|
Right this moment, we’re introducing Amazon Bedrock Studio, a brand new web-based generative synthetic intelligence (generative AI) growth expertise, in public preview. Amazon Bedrock Studio accelerates the event of generative AI purposes by offering a speedy prototyping atmosphere with key Amazon Bedrock options, together with Data Bases, Brokers, and Guardrails.
As a developer, now you can use your organization’s single sign-on credentials to register to Bedrock Studio and begin experimenting. You possibly can construct purposes utilizing a wide selection of high performing fashions, consider, and share your generative AI apps inside Bedrock Studio. The person interface guides you thru numerous steps to assist enhance a mannequin’s responses. You possibly can experiment with mannequin settings, and securely combine your organization information sources, instruments, and APIs, and set guardrails. You possibly can collaborate with crew members to ideate, experiment, and refine your generative AI purposes—all with out requiring superior machine studying (ML) experience or AWS Administration Console entry.
As an Amazon Internet Companies (AWS) administrator, you could be assured that builders will solely have entry to the options supplied by Bedrock Studio, and received’t have broader entry to AWS infrastructure and providers.
Now, let me present you how you can get began with Amazon Bedrock Studio.
Get began with Amazon Bedrock Studio
As an AWS administrator, you first must create an Amazon Bedrock Studio workspace, then choose and add customers you wish to give entry to the workspace. As soon as the workspace is created, you’ll be able to share the workspace URL with the respective customers. Customers with entry privileges can register to the workspace utilizing single sign-on, create tasks inside their workspace, and begin constructing generative AI purposes.
Create Amazon Bedrock Studio workspace
Navigate to the Amazon Bedrock console and select Bedrock Studio on the underside left pane.
Earlier than making a workspace, that you must configure and safe the one sign-on integration along with your id supplier (IdP) utilizing the AWS IAM Identification Middle. For detailed directions on how you can configure numerous IdPs, reminiscent of AWS Listing Service for Microsoft Lively Listing, Microsoft Entra ID, or Okta, take a look at the AWS IAM Identification Middle Consumer Information. For this demo, I configured person entry with the default IAM Identification Middle listing.
Subsequent, select Create workspace, enter your workspace particulars, and create any required AWS Identification and Entry Administration (IAM) roles.
If you would like, you can too choose default generative AI fashions and embedding fashions for the workspace. When you’re achieved, select Create.
Subsequent, choose the created workspace.
Then, select Consumer administration and Add customers or teams to pick out the customers you wish to give entry to this workspace.
Again within the Overview tab, now you can copy the Bedrock Studio URL and share it along with your customers.
Construct generative AI purposes utilizing Amazon Bedrock Studio
As a builder, now you can navigate to the supplied Bedrock Studio URL and register along with your single sign-on person credentials. Welcome to Amazon Bedrock Studio! Let me present you the way to select from trade main FMs, convey your personal information, use capabilities to make API calls, and safeguard your purposes utilizing guardrails.
Select from a number of trade main FMs
By selecting Discover, you can begin choosing out there FMs and discover the fashions utilizing pure language prompts.
If you happen to select Construct, you can begin constructing generative AI purposes in a playground mode, experiment with mannequin configurations, iterate on system prompts to outline the conduct of your software, and prototype new options.
Convey your personal information
With Bedrock Studio, you’ll be able to securely convey your personal information to customise your software by offering a single file or by choosing a information base created in Amazon Bedrock.
Use capabilities to make API calls and make mannequin responses extra related
A perform name permits the FM to dynamically entry and incorporate exterior information or capabilities when responding to a immediate. The mannequin determines which perform it must name based mostly on an OpenAPI schema that you simply present.
Capabilities allow a mannequin to incorporate data in its response that it doesn’t have direct entry to or prior information of. For instance, a perform might enable the mannequin to retrieve and embody the present climate circumstances in its response, though the mannequin itself doesn’t have that data saved.
Safeguard your purposes utilizing Guardrails for Amazon Bedrock
You possibly can create guardrails to advertise secure interactions between customers and your generative AI purposes by implementing safeguards custom-made to your use circumstances and accountable AI insurance policies.
Once you create purposes in Amazon Bedrock Studio, the corresponding managed assets reminiscent of information bases, brokers, and guardrails are robotically deployed in your AWS account. You should utilize the Amazon Bedrock API to entry these assets in downstream purposes.
Right here’s a brief demo video of Amazon Bedrock Studio created by my colleague Banjo Obayomi.
Be part of the preview
Amazon Bedrock Studio is offered at the moment in public preview in AWS Areas US East (N. Virginia) and US West (Oregon). To study extra, go to the Amazon Bedrock Studio web page and Consumer Information.
Give Amazon Bedrock Studio a attempt at the moment and tell us what you assume! Ship suggestions to AWS re:Publish for Amazon Bedrock or by means of your regular AWS contacts, and interact with the generative AI builder neighborhood at neighborhood.aws.
— Antje
Could 7, 2024: Up to date screenshots on this put up to replicate latest updates to the UI.
