mirror of https://github.com/abpframework/abp.git
erdemcaygor
2 months ago
267 changed files with 5921 additions and 2274 deletions
@ -0,0 +1,89 @@ |
|||
# ABP.IO Platform 10.0 Final Has Been Released! |
|||
|
|||
We are glad to announce that [ABP](https://abp.io/) 10.0 stable version has been released today. |
|||
|
|||
## What's New With Version 10.0? |
|||
|
|||
All the new features were explained in detail in the [10.0 RC Announcement Post](https://abp.io/community/announcements/announcing-abp-10-0-release-candidate-86lrnyox), so there is no need to review them again. You can check it out for more details. |
|||
|
|||
## Getting Started with 10.0 |
|||
|
|||
### How to Upgrade an Existing Solution |
|||
|
|||
You can upgrade your existing solutions with either ABP Studio or ABP CLI. In the following sections, both approaches are explained: |
|||
|
|||
### Upgrading via ABP Studio |
|||
|
|||
If you are already using the ABP Studio, you can upgrade it to the latest version. ABP Studio periodically checks for updates in the background, and when a new version of ABP Studio is available, you will be notified through a modal. Then, you can update it by confirming the opened modal. See [the documentation](https://abp.io/docs/latest/studio/installation#upgrading) for more info. |
|||
|
|||
After upgrading the ABP Studio, then you can open your solution in the application, and simply click the **Upgrade ABP Packages** action button to instantly upgrade your solution: |
|||
|
|||
 |
|||
|
|||
### Upgrading via ABP CLI |
|||
|
|||
Alternatively, you can upgrade your existing solution via ABP CLI. First, you need to install the ABP CLI or upgrade it to the latest version. |
|||
|
|||
If you haven't installed it yet, you can run the following command: |
|||
|
|||
```bash |
|||
dotnet tool install -g Volo.Abp.Studio.Cli |
|||
``` |
|||
|
|||
Or to update the existing CLI, you can run the following command: |
|||
|
|||
```bash |
|||
dotnet tool update -g Volo.Abp.Studio.Cli |
|||
``` |
|||
|
|||
After installing/updating the ABP CLI, you can use the [`update` command](https://abp.io/docs/latest/CLI#update) to update all the ABP related NuGet and NPM packages in your solution as follows: |
|||
|
|||
```bash |
|||
abp update |
|||
``` |
|||
|
|||
You can run this command in the root folder of your solution to update all ABP related packages. |
|||
|
|||
## Migration Guides |
|||
|
|||
There are a few breaking changes in this version that may affect your application. Please read the migration guide carefully, if you are upgrading from v9.x: [ABP Version 10.0 Migration Guide](https://abp.io/docs/10.0/release-info/migration-guides/abp-10-0) |
|||
|
|||
## Community News |
|||
|
|||
### New ABP Community Articles |
|||
|
|||
As always, exciting articles have been contributed by the ABP community. I will highlight some of them here: |
|||
|
|||
* [Alper Ebiçoğlu](https://abp.io/community/members/alper) |
|||
* [Optimize your .NET app for production Part 1](https://abp.io/community/articles/optimize-your-dotnet-app-for-production-for-any-.net-app-wa24j28e) |
|||
* [Optimize your .NET app for production Part 2](https://abp.io/community/articles/optimize-your-dotnet-app-for-production-for-any-.net-app-2-78xgncpi) |
|||
* [Return Code vs Exceptions: Which One is Better?](https://abp.io/community/articles/return-code-vs-exceptions-which-one-is-better-1rwcu9yi) |
|||
* [Sumeyye Kurtulus](https://abp.io/community/members/sumeyye.kurtulus) |
|||
* [Building Scalable Angular Apps with Reusable UI Components](https://abp.io/community/articles/building-scalable-angular-apps-with-reusable-ui-components-b9npiff3) |
|||
* [Angular Library Linking Made Easy: Paths, Workspaces and Symlinks](https://abp.io/community/articles/angular-library-linking-made-easy-paths-workspaces-and-5z2ate6e) |
|||
* [erdem çaygör](https://abp.io/community/members/erdem.caygor) |
|||
* [Building Dynamic Forms in Angular for Enterprise](https://abp.io/community/articles/building-dynamic-forms-in-angular-for-enterprise-6r3ewpxt) |
|||
* [From Server to Browser: Angular TransferState Explained](https://abp.io/community/articles/from-server-to-browser-angular-transferstate-explained-m99zf8oh) |
|||
* [Mansur Besleney](https://abp.io/community/members/mansur.besleney) |
|||
* [Top 10 Exception Handling Mistakes in .NET](https://abp.io/community/articles/top-10-exception-handling-mistakes-in-net-jhm8wzvg) |
|||
* [Berkan Şaşmaz](https://abp.io/community/members/berkansasmaz) |
|||
* [How to Dynamically Set the Connection String in EF Core](https://abp.io/community/articles/how-to-dynamically-set-the-connection-string-in-ef-core-30k87fpj) |
|||
* [Oğuzhan Ağır](https://abp.io/community/members/oguzhan.agir) |
|||
* [The ASP.NET Core Dependency Injection System](https://abp.io/community/articles/the-asp.net-core-dependency-injection-system-3vbsdhq8) |
|||
* [Selman Koç](https://abp.io/community/members/selmankoc) |
|||
* [5 Things Keep in Mind When Deploying Clustered Environment](https://abp.io/community/articles/5-things-keep-in-mind-when-deploying-clustered-environment-i9byusnv) |
|||
* [Muhammet Ali ÖZKAYA](https://abp.io/community/members/m.aliozkaya) |
|||
* [Repository Pattern in ASP.NET Core](https://abp.io/community/articles/repository-pattern-in-asp.net-core-2dudlg3j) |
|||
* [Armağan Ünlü](https://abp.io/community/members/armagan) |
|||
* [UI/UX Trends That Will Shape 2026](https://abp.io/community/articles/UI-UX-Trends-That-Will-Shape-2026-bx4c2kow) |
|||
* [Salih](https://abp.io/community/members/salih) |
|||
* [What is That Domain Service in DDD for .NET Developers?](https://abp.io/community/articles/what-is-that-domain-service-in-ddd-for-.net-developers-uqnpwjja) |
|||
* [Building an API Key Management System with ABP Framework](https://abp.io/community/articles/building-an-api-key-management-system-with-abp-framework-28gn4efw) |
|||
* [Fahri Gedik](https://abp.io/community/members/fahrigedik) |
|||
* [Signal-Based Forms in Angular](https://abp.io/community/articles/signal-based-forms-in-angular-21-9qentsqs) |
|||
|
|||
Thanks to the ABP Community for all the content they have published. You can also [post your ABP related (text or video) content](https://abp.io/community/posts/create) to the ABP Community. |
|||
|
|||
## About the Next Version |
|||
|
|||
The next feature version will be 10.1. You can follow the [release planning here](https://github.com/abpframework/abp/milestones). Please [submit an issue](https://github.com/abpframework/abp/issues/new) if you have any problems with this version. |
|||
|
After Width: | Height: | Size: 127 KiB |
|
After Width: | Height: | Size: 16 KiB |
@ -0,0 +1,156 @@ |
|||
# Announcing Server-Side Rendering (SSR) Support for ABP Framework Angular Applications |
|||
|
|||
We are pleased to announce that **Server-Side Rendering (SSR)** has become available for ABP Framework Angular applications! This highly requested feature brings major gains in performance, SEO, and user experience to your Angular applications based on ABP Framework. |
|||
|
|||
## What is Server-Side Rendering (SSR)? |
|||
|
|||
Server-Side Rendering refers to an approach which renders your Angular application on the server as opposed to the browser. The server creates the complete HTML for a page and sends it to the client, which can then show the page to the user. This poses many advantages over traditional client-side rendering. |
|||
|
|||
## Why SSR Matters for ABP Angular Applications |
|||
|
|||
### Improved Performance |
|||
- **Quicker visualization of the first contentful paint (FCP)**: Because prerendered HTML is sent over from the server, users will see content quicker. |
|||
- **Better perceived performance**: Even on slower devices, the page will be displaying something sooner. |
|||
- **Less JavaScript parsing time**: For example, the initial page load will not require parsing and executing a large bundle of JavaScript. |
|||
|
|||
### Enhanced SEO |
|||
- **Improved indexing by search engines**: Search engine bots are able to crawl and index your content quicker. |
|||
- **Improved rankings in search**: The quicker the content loads and the easier it is to access, the better your SEO score. |
|||
- **Preview when sharing on social channels**: Rich previews with the appropriate meta tags are generated when sharing links on social platforms. |
|||
|
|||
### Better User Experience |
|||
- **Support for low bandwidth**: Users with slower Internet connections will have a better experience |
|||
- **Progressive enhancement**: Users can start accessing the content before JavaScript has loaded |
|||
- **Better accessibility**: Screen readers and other assistive technologies can access the content immediately |
