate RAG into your applications. Behind the scenes, Amazon Bedrock will convert your input (prompt) into embeddings, query the knowledge base, augment the FM prompt with the search results as contextual information and return the generated response.

Let me walk you through the process of setting up MongoDB Atlas as a vector store in Knowledge Bases for Amazon Bedrock.

Configure MongoDB Atlas
Start by creating a MongoDB Atlas cluster on AWS. Choose an M10 dedicated cluster tier. Once the cluster is provisioned, create a database and collection. Next, create a database user and grant it the Read and write to any database role. Select Password as the Authentication Method. Finally, configure network access to modify the IP Access List – add IP address 0.0.0.0/0 to allow access from anywhere.

Use the following index definition to create the Vector Search index:

{
  "fields": [
    {
      "numDimensions": 1536,
      "path": "AMAZON_BEDROCK_CHUNK_VECTOR",
      "similarity": "cosine",
      "type": "vector"
    },
    {
      "path": "AMAZON_BEDROCK_METADATA",
      "type": "filter"
    },
    {
      "path": "AMAZON_BEDROCK_TEXT_CHUNK",
      "type": "filter"
    }
  ]
}

Configure the knowledge base
Create an AWS Secrets Manager secret to securely store the MongoDB Atlas database user credentials. Choose Other as the Secret type. Create an Amazon Simple Storage Service (Amazon S3) storage bucket and upload the Amazon Bedrock documentation user guide PDF. Later, you will use the knowledge base to ask questions about Amazon Bedrock.

You can also use another document of your choice because Knowledge Base supports multiple file formats (including text, HTML, and CSV).

Navigate to the Amazon Bedrock console and refer to the Amzaon Bedrock User Guide to configure the knowledge base. In the Select embeddings model and configure vector store, choose Titan Embeddings G1 – Text as the embedding model. From the list of databases, choose MongoDB Atlas.

Enter the basic information for the MongoDB Atlas cluster (Hostname, Database name, etc.) as well as the ARN of the AWS Secrets Manager secret you had created earlier. In the Metadata field mapping attributes, enter the vector store specific details. They should match the vector search index definition you used earlier.

Initiate the knowledge base creation. Once complete, synchronise the data source (S3 bucket data) with the MongoDB Atlas vector search index.

Once the synchronization is complete, navigate to MongoDB Atlas to confirm that the data has been ingested into the collection you created.

Notice the following attributes in each of the MongoDB Atlas documents:

• AMAZON_BEDROCK_TEXT_CHUNK – Contains the raw text for each data chunk.
• AMAZON_BEDROCK_CHUNK_VECTOR – Contains the vector embedding for the data chunk.
• AMAZON_BEDROCK_METADATA – Contains additional data for source attribution and rich query capabilities.

Test the knowledge base
It’s time to ask questions about Amazon Bedrock by querying the knowledge base. You will need to choose a foundation model. I picked Claude v2 in this case and used “What is Amazon Bedrock” as my input (query).

If you are using a different source document, adjust the questions accordingly.

You can also change the foundation model. For example, I switched to Claude 3 Sonnet. Notice the difference in the output and select Show source details to see the chunks cited for each footnote.

Integrate knowledge base with applications
To build RAG applications on top of Knowledge Bases for Amazon Bedrock, you can use the RetrieveAndGenerate API which allows you to query the knowledge base and get a response.

Here is an example using the AWS SDK for Python (Boto3):

import boto3

bedrock_agent_runtime = boto3.client(
    service_name = "bedrock-agent-runtime"
)

def retrieveAndGenerate(input, kbId):
    return bedrock_agent_runtime.retrieve_and_generate(
        input={
            'text': input
        },
        retrieveAndGenerateConfiguration={
            'type': 'KNOWLEDGE_BASE',
            'knowledgeBaseConfiguration': {
                'knowledgeBaseId': kbId,
                'modelArn': 'arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-sonnet-20240229-v1:0'
                }
            }
        )

response = retrieveAndGenerate("What is Amazon Bedrock?", "BFT0P4NR1U")["output"]["text"]

If you want to further customize your RAG solutions, consider using the Retrieve API, which returns the semantic search responses that you can use for the remaining part of the RAG workflow.

import boto3

bedrock_agent_runtime = boto3.client(
    service_name = "bedrock-agent-runtime"
)

def retrieve(query, kbId, numberOfResults=5):
    return bedrock_agent_runtime.retrieve(
        retrievalQuery= {
            'text': query
        },
        knowledgeBaseId=kbId,
        retrievalConfiguration= {
            'vectorSearchConfiguration': {
                'numberOfResults': numberOfResults
            }
        }
    )

response = retrieve("What is Amazon Bedrock?", "BGU0Q4NU0U")["retrievalResults"]

Things to know

• MongoDB Atlas cluster tier – This integration requires requires an Atlas cluster tier of at least M10.
• AWS PrivateLink – For the purposes of this demo, MongoDB Atlas database IP Access List was configured to allow access from anywhere. For production deployments, AWS PrivateLink is the recommended way to have Amazon Bedrock establish a secure connection to your MongoDB Atlas cluster. Refer to the Amazon Bedrock User guide (under MongoDB Atlas) for details.
• Vector embedding size – The dimension size of the vector index and the embedding model should be the same. For example, if you plan to use Cohere Embed (which has a dimension size of 1024) as the embedding model for the knowledge base, make sure to configure the vector search index accordingly.
• Metadata filters – You can add metadata for your source files to retrieve a well-defined subset of the semantically relevant chunks based on applied metadata filters. Refer to the documentation to learn more about how to use metadata filters.

