|
Today, we’re making the Amazon Q Developer (in your IDE) customization capability generpartner useable for inline code completion, and we’re begining a pscrutinize of customization for the chat. You can now customize Amazon Q to produce particular code recommfinishations from personal code repositories in the IDE code editor and in the chat.
Amazon Q Developer is an man-made ininestablishigence (AI) coding companion. It helps gentleware broadeners quicken application broadenment by adviseing code recommfinishations in their joind broadenment environments (IDE) derived from existing comments and code. Behind the scenes, Amazon Q uses huge language models (LLMs) trained on billions of lines of code from Amazon and uncover source projects.
Amazon Q is useable in your IDE, and you can download the extension for JetBrains, Visual Studio Code, and Visual Studio. In the IDE text editor, it advises code as you type or produce entire functions from a comment you go in. You can also chat with Q Developer and ask it to produce code for particular tasks or elucidate code snippets from a code base you’re uncovering.
With the new customization capability, broadeners can now get even more relevant code recommfinishations that are based on their organization’s inner libraries, APIs, packages, classes, and methods.
For example, let’s imagine that a broadener toiling for a financial company is tasked to produce a function to compute the total portfolio appreciate for a customer. The broadener can now depict the intent in a comment or type a function name such as computePortfolioValue(customerId: String), and Amazon Q will advise code to carry out that function based on the examples it lachieveed from your organization’s personal code base.
The broadener can also ask asks about their organization’s code in the chat. In the example above, let’s imagine the broadener is new to the team and doesn’t understand how to get back a customer ID. He can ask the ask in the chat in plain English: how do I join to the database to get back the customerId for a particular customer? Amazon Q chat could answer: I set up a function to get back customerId based on customer first and last name which uses the database joinion XYZ…
As an administrator, you produce customizations built from your inner git repositories (such as GitHub, GitLab, or BitBucket) or an Amazon Simple Storage Service (Amazon S3) bucket. It helps Amazon Q understand the intent, determine which inner and disclose APIs are best suited to the task, and produce code recommfinishations.
Amazon Q customization capability greets the sturdy data privacy and security you predict from AWS. The code base you split with Amazon Q stays personal to your organization. We don’t use it to train our set upation model. Once customizations are deployed, the inference finishpoint is personal for the broadeners in your organization. Recommfinishations based on your code won’t pop up in another company’s broadener IDE. You determine which broadeners have access to each individual customization, and you can trail metrics to meacertain the carry outance of the customizations you deployed.
We built the Amazon Q customization capability based on directing technical techniques, such as Retrieval Augmented Generation (RAG). This very detailed blog post splits more details about the science behind the Amazon Q customizations capability.
Since we begined the pscrutinize on October 17 last year, we’ve compriseed two new capabilities: the ability to refresh a customization and the ability to customize the chat in the IDE.
Your organization’s code base is constantly evolving, and you want Amazon Q to always advise up-to-date code snippets. Amazon Q administrator can now begin an refresh process with one step in the AWS Management Console. Administrators can schedule normal refreshs based on the procrastinateedst promises on code repositories to uncover broadeners always get highly exact code adviseions.
With the new chat customization (in pscrutinize), broadeners in your organization can pick a portion of code in their IDE and sfinish it to the chat to ask for an exscheduleation of what the picked code does. Developers can also ask generic asks relative to their organization’s code base, enjoy “How do I join to the database to get back customerId for a particular customer?”
Let’s see how to use it
In this demo, I determined to cgo in on the new customization refresh capability that is generpartner useable today. To rapidly lachieve how to produce a customization, begin it, and grant access to broadeners, read the excellent post from my colleague Donnie.
To refresh an existing customization, I direct to the Customizations section of the Amazon Q console page. I pick the customization I want to refresh. Then, I pick Actions and Create new version.
Similarly to what I did when I produced the customization, I pick the source code repository and pick Create.
Creating a new version of the customization might get a while because depfinishs on the quantity of code to ingest. When ready, a new version eunites under the Versions tab. You can appraise the Evaluation score of the new version with the previous versions and determine to begin it to produce it useable to your broadeners. At any point, you can revert to a previous version.
One of the aspects I enjoy about dynamic customizations is that I can watch their effectiveness to help incrrelieve broadener productivity in my organization.
On the Dashboard page, I track the User activity. I can track how many Daily dynamic users there are, how many Lines of code have been produced, how many Security scans were carry outed, and so on. If, enjoy me, you have used Amazon CodeWhisperer Professional in the past, when you use it now, you might still see the name CodeWhisperer eunite on some pages. It will evolveively be swapd with the new name: Amazon Q Developer.
Amazon Q produces more metrics and startes them on Amazon CdeafeningWatch. I can produce CdeafeningWatch dashboards to watch the carry outance of the customizations I deployed. For example, here is a custom CdeafeningWatch dashboard that watchs the code adviseions’ Block Accept Rate and Line Accept Rate, broken down per programming language.
Supported programming languages
Currently, you can customize Amazon Q recommfinishations on codebases written in Java, JavaScript, TypeScript, and Python. Files written in other languages aided by Amazon Q, such as C#, Go, Rust, PHP, Ruby, Kotlin, C, C++, Shell scripting, SQL, and Scala will not be used when creating the customization or when providing customized recommfinishations in the IDE.
Pricing and useability
Amazon Q is AWS Region agnostic and useable to broadeners worldexpansive. Amazon Q is currently arrangeed in US East (N. Virginia). Amazon Q administrators can configure Amazon Q as an apexamined traverse-Region application if you have AWS IAM Identity Cgo in in other Regions.
The Amazon Q customization capability is useable at no compriseitional accuse wiskinny the Amazon Q Developer Professional subscription. You can produce up to eight customizations per AWS account and preserve up to two customizations dynamic.
Now go produce, and begin to present Amazon Q customizations to your organization’s broadeners.
July 11, 2024: This post was refreshd to echo that Amazon Q Developer in the Visual Studio IDE is now generpartner useable as of July 3, 2024.