|||
|
|||
## Getting Started with SSR |
|||
|
|||
### Adding SSR to an Existing Project |
|||
|
|||
You can easily add SSR support to your existing ABP Angular application using the Angular CLI with ABP schematics: |
|||
|
|||
```bash |
|||
# Generate SSR configuration for your project |
|||
ng generate @abp/ng.schematics:ssr-add |
|||
|
|||
# Alternatively, you can use the short form |
|||
ng g @abp/ng.schematics:ssr-add |
|||
``` |
|||
|
|||
If you have multiple projects in your workspace, you can specify which project to add SSR to: |
|||
|
|||
```bash |
|||
ng g @abp/ng.schematics:ssr-add --project=my-project |
|||
``` |
|||
|
|||
If you want to skip the automatic installation of dependencies: |
|||
|
|||
```bash |
|||
ng g @abp/ng.schematics:ssr-add --skip-install |
|||
``` |
|||
|
|||
## What Gets Configured |
|||
|
|||
When you add SSR to your ABP Angular project, the schematic automatically: |
|||
|
|||
1. **Installs necessary dependencies**: Adds `@angular/ssr` and related packages |
|||
2. **Creates Server Configuration**: Creates `server.ts` and related files |
|||
3. **Updates Project Structure**: |
|||
- Creates `main.server.ts` to bootstrap the server |
|||
- Adds `app.config.server.ts` for standalone apps (or `app.module.server.ts` for NgModule apps) |
|||
- Configures server routes in `app.routes.server.ts` |
|||
4. **Updates Build Configuration**: updates `angular.json` to include: |
|||
- a `serve-ssr` target for local SSR development |
|||
- a `prerender` target for static site generation |
|||
- Proper output paths for browser and server bundles |
|||
|
|||
## Supported Configurations |
|||
|
|||
The ABP SSR schematic supports both modern and legacy Angular build configurations: |
|||
|
|||
### Application Builder (Suggested) |
|||
- The new `@angular-devkit/build-angular:application` builder |
|||
- Optimized for Angular 17+ apps |
|||
- Enhanced performance and smaller bundle sizes |
|||
|
|||
### Server Builder (Legacy) |
|||
- The original `@angular-devkit/build-angular:server` builder |
|||
- Designed for legacy Angular applications |
|||
- Compatible with legacy applications |
|||
|
|||
## Running Your SSR Application |
|||
|
|||
After adding SSR to your project, you can run your application in SSR mode: |
|||
|
|||
```bash |
|||
# Development mode with SSR |
|||
ng serve |
|||
|
|||
# Or specifically target SSR development server |
|||
npm run serve:ssr |
|||
|
|||
# Build for production |
|||
npm run build:ssr |
|||
|
|||
# Preview production build |
|||
npm run serve:ssr:production |
|||
``` |
|||
|
|||
## Important Considerations |
|||
|
|||
### Browser-Only APIs |
|||
Some browser APIs are not available on the server. Use platform checks to conditionally execute code: |
|||
|
|||
```typescript |
|||
import { isPlatformBrowser } from '@angular/common'; |
|||
import { PLATFORM_ID, inject } from '@angular/core'; |
|||
|
|||
export class MyComponent { |
|||
private platformId = inject(PLATFORM_ID); |
|||
|
|||
ngOnInit() { |
|||
if (isPlatformBrowser(this.platformId)) { |
|||
// Code that uses browser-only APIs |
|||
console.log('Running in browser'); |
|||
localStorage.setItem('key', 'value'); |
|||
} |
|||
} |
|||
} |
|||
``` |
|||
|
|||
### Storage APIs |
|||
`localStorage` and `sessionStorage` are not accessible on the server. Consider using: |
|||
- Cookies for server-accessible data. |
|||
- The state transfer API for hydration. |
|||
- ABP's built-in storage abstractions. |
|||
|
|||
### Third-Party Libraries |
|||
Please ensure that any third-party libraries you use are compatible with SSR. These libraries can require: |
|||
- Dynamic imports for browser-only code. |
|||
- Platform-specific service providers. |
|||
- Custom Angular Universal integration. |
|||
|
|||
## ABP Framework Integration |
|||
|
|||
The SSR implementation is natively integrated with all of the ABP Framework features: |
|||
|
|||
- **Authentication & Authorization**: The OAuth/OpenID Connect flow functions seamlessly with ABP |
|||
- **Multi-tenancy**: Fully supports tenant resolution and switching |
|||
- **Localization**: Server-side rendering respects the locale |
|||
- **Permission Management**: Permission checks work on both server and client |
|||
- **Configuration**: The ABP configuration system is SSR-ready |
|||
## Performance Tips |
|||
|
|||
1. **Utilize State Transfer**: Send data from server to client to eliminate redundant HTTP requests |
|||
2. **Optimize Images**: Proper image loading strategies, such as lazy loading and responsive images. |
|||
3. **Cache API Responses**: At the server, implement proper caching strategies. |
|||
4. **Monitor Bundle Size**: Keep your server bundle optimized |
|||
5. **Use Prerendering**: The prerender target should be used for static content. |
|||
|
|||
## Conclusion |
|||
|
|||
Server-side rendering can be a very effective feature in improving your ABP Angular application's performance, SEO, and user experience. Our new SSR schematic will make it easier than ever to add SSR to your project. |
|||
|
|||
Try it today and let us know what you think! |
|||
|
|||
--- |
|||
|
After Width: | Height: | Size: 752 KiB |
@ -0,0 +1,322 @@ |
|||
# Signal-Based Forms in Angular 21: Why You’ll Never Miss Reactive Forms Again |
|||
|
|||
Angular 21 introduces one of the most exciting developments in the modern edition of Angular: **Signal-Based Forms**. Built directly on the reactive foundation of Angular signals, this new experimental API provides a cleaner, more intuitive, strongly typed, and ergonomic approach for managing form state—without the heavy boilerplate of Reactive Forms. |
|||
|
|||
> ⚠️ **Important:** Signal Forms are *experimental*. |
|||
> Their API can change. Avoid using them in critical production scenarios unless you understand the risks. |
|||
|
|||
Despite this, Signal Forms clearly represent Angular’s future direction. |
|||
--- |
|||
|
|||
## Why Signal Forms? |
|||
|
|||
Traditionally in Angular, building forms has involved several concerns: |
|||
|
|||
- Tracking values |
|||
- Managing UI interaction states (touched, dirty) |
|||
- Handling validation |
|||
- Keeping UI and model in sync |
|||
|
|||
Reactive Forms solved many challenges but introduced their own: |
|||
|
|||
- Verbosity FormBuilder API |
|||
- Required subscriptions (valueChanges) |
|||
- Manual cleaning |
|||
- Difficult nested forms |
|||
- Weak type-safety |
|||
|
|||
**Signal Forms solve these problems through:** |
|||
|
|||
1." Automatic synchronization |
|||
2." Full type safety |
|||
3." Schema-based validation |
|||
4." Fine-grained reactivity |
|||
5." Drastically reduced boilerplate |
|||
6." Natural integration with Angular Signals |
|||
|
|||
--- |
|||
|
|||
### 1. Form Models — The Core of Signal Forms |
|||
|
|||
A **form model** is simply a writable signal holding the structure of your form data. |
|||
|
|||
```ts |
|||
import { Component, signal } from '@angular/core'; |
|||
import { form, Field } from '@angular/forms/signals'; |
|||
|
|||
@Component({ |
|||
selector: 'app-login', |
|||
imports: [Field], |
|||
template: ` |
|||
<input type="email" [field]="loginForm.email" /> |
|||
<input type="password" [field]="loginForm.password" /> |
|||
`, |
|||
}) |
|||
export class LoginComponent { |
|||
loginModel = signal({ |
|||
email: '', |
|||
password: '', |
|||
}); |
|||
|
|||
loginForm = form(this.loginModel); |
|||
} |
|||
``` |
|||
|
|||
Calling `form(model)` creates a **Field Tree** that maps directly to your model. |
|||
|
|||
--- |
|||
|
|||
### 2. Achieving Full Type Safety |
|||
|
|||
Although TypeScript can infer types from object literals, defining explicit interfaces provides maximum safety and better IDE support. |
|||
|
|||
```ts |
|||
interface LoginData { |
|||
email: string; |
|||
password: string; |
|||
} |
|||
|
|||
loginModel = signal<LoginData>({ |
|||
email: '', |
|||
password: '', |
|||
}); |
|||
|
|||
loginForm = form(loginModel); |
|||
``` |
|||
|
|||
Now: |
|||
|
|||
- `loginForm.email` → `FieldTree<string>` |
|||
- Accessing invalid fields like `loginForm.username` results in compile-time errors |
|||
|
|||
This level of type safety surpasses Reactive Forms. |
|||
|
|||
--- |
|||
|
|||
### 3. Reading Form Values |
|||
|
|||
#### Read from the model (entire form): |
|||
|
|||
```ts |
|||
onSubmit() { |
|||
const data = this.loginModel(); |
|||
console.log(data.email, data.password); |
|||
} |
|||
``` |
|||
|
|||
#### Read from an individual field: |
|||
|
|||
```html |
|||
<p>Current email: {{ loginForm.email().value() }}</p> |
|||
``` |
|||
|
|||
Each field exposes: |
|||
|
|||
- `value()` |
|||
- `valid()` |
|||
- `errors()` |
|||
- `dirty()` |
|||
- `touched()` |
|||
|
|||
All as signals. |
|||
|
|||