Now available
MongoDB Atlas vector store in Knowledge Bases for Amazon Bedrock is available in the US East (N. Virginia) and US West (Oregon) Regions. Be sure to check the full Region list for future updates.

Learn more

• MongoDB Atlas on AWS Marketplace
• Knowledge Bases for Amazon Bedrock product page
• Knowledge Bases for Amazon Bedrock documentation

Try out the MongoDB Atlas integration with Knowledge Bases for Amazon Bedrock! Send feedback to AWS re:Post for Amazon Bedrock or through your usual AWS contacts and engage with the generative AI builder community at community.aws.

— Abhishek

from AWS News Blog https://ift.tt/sND2eXI
via IFTTT

Stop the CNAME chain struggle: Simplified management with Route 53 Resolver DNS Firewall

Starting today, you can configure your DNS Firewall to automatically trust all domains in a resolution chain (such as aCNAME, DNAME, or Alias chain).

Let’s walk through this in nontechnical terms for those unfamiliar with DNS.

Why use DNS Firewall?
DNS Firewall provides protection for outbound DNS requests from your private network in the cloud (Amazon Virtual Private Cloud (Amazon VPC)). These requests route through Amazon Route 53 Resolver for domain name resolution. Firewall administrators can configure rules to filter and regulate the outbound DNS traffic.

DNS Firewall helps to protect against multiple security risks.

Let’s imagine a malicious actor managed to install and run some code on your Amazon Elastic Compute Cloud (Amazon EC2) instances or containers running inside one of your virtual private clouds (VPCs). The malicious code is likely to initiate outgoing network connections. It might do so to connect to a command server and receive commands to execute on your machine. Or it might initiate connections to a third-party service in a coordinated distributed denial of service (DDoS) attack. It might also try to exfiltrate data it managed to collect on your network.

Fortunately, your network and security groups are correctly configured. They block all outgoing traffic except the one to well-known API endpoints used by your app. So far so good—the malicious code cannot dial back home using regular TCP or UDP connections.

But what about DNS traffic? The malicious code may send DNS requests to an authoritative DNS server they control to either send control commands or encoded data, and it can receive data back in the response. I’ve illustrated the process in the following diagram.

To prevent these scenarios, you can use a DNS Firewall to monitor and control the domains that your applications can query. You can deny access to the domains that you know to be bad and allow all other queries to pass through. Alternately, you can deny access to all domains except those you explicitly trust.

What is the challenge with CNAME, DNAME, and Alias records?
Imagine you configured your DNS Firewall to allow DNS queries only to specific well-known domains and blocked all others. Your application communicates with alexa.amazon.com; therefore, you created a rule allowing DNS traffic to resolve that hostname.

However, the DNS system has multiple types of records. The ones of interest in this article are

• A records that map a DNS name to an IP address,
• CNAME records that are synonyms for other DNS names,
• DNAME records that provide redirection from a part of the DNS name tree to another part of the DNS name tree, and
• Alias records that provide a Route 53 specific extension to DNS functionality. Alias records let you route traffic to selected AWS resources, such as Amazon CloudFront distributions and Amazon S3 buckets

When querying alexa.amazon.com, I see it’s actually a CNAME record that points to pitangui.amazon.com, which is another CNAME record that points to tp.5fd53c725-frontier.amazon.com, which, in turn, is a CNAME to d1wg1w6p5q8555.cloudfront.net. Only the last name (d1wg1w6p5q8555.cloudfront.net) has an A record associated with an IP address 3.162.42.28. The IP address is likely to be different for you. It points to the closest Amazon CloudFront edge location, likely the one from Paris (CDG52) for me.

A similar redirection mechanism happens when resolving DNAME or Alias records.

To allow the complete resolution of such a CNAME chain, you could be tempted to configure your DNS Firewall rule to allow all names under amazon.com (*.amazon.com), but that would fail to resolve the last CNAME that goes to cloudfront.net.

Worst, the DNS CNAME chain is controlled by the service your application connects to. The chain might change at any time, forcing you to manually maintain the list of rules and authorized domains inside your DNS Firewall rules.

Introducing DNS Firewall redirection chain authorization
Based on this explanation, you’re now equipped to understand the new capability we launch today. We added a parameter to the UpdateFirewallRule API (also available on the AWS Command Line Interface (AWS CLI) and AWS Management Console) to configure the DNS Firewall so that it follows and automatically trusts all the domains in a CNAME, DNAME, or Alias chain.

This parameter allows firewall administrators to only allow the domain your applications query. The firewall will automatically trust all intermediate domains in the chain until it reaches the A record with the IP address.

Let’s see it in action
I start with a DNS Firewall already configured with a domain list, a rule group, and a rule that ALLOW queries for the domain alexa.amazon.com. The rule group is attached to a VPC where I have an EC2 instance started.

When I connect to that EC2 instance and issue a DNS query to resolve alexa.amazon.com, it only returns the first name in the domain chain (pitangui.amazon.com) and stops there. This is expected because pitangui.amazon.com is not authorized to be resolved.

To solve this, I update the firewall rule to trust the entire redirection chain. I use the AWS CLI to call the update-firewall-rule API with a new parameter firewall-domain-redirection-action set to TRUST_REDIRECTION_DOMAIN.

The following diagram illustrates the setup at this stage.

Back to the EC2 instance, I try the DNS query again. This time, it works. It resolves the entire redirection chain, down to the IP address .

Thanks to the trusted chain redirection, network administrators now have an easy way to implement a strategy to block all domains and authorize only known domains in their DNS Firewall without having to care about CNAME, DNAME, or Alias chains.

This capability is available at no additional cost in all AWS Regions. Try it out today!

-- seb

from AWS News Blog https://ift.tt/e7MpBtm
via IFTTT