--- |
|||
|
|||
### 4. Updating Form Models Programmatically |
|||
|
|||
Signal Forms allow three update methods. |
|||
|
|||
#### 1. Replace the entire model |
|||
|
|||
```ts |
|||
this.userModel.set({ |
|||
name: 'Alice', |
|||
email: 'alice@example.com', |
|||
}); |
|||
``` |
|||
|
|||
#### 2. Patch specific fields |
|||
|
|||
```ts |
|||
this.userModel.update(prev => ({ |
|||
...prev, |
|||
email: newEmail, |
|||
})); |
|||
``` |
|||
|
|||
#### 3. Update a single field |
|||
|
|||
```ts |
|||
this.userForm.email().value.set(''); |
|||
``` |
|||
|
|||
This eliminates the need for: |
|||
|
|||
- `patchValue()` |
|||
- `setValue()` |
|||
- `formGroup.get('field')` |
|||
|
|||
--- |
|||
|
|||
### 5. Automatic Two-Way Binding With `[field]` |
|||
|
|||
The `[field]` directive enables perfect two-way data binding: |
|||
|
|||
```html |
|||
<input [field]="userForm.name" /> |
|||
``` |
|||
|
|||
#### How it works: |
|||
|
|||
- **User input → Field state → Model** |
|||
- **Model updates → Field state → Input UI** |
|||
|
|||
No subscriptions. |
|||
No event handlers. |
|||
No boilerplate. |
|||
|
|||
Reactive Forms could never achieve this cleanly. |
|||
|
|||
--- |
|||
|
|||
### 6. Nested Models and Arrays |
|||
|
|||
Models can contain nested object structures: |
|||
|
|||
```ts |
|||
userModel = signal({ |
|||
name: '', |
|||
address: { |
|||
street: '', |
|||
city: '', |
|||
}, |
|||
}); |
|||
``` |
|||
|
|||
Access fields easily: |
|||
|
|||
```html |
|||
<input [field]="userForm.address.street" /> |
|||
``` |
|||
|
|||
Arrays are also supported: |
|||
|
|||
```ts |
|||
orderModel = signal({ |
|||
items: [ |
|||
{ product: '', quantity: 1, price: 0 } |
|||
] |
|||
}); |
|||
``` |
|||
|
|||
Field state persists even when array items move, thanks to identity tracking. |
|||
|
|||
--- |
|||
|
|||
### 7. Schema-Based Validation |
|||
|
|||
Validation is clean and centralized: |
|||
|
|||
```ts |
|||
import { required, email } from '@angular/forms/signals'; |
|||
|
|||
const model = signal({ email: '' }); |
|||
|
|||
const formRef = form(model, { |
|||
email: [required(), email()], |
|||
}); |
|||
``` |
|||
|
|||
Field validation state is reactive: |
|||
|
|||
```ts |
|||
formRef.email().valid() |
|||
formRef.email().errors() |
|||
formRef.email().touched() |
|||
``` |
|||
|
|||
Validation no longer scatters across components. |
|||
|
|||
--- |
|||
|
|||
### 8. When Should You Use Signal Forms? |
|||
|
|||
#### New Angular 21+ apps |
|||
Signal-first architecture is the new standard. |
|||
|
|||
#### Teams wanting stronger type safety |
|||
Every field is exactly typed. |
|||
|
|||
#### Devs tired of Reactive Form boilerplate |
|||
Signal Forms drastically simplify code. |
|||
|
|||
#### Complex UI with computed reactive form state |
|||
Signals integrate perfectly. |
|||
|
|||
#### ❌ Avoid if: |
|||
- You need long-term stability |
|||
- You rely on mature Reactive Forms features |
|||
- Your app must avoid experimental APIs |
|||
|
|||
--- |
|||
|
|||
### 9. Reactive Forms vs Signal Forms |
|||
|
|||
| Feature | Reactive Forms | Signal Forms | |
|||
|--------|----------------|--------------| |
|||
| Boilerplate | High | Very low | |
|||
| Type-safety | Weak | Strong | |
|||
| Two-way binding | Manual | Automatic | |
|||
| Validation | Scattered | Centralized schema | |
|||
| Nested forms | Verbose | Natural | |
|||
| Subscriptions | Required | None | |
|||
| Change detection | Zone-heavy | Fine-grained | |
|||
|
|||
Signal Forms feel like the "modern Angular mode," while Reactive Forms increasingly feel legacy. |
|||
|
|||
--- |
|||
|
|||
### 10. Full Example: Login Form |
|||
|
|||
```ts |
|||
@Component({ |
|||
selector: 'app-login', |
|||
imports: [Field], |
|||
template: ` |
|||
<form (ngSubmit)="submit()"> |
|||
<input type="email" [field]="form.email" /> |
|||
<input type="password" [field]="form.password" /> |
|||
<button>Login</button> |
|||
</form> |
|||
`, |
|||
}) |
|||
export class LoginComponent { |
|||
model = signal({ email: '', password: '' }); |
|||
form = form(this.model); |
|||
|
|||
submit() { |
|||
console.log(this.model()); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
Minimal. Reactive. Completely type-safe. |
|||
|
|||
--- |
|||
|
|||
## **Conclusion** |
|||
|
|||
Signal Forms in Angular 21 represent a big step forward: |
|||
|
|||
- Cleaner API |
|||
- Stronger type safety |
|||
- Automatic two-way binding |
|||
- Centralized validation |
|||
- Fine-grained reactivity |
|||
- Dramatically better developer experience |
|||
|
|||
|
|||
Although these are experimental, they clearly show the future of Angular's form ecosystem. |
|||
Once you get into using Signal Forms, you may never want to use Reactive Forms again. |
|||
|
|||
--- |
|||
@ -0,0 +1,25 @@ |
|||
**ABP Black Friday Deals are Almost Here\!** |
|||
|
|||
The season of huge savings is back\! We are happy to announce **ABP Black Friday Campaign**, packed with exclusive deals that you simply won't want to miss. Whether you are ready to start building with ABP or looking to expand your existing license, this is your chance to maximize your savings\! |
|||
|
|||
**Campaign Dates: Mark Your Calendar** |
|||
|
|||
Black Friday campaign is live for one week only\! Our deals run from: **November 24th \- December 1st.** |
|||
|
|||
Don't miss this limited-time opportunity to **save up to $3,000** and take your software development to the next level. |
|||
|
|||
**What's Included in the ABP Black Friday Campaign?** |
|||
|
|||
Here’s why this campaign is the best time to buy or upgrade: |
|||
|
|||
* Open to Everyone: This campaign is available for both new and existing customers. |
|||
* Stack Your Savings: You can combine this Black Friday offer with our multi-year discounts for the greatest possible value. |
|||
* Flexible Upgrades: Planning to upgrade to a higher package? Now is the perfect time to make that move at a lower cost. |
|||
* More Developer Seats? No Problem\! Additional developer seats are also eligible under this campaign, allowing you to grow your team effortlessly and affordably. |
|||
|
|||
**Save Money Now\!** |
|||
|
|||
This campaign is your best opportunity all year to unlock advanced features, scale your team, or upgrade your plan while **saving up to $3,000.** Secure your savings before the campaign ends on December 1st\! |
|||
|
|||
[**Visit Pricing Page to Explore Offers\!**](https://abp.io/pricing) |
|||
|
|||
@ -0,0 +1,158 @@ |
|||
# My First Look and Experience with Google AntiGravity |
|||
|
|||
## Is Google AntiGravity Going to Replace Your Main Code Editor? |
|||
|
|||
Today, I tried the new code-editor AntiGravity by Google. *"It's beyond a code-editor*" by Google 🙄 |
|||
When I first launch it, I see the UI is almost same as Cursor. They're both based on Visual Studio Code. |
|||
That's why it was not hard to find what I'm looking for. |
|||
|
|||
First of all, the main difference as I see from the Cursor is; when I type a prompt in the agent section **AntiGravity first creates a Task List** (like a road-map) and whenever it finishes a task, it checks the corresponding task. Actually Cursor has a similar functionality but AntiGravity took it one step further. |
|||
|
|||
Second thing which was good to me; AntiGravity uses [Nano Banana 🍌](https://gemini.google/tr/overview/image-generation/). This is Google's AI image generation model... Why it's important because when you create an app, you don't need to search for graphics, deal with image licenses. **AntiGravity generates images automatically and no license is required!** |
|||
|
|||
Third exciting feature for me; **AntiGravity is integrated with Google Chrome and can communicate with the running website**. When I first run my web project, it installed a browser extension which can see and interact with my website. It can see the results, click somewhere else on the page, scroll, fill up the forms, amazing 😵 |
|||
|
|||
Another feature I loved is that **you can enter a new prompt even while AntiGravity is still generating a response** 🧐. It instantly prioritizes the latest input and adjusts the ongoing process if needed. But in Cursor, if you add a prompt before the cursor finishes, it simply queues it and runs it later 😔. |
|||
|
|||
And lastly, **AntiGravity is working very good with Gemini 3**. |
|||
|
|||
Well, everything was not so perfect 😥 When I tried AntiGravity, couple of times it stucked AI generation and Agent stopped. I faced errors like this 👇 |
|||
|
|||
 |
|||
|
|||
|
|||
|
|||
## Debugging .NET Projects via AntiGravity |
|||
|
|||
⚠ There's a crucial development issue with AntiGravity (and also for Cursor, Windsurf etc...) 🤕 you **cannot debug your .NET application with AntiGravity 🥺.** *This is Microsoft's policy!* Microsoft doesn't allow debugging for 3rd party IDEs and shows the below error... That's why I cannot say it's a downside of AntiGravity. You need to use Microsft's original VS Code, Visual Studio or Rider for debugging. But wait a while there's a workaround for this, I'll let you know in the next section. |
|||
|
|||
|
|||
|
|||
 |
|||
|
|||
### What does this error mean? |
|||
|
|||
AntiGravity, Cursor, Windsurf etc... are using Visual Studio Code and the C# extension for VS Code includes the Microsoft .NET Core Debugger "*vsdbg*". |
|||
VS Code is open-source but "*vsdbg*" is not open-source! It's working only with Visual Studio Code, Visual Studio and Visual Studio for Mac. This is clearly stated at [Microsoft's this link](https://github.com/dotnet/vscode-csharp/blob/main/docs/debugger/Microsoft-.NET-Core-Debugger-licensing-and-Microsoft-Visual-Studio-Code.md). |
|||
|
|||
### Ok! How to resolve debugging issue with AntiGravity? and Cursor and Windsurf... |
|||
|
|||
There's a free C# debugger extension for Visual Studio Code based IDEs that supports AntiGravity, Cursor and Windsurf. The extension name is **C#**. |
|||
You can download this free C# debugger extension at 👉 [open-vsx.org/extension/muhammad-sammy/csharp/](https://open-vsx.org/extension/muhammad-sammy/csharp/). |
|||
For AntiGravity open Extension window (*Ctrl + Shift + X*) and search for `C#`, there you'll see this extension. |
|||
|
|||
 |
|||
|
|||
After installing, I restarted AntiGravity and now I can see the red circle which allows me to add breakpoint on C# code. |
|||
|
|||
 |
|||
|
|||
### Another Extension For Debugging .NET Apps on VS Code |
|||
|
|||
Recently I heard about DotRush extension from the folks. As they say DotRush works slightly faster and support Razor pages (.cshtml files). |
|||
Here's the link for DotRush https://github.com/JaneySprings/DotRush |
|||
|
|||
### Finding Website Running Port |
|||
|
|||
When you run the web project via C# debugger extension, normally it's not using the `launch.json` therefore the website port is not the one when you start from Visual Studio / Rider... So what's my website's port which I just run now? Normally for ASP.NET Core **the default port is 5000**. You can try navigating to http://localhost:5000/. |
|||
Alternatively you can write the below code in `Program.cs` which prints the full address of your website in the logs. |
|||
If you do the steps which I showed you, you can debug your C# application via AntiGravity and other VS Code derivatives. |
|||
|
|||
 |
|||
|
|||
## How Much is AntiGravity? 💲 |
|||
|
|||
Currently there's only individual plan is available for personal accounts and that's free 👏! The contents of Team and Enterprise plans and prices are not announced yet. But **Gemini 3 is not free**! I used it with my company's Google Workspace account which we normally pay for Gemini. |
|||
|
|||
 |
|||
|
|||
## More About AntiGravity |
|||
|
|||
There have been many AI assisted IDEs like [Windsurf](https://windsurf.com/), [Cursor](https://cursor.com/), [Zed](https://zed.dev/), [Replit](https://replit.com/) and [Fleet](https://www.jetbrains.com/fleet/). But this time it's different, this is backed by Google. |
|||
As you see from the below image AntiGravity, uses a standard grid layout as others based on VS Code editor. |
|||
It's very similar to Cursor, Visual Studio, Rider. |
|||
|
|||
 |
|||
|
|||
## Supported LLMs 🧠 |
|||
|
|||
Antigravity offers the below models which supports reasoning: Gemini 3 Pro, Claude Sonnet 4.5, GPT-OSS |
|||
|
|||
 |
|||
|
|||
Antigravity uses other models for supportive tasks in the background: |
|||
|
|||
- **Nano banana**: This is used to generate images. |
|||
- **Gemini 2.5 Pro UI Checkpoint**: It's for the browser subagent to trigger browser action such as clicking, scrolling, or filling in input. |
|||
- **Gemini 2.5 Flash**: For checkpointing and context summarization, this is used. |
|||
- **Gemini 2.5 Flash Lite**: And when it's need to make a semantic search in your code-base, this is used. |
|||
|
|||
## AntiGravity Can See Your Website |
|||
|
|||
This makes a big difference from traditional IDEs. AntiGravity's browser agent is taking screenshots of your pages when it needs to check. This is achieved by a Chrome Extension as a tool to the agent, and you can also prompt the agent to take a screenshot of a page. It can iterate on website designs and implementations, it can perform UI Testing, it can monitor dashboards, it can automate routine tasks like rerunning CI. |
|||
This is the link for the extension 👉 [chromewebstore.google.com/detail/antigravity-browser-exten/eeijfnjmjelapkebgockoeaadonbchdd](https://chromewebstore.google.com/detail/antigravity-browser-exten/eeijfnjmjelapkebgockoeaadonbchdd). AntiGravity will install this extension automatically on the first run. |
|||
|
|||
 |
|||
|
|||
 |
|||
|
|||
## MCP Integration |
|||
|
|||
### When Do We Need MCP in a Code Editor? |
|||
|
|||
Simply if we want to connect to a 3rd party service to complete our task we need MCP. So AntiGravity can connect to your DB and write proper SQL queries or it can pull in recent build logs from Netlify or Heroku. Also you can ask AntiGravity to to connect GitHub for finding the best authentication pattern. |
|||
|
|||
### AntiGravity Supports These MCP Servers |
|||
|
|||
Airweave, AlloyDB for PostgreSQL, Atlassian, BigQuery, Cloud SQL for PostgreSQL, Cloud SQL for MySQL, Cloud SQL for SQL Server, Dart, Dataplex, Figma Dev Mode MCP, Firebase, GitHub, Harness, Heroku, Linear, Locofy, Looker, MCP Toolbox for Databases, MongoDB, Neon, Netlify, Notion, PayPal, Perplexity Ask, Pinecone, Prisma, Redis, Sequential Thinking, SonarQube, Spanner, Stripe and Supabase. |
|||
|
|||
 |
|||
|
|||
## Agent Settings ⚙️ |
|||
|
|||
The major settings of Agent are: |
|||
|
|||
- **Agent Auto Fix Lints**: I enabled this setting because I want the Agent automatically fixes its own mistakes for invalid syntax, bad formatting, unused variables, unreachable code or following coding standards... It makes extra tool calls that's why little bit expensive 🥴. |
|||
- **Auto Execution**: Sometimes Agent tries to build application or writing test code and running it, in these cases it executes command. I choose "Turbo" 🤜 With this option, Agent always runs the terminal command and controls my browser. |
|||
- **Review Policy**: How much control you are giving to agent 🙎. I choose "Always Proceed" 👌 because I mostly trust AI 😀. The Agent will never ask for review. |
|||
|
|||
 |
|||
|
|||
## Differences Between Cursor and AntiGravity |
|||
|
|||
While Cursor was the champion of AI code editors, **Antigravity brings a different philosophy**. |
|||
|
|||
### 1. "Agent-First 🤖" vs "You-First 🤠" |
|||
|
|||
- **Cursor:** It acts like an assistant; it predicts your next move, auto-completes your thoughts, and helps you refactor while you type. You are still the driver; Cursor just drives the car at 200 km/h. |
|||
- **Antigravity:** Antigravity is built to let you manage coding tasks. It is "Agent-First." You don't just type code; you assign tasks to autonomous agents (e.g., "Fix the bug in the login flow and verify it in the browser"). It behaves more like a junior developer that you supervise. |
|||
|
|||
### 2. The Interface |
|||
|
|||
- **Cursor:** Looks and feels exactly like **VS Code**. If you know VS Code, you know Cursor. |
|||
|
|||
- **Antigravity:** Introduces 2 major layouts: |
|||
- **Editor View:** Similar to a standard IDE |
|||
- **Manager View:** A dashboard where you see multiple "Agents" working in parallel. You can watch them plan, execute, and test tasks asynchronously. |
|||
|
|||
### 3. Verification & Trust |
|||
|
|||
- **Cursor:** You verify by reading the code diffs it suggests. |
|||
- **Antigravity:** Introduces **Artifacts**... Since the agents work autonomously, they generate proof-of-work documents, screenshots of the app running, browser logs and execution plans. So you can verify what they did without necessarily reading every line of code immediately. |
|||
|
|||
### 4. Capabilities |
|||
|
|||
- **Cursor:** Best-in-class **Autocomplete** ("Tab" feature) and **Composer** (multi-file editing). It excels at "Vibe Coding". It's getting into a flow state where the AI writes the boilerplate and you direct the logic. |
|||
- **Antigravity:** Is good at **Autonomous Execution**. It has a built-in browser and terminal that the *Agent* controls. The Agent can write code, run the server, open the browser, see the error, and fix it 😎 |
|||
|
|||
### 5. AI Models (Brains 🧠) |
|||
|
|||
- **Cursor:** Model Agnostic. You can switch between **Claude 3.5 Sonnet** *-mostly the community uses this-*, GPT-4o, and others. |
|||
- **Antigravity:** Built deeply around **Gemini 3 Pro**. It leverages Gemini's massive context window (1M+ tokens) to understand huge mono repos without needing as much "RAG" as Cursor. |
|||
|
|||
|
|||
|
|||
## Try It Yourself Now 🤝 |
|||
|
|||
If you are ready to experience the new AI code editor by Google, download and use 👇 |
|||
[**Launch Google AntiGravity**](https://antigravity.google/) |
|||
|
After Width: | Height: | Size: 70 KiB |
|
After Width: | Height: | Size: 183 KiB |
|
After Width: | Height: | Size: 62 KiB |
|
After Width: | Height: | Size: 1.1 MiB |
|
After Width: | Height: | Size: 90 KiB |
|
After Width: | Height: | Size: 13 KiB |
|
After Width: | Height: | Size: 102 KiB |
|
After Width: | Height: | Size: 293 KiB |
|
After Width: | Height: | Size: 76 KiB |
|
After Width: | Height: | Size: 46 KiB |
|
After Width: | Height: | Size: 13 KiB |
|
After Width: | Height: | Size: 13 KiB |
|
After Width: | Height: | Size: 275 KiB |
|
After Width: | Height: | Size: 49 KiB |
|
After Width: | Height: | Size: 154 KiB |
|
After Width: | Height: | Size: 5.4 KiB |
|
After Width: | Height: | Size: 6.3 KiB |
|
After Width: | Height: | Size: 6.0 KiB |
|
After Width: | Height: | Size: 4.8 KiB |
|
After Width: | Height: | Size: 7.2 KiB |
|
After Width: | Height: | Size: 3.1 KiB |
|
After Width: | Height: | Size: 6.6 KiB |
@ -0,0 +1,414 @@ |
|||
# Building Production-Ready LLM Applications with .NET: A Practical Guide |
|||
|
|||
Large Language Models (LLMs) have evolved rapidly, and integrating them into production .NET applications requires staying current with the latest approaches. In this article, I'll share practical tips and patterns I've learned while building LLM-powered systems, covering everything from API changes in GPT-5 to implementing efficient RAG (Retrieval Augmented Generation) architectures. |
|||
|
|||
Whether you're building a chatbot, a knowledge base assistant, or integrating AI into your enterprise applications, these production-tested insights will help you avoid common pitfalls and build more reliable systems. |
|||
|
|||
## The Temperature Paradigm Shift: GPT-5 Changes Everything |
|||
|
|||
If you've been working with GPT-4 or earlier models, you're familiar with the `temperature` and `top_p` parameters for controlling response randomness. **Here's the critical update**: GPT-5 no longer supports these parameters! |
|||
|
|||
### The Old Way (GPT-4) |
|||
```csharp |
|||
var chatRequest = new ChatOptions |
|||
{ |
|||
Temperature = 0.7, // ✅ Worked with GPT-4 |
|||
TopP = 0.9 // ✅ Worked with GPT-4 |
|||
}; |
|||
``` |
|||
|
|||
### The New Way (GPT-5) |
|||
```csharp |
|||
var chatRequest = new ChatOptions |
|||
{ |
|||
RawRepresentationFactory = (client => new ChatCompletionOptions() |
|||
{ |
|||
#pragma warning disable OPENAI001 |
|||
ReasoningEffortLevel = "minimal", |
|||
#pragma warning restore OPENAI001 |
|||
}) |
|||
}; |
|||
``` |
|||
|
|||
**Why the change?** GPT-5 incorporates an internal reasoning and verification process. Instead of controlling randomness, you now specify how much computational effort the model should invest in reasoning through the problem. |
|||
|
|||
 |
|||
|
|||
### Choosing the Right Reasoning Level |
|||
|
|||
- **Low**: Quick responses for simple queries (e.g., "What's the capital of France?") |
|||
- **Medium**: Balanced approach for most use cases |
|||
- **High**: Complex reasoning tasks (e.g., code generation, multi-step problem solving) |
|||
|
|||
> **Pro Tip**: Reasoning tokens are included in your API costs. Use "High" only when necessary to optimize your budget. |
|||
|
|||
## System Prompts: The "Lost in the Middle" Problem |
|||
|
|||
Here's a critical insight that can save you hours of debugging: **Important rules must be repeated at the END of your prompt!** |
|||
|
|||
### ❌ What Doesn't Work |
|||
``` |
|||
You are a helpful assistant. |
|||
RULE: Never share passwords or sensitive information. |
|||
|
|||
[User Input] |
|||
``` |
|||
|
|||
### ✅ What Actually Works |
|||
``` |
|||
You are a helpful assistant. |
|||
RULE: Never share passwords or sensitive information. |
|||
|
|||
[User Input] |
|||
|
|||
⚠️ REMINDER: Apply the rules above strictly, ESPECIALLY regarding passwords. |
|||
``` |
|||
|
|||
**Why?** LLMs suffer from the "Lost in the Middle" phenomenon—they pay more attention to the beginning and end of the context window. Critical instructions buried in the middle are often ignored. |
|||
|
|||
## RAG Architecture: The Parent-Child Pattern |
|||
|
|||
Retrieval Augmented Generation (RAG) is essential for grounding LLM responses in your own data. The most effective pattern I've found is the **Parent-Child approach**. |
|||
|
|||
 |
|||
|
|||
### How It Works |
|||
|
|||
1. **Split documents into hierarchies**: |
|||
- **Parent chunks**: Large sections (1000-2000 tokens) for context |
|||
- **Child chunks**: Small segments (200-500 tokens) for precise retrieval |
|||
|
|||
2. **Store both in vector database** with references |
|||
|
|||
3. **Query flow**: |
|||
- Search using child chunks (higher precision) |
|||
- Return parent chunks to LLM (richer context) |
|||
|
|||
### The Overlap Strategy |
|||
|
|||
Always use overlapping chunks to prevent information loss at boundaries! |
|||
|
|||
``` |
|||
Chunk 1: Token 0-500 |
|||
Chunk 2: Token 400-900 ← 100 token overlap |
|||
Chunk 3: Token 800-1300 ← 100 token overlap |
|||
``` |
|||
|
|||
**Standard recommendation**: 10-20% overlap (for 500 tokens, use 50-100 token overlap) |
|||
|
|||
### Implementation with Semantic Kernel |
|||
|
|||
```csharp |
|||
using Microsoft.SemanticKernel.Text; |
|||
|
|||
var chunks = TextChunker.SplitPlainTextParagraphs( |
|||
documentText, |
|||
maxTokensPerParagraph: 500, |
|||
overlapTokens: 50 |
|||
); |
|||
|
|||
foreach (var chunk in chunks) |
|||
{ |
|||
var embedding = await embeddingService.GenerateEmbeddingAsync(chunk); |
|||
await vectorDb.StoreAsync(chunk, embedding); |
|||
} |
|||
``` |
|||
|
|||
## PostgreSQL + pgvector: The Pragmatic Choice |
|||
|
|||
For .NET developers, choosing a vector database can be overwhelming. After evaluating multiple options, **PostgreSQL with pgvector** is the most practical choice for most scenarios. |
|||
|
|||
 |
|||
|
|||
### Why pgvector? |
|||
|
|||
✅ **Use existing SQL knowledge** - No new query language to learn |
|||
✅ **EF Core integration** - Works with your existing data access layer |
|||
✅ **JOIN with metadata** - Combine vector search with traditional queries |
|||
✅ **WHERE clause filtering** - Filter by tenant, user, date, etc. |
|||
✅ **ACID compliance** - Transaction support for data consistency |
|||
✅ **No separate infrastructure** - One database for everything |
|||
|
|||
### Setting Up pgvector with EF Core |
|||
|
|||
First, install the NuGet package: |
|||
|
|||
```bash |
|||
dotnet add package Pgvector.EntityFrameworkCore |
|||
``` |
|||
|
|||
Define your entity: |
|||
|
|||
```csharp |
|||
using Pgvector; |
|||
using Pgvector.EntityFrameworkCore; |
|||
|
|||
public class DocumentChunk |
|||
{ |
|||
public Guid Id { get; set; } |
|||
public string Content { get; set; } |
|||
public Vector Embedding { get; set; } // 👈 pgvector type |
|||
public Guid ParentChunkId { get; set; } |
|||
public DateTime CreatedAt { get; set; } |
|||
} |
|||
``` |
|||
|
|||
Configure in DbContext: |
|||
|
|||
```csharp |
|||
protected override void OnModelCreating(ModelBuilder builder) |
|||
{ |
|||
builder.HasPostgresExtension("vector"); |
|||
|
|||
builder.Entity<DocumentChunk>() |
|||
.Property(e => e.Embedding) |
|||
.HasColumnType("vector(1536)"); // 👈 OpenAI embedding dimension |
|||
|
|||
builder.Entity<DocumentChunk>() |
|||
.HasIndex(e => e.Embedding) |
|||
.HasMethod("hnsw") // 👈 Fast approximate search |
|||
.HasOperators("vector_cosine_ops"); |
|||
} |
|||
``` |
|||
|
|||
### Performing Vector Search |
|||
|
|||
```csharp |
|||
using Pgvector.EntityFrameworkCore; |
|||
|
|||
public async Task<List<DocumentChunk>> SearchAsync(string query) |
|||
{ |
|||
// 1. Convert query to embedding |
|||
var queryVector = await _embeddingService.GetEmbeddingAsync(query); |
|||
|
|||
// 2. Search |
|||
return await _context.DocumentChunks |
|||
.OrderBy(c => c.Embedding.L2Distance(queryVector)) // 👈 Lower is better |
|||
.Take(5) |
|||
.ToListAsync(); |
|||
} |
|||
``` |
|||
|
|||
**Source**: [Pgvector.NET on GitHub](https://github.com/pgvector/pgvector-dotnet?tab=readme-ov-file#entity-framework-core) |
|||
|
|||
## Smart Tool Usage: Make RAG a Tool, Not a Tax |
|||
|
|||
A common mistake is calling RAG on every single user message. This wastes tokens and money. Instead, **make RAG a tool** and let the LLM decide when to use it. |
|||
|
|||
### ❌ Expensive Approach |
|||
```csharp |
|||
// Always call RAG, even for "Hello" |
|||
var context = await PerformRAG(userMessage); |
|||
var response = await chatClient.CompleteAsync($"{context}\n\n{userMessage}"); |
|||
``` |
|||
|
|||
### ✅ Smart Approach |
|||
```csharp |
|||
[KernelFunction] |
|||
[Description("Search the company knowledge base for information")] |
|||
public async Task<string> SearchKnowledgeBase( |
|||
[Description("The search query")] string query) |
|||
{ |
|||
var results = await _vectorDb.SearchAsync(query); |
|||
return string.Join("\n---\n", results.Select(r => r.Content)); |
|||
} |
|||
``` |
|||
|
|||
The LLM will call `SearchKnowledgeBase` only when needed: |
|||
- "Hello" → No tool call |
|||
- "What was our 2024 revenue?" → Calls tool |
|||
- "Tell me a joke" → No tool call |
|||
|
|||
## Multilingual RAG: Query Translation Strategy |
|||
|
|||
When your documents are in one language (e.g., English) but users query in another (e.g., Turkish), you need a translation strategy. |
|||
|
|||
 |
|||
|
|||
### Solution Options |
|||
|
|||
**Option 1**: Use an LLM that automatically calls tools in English |
|||
- Many modern LLMs can do this if properly instructed |
|||
|
|||
**Option 2**: Tool chain approach |
|||
```csharp |
|||
[KernelFunction] |
|||
[Description("Translate text to English")] |
|||
public async Task<string> TranslateToEnglish(string text) |
|||
{ |
|||
// Translation logic |
|||
} |
|||
|
|||
[KernelFunction] |
|||
[Description("Search knowledge base (English only)")] |
|||
public async Task<string> SearchKnowledgeBase(string englishQuery) |
|||
{ |
|||
// Search logic |
|||
} |
|||
``` |
|||
|
|||
The LLM will: |
|||
1. Call `TranslateToEnglish("2024 geliri nedir?")` |
|||
2. Get "What was 2024 revenue?" |
|||
3. Call `SearchKnowledgeBase("What was 2024 revenue?")` |
|||
4. Return results and respond in Turkish |
|||
|
|||
## Model Context Protocol (MCP): Beyond In-Process Tools |
|||
|
|||
Microsoft and Anthropic recently released official C# SDKs for the Model Context Protocol (MCP). This is a game-changer for tool reusability. |
|||
|
|||
 |
|||
|
|||
### MCP vs. Semantic Kernel Plugins |
|||
|
|||
| Feature | SK Plugins | MCP Servers | |
|||
|---------|-----------|-------------| |
|||
| **Process** | In-process | Out-of-process (stdio/http) | |
|||
| **Reusability** | Application-specific | Cross-application | |
|||
| **Examples** | Used within your app | VS Code Copilot, Claude Desktop | |
|||
|
|||
### Creating an MCP Server |
|||
|
|||
```csharp |
|||
using Microsoft.Extensions.Hosting; |
|||
using ModelContextProtocol.Extensions.Hosting; |
|||
|
|||
var builder = Host.CreateEmptyApplicationBuilder(settings: null); |
|||
|
|||
builder.Services.AddMcpServer() |
|||
.WithStdioServerTransport() |
|||
.WithToolsFromAssembly(); |
|||
|
|||
await builder.Build().RunAsync(); |
|||
``` |
|||
|
|||
Define your tools: |
|||
|
|||
```csharp |
|||
[McpServerToolType] |
|||
public static class FileSystemTools |
|||
{ |
|||
[McpServerTool, Description("Read a file from the file system")] |
|||
public static async Task<string> ReadFile(string path) |
|||
{ |
|||
// ⚠️ SECURITY: Always validate paths! |
|||
if (!IsPathSafe(path)) |
|||
throw new SecurityException("Invalid path"); |
|||
|
|||
return await File.ReadAllTextAsync(path); |
|||
} |
|||
|
|||
private static bool IsPathSafe(string path) |
|||
{ |
|||
// Implement path traversal prevention |
|||
var fullPath = Path.GetFullPath(path); |
|||
return fullPath.StartsWith(AllowedDirectory); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
Your MCP server can now be used by VS Code Copilot, Claude Desktop, or any other MCP client! |
|||
|
|||
## Chat History Management: Truncation + RAG Hybrid |
|||
|
|||
For long conversations, storing all history in the context window becomes impractical. Here's the pattern that works: |
|||
|
|||
 |
|||
|
|||
### ❌ Lossy Approach |
|||
``` |
|||
First 50 messages → Summarize with LLM → Single summary message |
|||
``` |
|||
**Problem**: Detail loss (fidelity loss) |
|||
|
|||
### ✅ Hybrid Approach |
|||
1. **Recent messages** (last 5-10): Keep in prompt for immediate context |
|||
2. **Older messages**: Store in vector database as a tool |
|||
|
|||
```csharp |
|||
[KernelFunction] |
|||
[Description("Search conversation history for past discussions")] |
|||
public async Task<string> SearchChatHistory( |
|||
[Description("What to search for")] string query) |
|||
{ |
|||
var relevantMessages = await _vectorDb.SearchAsync(query); |
|||
return string.Join("\n", relevantMessages.Select(m => |
|||
$"[{m.Timestamp}] {m.Role}: {m.Content}")); |
|||
} |
|||
``` |
|||
|
|||
The LLM retrieves only relevant past context when needed, avoiding summary-induced information loss. |
|||
|
|||
## RAG vs. Fine-Tuning: Choose Wisely |
|||
|
|||
A common misconception is using fine-tuning for knowledge injection. Here's when to use each: |
|||
|
|||
| Purpose | RAG | Fine-Tuning | |
|||
|---------|-----|-------------| |
|||
| **Goal** | Memory (provide facts) | Behavior (teach style) | |
|||
| **Updates** | Dynamic (add docs anytime) | Static (requires retraining) | |
|||
| **Cost** | Low dev, higher inference | High dev, lower inference | |
|||
| **Hallucination** | Reduces | Doesn't reduce | |
|||
| **Use Case** | Company docs, FAQs | Brand voice, specific format | |
|||
|
|||
**Common mistake**: "Let's fine-tune on our company documents" ❌ |
|||
**Better approach**: Use RAG! ✅ |
|||
|
|||
Fine-tuning is for teaching the model *how* to respond, not *what* to know. |
|||
|
|||
**Source**: [Oracle - RAG vs Fine-Tuning](https://www.oracle.com/artificial-intelligence/generative-ai/retrieval-augmented-generation-rag/rag-fine-tuning/) |
|||
|
|||
## Bonus: Why SVG is Superior for LLM-Generated Images |
|||
|
|||
When using LLMs to generate diagrams and visualizations, always request SVG format instead of PNG or JPG. |
|||
|
|||
### Why SVG? |
|||
|
|||
✅ **Text-based** → LLMs produce better results |
|||
✅ **Lower cost** → Fewer tokens than base64-encoded images |
|||
✅ **Editable** → Easy to modify after generation |
|||
✅ **Scalable** → Perfect quality at any size |
|||
✅ **Version control friendly** → Works great in Git |
|||
|
|||
### Example Prompt |
|||
|
|||
``` |
|||
Create an architecture diagram showing PostgreSQL with pgvector integration. |
|||
Format: SVG, 800x400 pixels. Show: .NET Application → EF Core → PostgreSQL → Vector Search. |
|||
Use arrows to connect stages. Color scheme: Blue tones. |
|||
``` |
|||
|
|||
 |
|||
|
|||
All diagrams in this article were generated as SVG, resulting in excellent quality and lower token costs! |
|||
|
|||
> **Pro Tip**: If you don't need photographs or complex renders, always choose SVG. |
|||
|
|||
## Architecture Roadmap: Putting It All Together |
|||
|
|||
Here's the recommended stack for building production LLM applications with .NET: |
|||
|
|||
1. **Orchestration**: Microsoft.Extensions.AI + Semantic Kernel (when needed) |
|||
2. **Vector Database**: PostgreSQL + Pgvector.EntityFrameworkCore |
|||
3. **RAG Pattern**: Parent-Child chunks with 10-20% overlap |
|||
4. **Tools**: MCP servers for reusability |
|||
5. **Reasoning**: ReasoningEffortLevel instead of temperature |
|||
6. **Prompting**: Critical rules at the end |
|||
7. **Cost Optimization**: Make RAG a tool, not automatic |
|||
|
|||
## Key Takeaways |
|||
|
|||
Let me summarize the most important production tips: |
|||
|
|||
1. **Temperature is gone** → Use `ReasoningEffortLevel` with GPT-5 |
|||
2. **Rules at the end** → Combat "Lost in the Middle" |
|||
3. **RAG as a tool** → Reduce costs significantly |
|||
4. **Parent-Child pattern** → Search small, respond with large |
|||
5. **Always use overlap** → 10-20% is the standard |
|||
6. **pgvector for most cases** → Unless you have billions of vectors |
|||
7. **MCP for reusability** → One codebase, works everywhere |
|||
8. **SVG for diagrams** → Better results, lower cost |
|||
9. **Hybrid chat history** → Recent in prompt, old in vector DB |
|||
10. **RAG > Fine-tuning** → For knowledge, not behavior |
|||
|
|||
Happy coding! 🚀 |
|||
@ -0,0 +1 @@ |
|||
Learn how to build production-ready LLM applications with .NET. This comprehensive guide covers GPT-5 API changes, advanced RAG architectures with parent-child patterns, PostgreSQL pgvector integration, smart tool usage strategies, multilingual query handling, Model Context Protocol (MCP) for cross-application tool reusability, and chat history management techniques for enterprise applications. |
|||
@ -1,307 +0,0 @@ |
|||
# Artificial Intelligence |
|||
|
|||
ABP provides a simple way to integrate AI capabilities into your applications by unifying two popular .NET AI stacks under a common concept called a "workspace": |
|||
|
|||
- Microsoft.Extensions.AI `IChatClient` |
|||
- Microsoft.SemanticKernel `Kernel` |
|||
|
|||
A workspace is just a named scope. You configure providers per workspace and then resolve either default services (for the "Default" workspace) or workspace-scoped services. |
|||
|
|||
## Installation |
|||
|
|||
> This package is not included by default. Install it to enable AI features. |
|||
|
|||
It is suggested to use the ABP CLI to install the package. Open a command line window in the folder of the project (.csproj file) and type the following command: |
|||
|
|||
```bash |
|||
abp add-package Volo.Abp.AI |
|||
``` |
|||
|
|||
### Manual Installation |
|||
|
|||
Add nuget package to your project: |
|||
|
|||
```bash |
|||
dotnet add package Volo.Abp.AI |
|||
``` |
|||
|
|||
Then add the module dependency to your module class: |
|||
|
|||
```csharp |
|||
using Volo.Abp.AI; |
|||
using Volo.Abp.Modularity; |
|||
|
|||
[DependsOn(typeof(AbpAIModule))] |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
} |
|||
``` |
|||
|
|||
## Usage |
|||
|
|||
### Chat Client |
|||
|
|||
#### Default configuration (quick start) |
|||
|
|||
Configure the default workspace to inject `IChatClient` directly. |
|||
|
|||
```csharp |
|||
using Microsoft.Extensions.AI; |
|||
using Microsoft.SemanticKernel; |
|||
using Volo.Abp.AI; |
|||
using Volo.Abp.Modularity; |
|||
|
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void ConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
context.Services.PreConfigure<AbpAIOptions>(options => |
|||
{ |
|||
options.Workspaces.ConfigureDefault(configuration => |
|||
{ |
|||
configuration.ConfigureChatClient(chatClientConfiguration => |
|||
{ |
|||
chatClientConfiguration.Builder = new ChatClientBuilder( |
|||
sp => new OllamaApiClient("http://localhost:11434", "mistral") |
|||
); |
|||
}); |
|||
|
|||
// Chat client only in this quick start |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
Once configured, inject the default chat client: |
|||
|
|||
```csharp |
|||
using Microsoft.Extensions.AI; |
|||
|
|||
public class MyService |
|||
{ |
|||
private readonly IChatClient _chatClient; // default chat client |
|||
|
|||
public MyService(IChatClient chatClient) |
|||
{ |
|||
_chatClient = chatClient; |
|||
} |
|||
} |
|||
``` |
|||
|
|||
#### Workspace configuration |
|||
|
|||
Workspaces allow multiple, isolated AI configurations. Define workspace types (optionally decorated with `WorkspaceNameAttribute`). If omitted, the type’s full name is used. |
|||
|
|||
```csharp |
|||
using Volo.Abp.AI; |
|||
|
|||
[WorkspaceName("GreetingAssistant")] |
|||
public class GreetingAssistant // ChatClient-only workspace |
|||
{ |
|||
} |
|||
``` |
|||
|
|||
Configure a ChatClient workspace: |
|||
|
|||
```csharp |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void ConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
context.Services.PreConfigure<AbpAIOptions>(options => |
|||
{ |
|||
options.Workspaces.Configure<GreetingAssistant>(configuration => |
|||
{ |
|||
configuration.ConfigureChatClient(chatClientConfiguration => |
|||
{ |
|||
chatClientConfiguration.Builder = new ChatClientBuilder( |
|||
sp => new OllamaApiClient("http://localhost:11434", "mistral") |
|||
); |
|||
|
|||
chatClientConfiguration.BuilderConfigurers.Add(builder => |
|||
{ |
|||
// Anything you want to do with the builder: |
|||
// builder.UseFunctionInvocation().UseLogging(); // For example |
|||
}); |
|||
}); |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
### Semantic Kernel |
|||
|
|||
#### Default configuration |
|||
|
|||
|
|||
```csharp |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void ConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
context.Services.PreConfigure<AbpAIOptions>(options => |
|||
{ |
|||
options.Workspaces.ConfigureDefault(configuration => |
|||
{ |
|||
configuration.ConfigureKernel(kernelConfiguration => |
|||
{ |
|||
kernelConfiguration.Builder = Kernel.CreateBuilder() |
|||
.AddAzureOpenAIChatClient("...", "..."); |
|||
}); |
|||
// Note: Chat client is not configured here |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
Once configured, inject the default kernel: |
|||
|
|||
```csharp |
|||
using System.Threading.Tasks; |
|||
using Volo.Abp.AI; |
|||
|
|||
public class MyService |
|||
{ |
|||
private readonly IKernelAccessor _kernelAccessor; |
|||
public MyService(IKernelAccessor kernelAccessor) |
|||
{ |
|||
_kernelAccessor = kernelAccessor; |
|||
} |
|||
|
|||
public async Task DoSomethingAsync() |
|||
{ |
|||
var kernel = _kernelAccessor.Kernel; // Kernel might be null if no workspace is configured. |
|||
|
|||
var result = await kernel.InvokeAsync(/*... */); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
#### Workspace configuration |
|||
|
|||
```csharp |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void ConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
context.Services.PreConfigure<AbpAIOptions>(options => |
|||
{ |
|||
options.Workspaces.Configure<ContentPlanner>(configuration => |
|||
{ |
|||
configuration.ConfigureKernel(kernelConfiguration => |
|||
{ |
|||
kernelConfiguration.Builder = Kernel.CreateBuilder() |
|||
.AddOpenAIChatCompletion("...", "..."); |
|||
}); |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
#### Workspace usage |
|||
|
|||
```csharp |
|||
using Microsoft.Extensions.AI; |
|||
using Volo.Abp.AI; |
|||
using Microsoft.SemanticKernel; |
|||
|
|||
public class PlanningService |
|||
{ |
|||
private readonly IKernelAccessor<ContentPlanner> _kernelAccessor; |
|||
private readonly IChatClient<ContentPlanner> _chatClient; // available even if only Kernel is configured |
|||
|
|||
public PlanningService( |
|||
IKernelAccessor<ContentPlanner> kernelAccessor, |
|||
IChatClient<ContentPlanner> chatClient) |
|||
{ |
|||
_kernelAccessor = kernelAccessor; |
|||
_chatClient = chatClient; |
|||
} |
|||
|
|||
public async Task<string> PlanAsync(string topic) |
|||
{ |
|||
var kernel = _kernelAccessor.Kernel; // Microsoft.SemanticKernel.Kernel |
|||
// Use Semantic Kernel APIs if needed... |
|||
|
|||
var response = await _chatClient.GetResponseAsync( |
|||
[new ChatMessage(ChatRole.User, $"Create a content plan for: {topic}")] |
|||
); |
|||
return response?.Message?.Text ?? string.Empty; |
|||
} |
|||
} |
|||
``` |
|||
|
|||
## Options |
|||
|
|||
`AbpAIOptions` configuration pattern offers `ConfigureChatClient(...)` and `ConfigureKernel(...)` methods for configuration. These methods are defined in the `WorkspaceConfiguration` class. They are used to configure the `ChatClient` and `Kernel` respectively. |
|||
|
|||
`Builder` is set once and is used to build the `ChatClient` or `Kernel` instance. `BuilderConfigurers` is a list of actions that are applied to the `Builder` instance for incremental changes. These actions are executed in the order they are added. |
|||
|
|||
If a workspace configures only the Kernel, a chat client may still be exposed for that workspace through the Kernel’s service provider (when available). |
|||
|
|||
|
|||
## Advanced Usage and Customizations |
|||
|
|||
### Addding Your Own DelegatingChatClient |
|||
|
|||
If you want to build your own decorator, implement a `DelegatingChatClient` derivative and provide an extension method that adds it to the `ChatClientBuilder` using `builder.Use(...)`. |
|||
|
|||
Example sketch: |
|||
|
|||
```csharp |
|||
using Microsoft.Extensions.AI; |
|||
|
|||
public class SystemMessageChatClient : DelegatingChatClient |
|||
{ |
|||
public SystemMessageChatClient(IChatClient inner, string systemMessage) : base(inner) |
|||
{ |
|||
SystemMessage = systemMessage; |
|||
} |
|||
|
|||
public string SystemMessage { get; set; } |
|||
|
|||
public override Task<ChatResponse> GetResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default) |
|||
{ |
|||
// Mutate messages/options as needed, then call base |
|||
return base.GetResponseAsync(messages, options, cancellationToken); |
|||
} |
|||
} |
|||
|
|||
public static class SystemMessageChatClientExtensions |
|||
{ |
|||
public static ChatClientBuilder UseSystemMessage(this ChatClientBuilder builder, string systemMessage) |
|||
{ |
|||
return builder.Use(client => new SystemMessageChatClient(client, systemMessage)); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
|
|||
```cs |
|||
chatClientConfiguration.BuilderConfigurers.Add(builder => |
|||
{ |
|||
builder.UseSystemMessage("You are a helpful assistant that greets users in a friendly manner with their names."); |
|||
}); |
|||
``` |
|||
|
|||
## Technical Anatomy |
|||
|
|||
- `AbpAIModule`: Wires up configured workspaces, registers keyed services and default services for the `"Default"` workspace. |
|||
- `AbpAIOptions`: Holds `Workspaces` and provides helper methods for internal keyed service naming. |
|||
- `WorkspaceConfigurationDictionary` and `WorkspaceConfiguration`: Configure per-workspace Chat Client and Kernel. |
|||
- `ChatClientConfiguration` and `KernelConfiguration`: Hold builders and a list of ordered builder configurers. |
|||
- `WorkspaceNameAttribute`: Names a workspace; falls back to the type’s full name if not specified. |
|||
- `IChatClient<TWorkspace>`: Typed chat client for a workspace. |
|||
- `IKernelAccessor<TWorkspace>`: Provides access to the workspace’s `Kernel` instance if configured. |
|||
- `AbpAIWorkspaceOptions`: Exposes `ConfiguredWorkspaceNames` for diagnostics. |
|||
|
|||
There are no database tables for this feature; it is a pure configuration and DI integration layer. |
|||
|
|||
## See Also |
|||
|
|||
- Microsoft.Extensions.AI (Chat Client) |
|||
- Microsoft Semantic Kernel |
|||
@ -0,0 +1,31 @@ |
|||
# Artificial Intelligence |
|||
ABP Framework provides integration for AI capabilities to your application by using Microsoft's popular AI libraries. The main purpose of this integration is to provide a consistent and easy way to use AI capabilities and manage different AI providers, models and configurations in a single application. |
|||
|
|||
ABP introduces a concept called **AI Workspace**. A workspace allows you to configure isolated AI configurations for a named scope. You can then resolve AI services for a specific workspace when you need to use them. |
|||
|
|||
> ABP Framework can work with any AI library or framework that supports .NET development. However, the AI integration features explained in the following documents provide a modular and standard way to work with AI, which allows ABP developers to create reusable modules and components with AI capabilities in a standard way. |
|||
|
|||
## Installation |
|||
|
|||
Use the [ABP CLI](../../../cli/index.md) to install the [Volo.Abp.AI](https://www.nuget.org/packages/Volo.Abp.AI) NuGet package into your project. Open a command line window in the root directory of your project (`.csproj` file) and type the following command: |
|||
|
|||
```bash |
|||
abp add-package Volo.Abp.AI |
|||
``` |
|||
|
|||
*For different installation options, check [the package definition page](https://abp.io/package-detail/Volo.Abp.AI).* |
|||
|
|||
## Usage |
|||
|
|||
The `Volo.Abp.AI` package provides integration with the following libraries: |
|||
|
|||
* [Microsoft.Extensions.AI](https://learn.microsoft.com/en-us/dotnet/ai/microsoft-extensions-ai) |
|||
* [Microsoft.SemanticKernel](https://learn.microsoft.com/en-us/semantic-kernel/overview/) |
|||
|
|||
The Microsoft.Extensions.AI library is suggested for library developers to keep the library dependency minimum and simple (since it provides basic abstractions and fundamental AI provider integrations), while Semantic Kernel is suggested for applications that need rich and advanced AI integration features. |
|||
|
|||
Check the following documentation to learn how to use these libraries with the ABP integration: |
|||
|
|||
- [ABP Microsoft.Extensions.AI integration](./microsoft-extensions-ai.md) |
|||
- [ABP Microsoft.SemanticKernel integration](./microsoft-semantic-kernel.md) |
|||
|
|||
@ -0,0 +1,176 @@ |
|||
# Microsoft.Extensions.AI |
|||
[Microsoft.Extensions.AI](https://learn.microsoft.com/en-us/dotnet/ai/microsoft-extensions-ai) is a library that provides a unified API for integrating AI services. It is a part of the Microsoft AI Extensions Library. It is used to integrate AI services into your application. This documentation is about the usage of this library with ABP Framework. Make sure you have read the [Artificial Intelligence](./index.md) documentation before reading this documentation. |
|||
|
|||
## Usage |
|||
|
|||
You can resolve `IChatClient` to access configured chat client from your service and use it directly. |
|||
|
|||
```csharp |
|||
public class MyService |
|||
{ |
|||
private readonly IChatClient _chatClient; |
|||
public MyService(IChatClient chatClient) |
|||
{ |
|||
_chatClient = chatClient; |
|||
} |
|||
|
|||
public async Task<string> GetResponseAsync(string prompt) |
|||
{ |
|||
return await _chatClient.GetResponseAsync(prompt); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
You can also resolve `IChatClientAccessor` to access the `IChatClient` optionally configured scenarios such as developing a module or a service that may use AI capabilities **optionally**. |
|||
|
|||
|
|||
```csharp |
|||
public class MyService |
|||
{ |
|||
private readonly IChatClientAccessor _chatClientAccessor; |
|||
public MyService(IChatClientAccessor chatClientAccessor) |
|||
{ |
|||
_chatClientAccessor = chatClientAccessor; |
|||
} |
|||
|
|||
public async Task<string> GetResponseAsync(string prompt) |
|||
{ |
|||
var chatClient = _chatClientAccessor.ChatClient; |
|||
if (chatClient is null) |
|||
{ |
|||
return "No chat client configured"; |
|||
} |
|||
return await chatClient.GetResponseAsync(prompt); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
### Workspaces |
|||
|
|||
Workspaces are a way to configure isolated AI configurations for a named scope. You can define a workspace by decorating a class with the `WorkspaceNameAttribute` attribute that carries the workspace name. |
|||
- Workspace names must be unique. |
|||
- Workspace names cannot contain spaces _(use underscores or camelCase)_. |
|||
- Workspace names are case-sensitive. |
|||
|
|||
```csharp |
|||
using Volo.Abp.AI; |
|||
|
|||
[WorkspaceName("CommentSummarization")] |
|||
public class CommentSummarization |
|||
{ |
|||
} |
|||
``` |
|||
|
|||
> [!NOTE] |
|||
> If you don't specify the workspace name, the full name of the class will be used as the workspace name. |
|||
|
|||
You can resolve generic versions of `IChatClient` and `IChatClientAccessor` services for a specific workspace as generic arguments. If Chat Client is not configured for a workspace, you will get `null` from the accessor services. You should check the accessor before using it. This applies only for specified workspaces. Another workspace may have a configured Chat Client. |
|||
|
|||
`IChatClient<TWorkSpace>` or `IChatClientAccessor<TWorkSpace>` can be resolved to access a specific workspace's chat client. This is a typed chat client and can be configured separately from the default chat client. |
|||
|
|||
|
|||
Example of resolving a typed chat client: |
|||
```csharp |
|||
public class MyService |
|||
{ |
|||
private readonly IChatClient<CommentSummarization> _chatClient; |
|||
|
|||
public MyService(IChatClient<CommentSummarization> chatClient) |
|||
{ |
|||
_chatClient = chatClient; |
|||
} |
|||
|
|||
public async Task<string> GetResponseAsync(string prompt) |
|||
{ |
|||
return await _chatClient.GetResponseAsync(prompt); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
Example of resolving a typed chat client accessor: |
|||
```csharp |
|||
public class MyService |
|||
{ |
|||
private readonly IChatClientAccessor<CommentSummarization> _chatClientAccessor; |
|||
} |
|||
public async Task<string> GetResponseAsync(string prompt) |
|||
{ |
|||
var chatClient = _chatClientAccessor.ChatClient; |
|||
if (chatClient is null) |
|||
{ |
|||
return "No chat client configured"; |
|||
} |
|||
return await chatClient.GetResponseAsync(prompt); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
## Configuration |
|||
|
|||
`AbpAIWorkspaceOptions` configuration is used to configure AI workspaces and their configurations. You can configure the default workspace and also configure isolated workspaces by using the this options class.It has to be configured **before the services are configured** in the `PreConfigure` method of your module class. It is important since the services are registered after the configuration is applied. |
|||
|
|||
- `AbpAIWorkspaceOptions` has a `Workspaces` property that is type of `WorkspaceConfigurationDictionary` which is a dictionary of workspace names and their configurations. It provides `Configure<T>` and `ConfigureDefault` methods to configure the default workspace and also configure isolated workspaces by using the workspace type. |
|||
|
|||
- Configure method passes `WorkspaceConfiguration` object to the configure action. You can configure the `ChatClient` by using the `ConfigureChatClient` method. |
|||
|
|||
- `ConfigureChatClient()` method passes `ChatClientConfiguration` parameter to the configure action. You can configure the `Builder` and `BuilderConfigurers` by using the `ConfigureBuilder` method. |
|||
- `Builder` is set once and is used to build the `ChatClient` instance. |
|||
- `BuilderConfigurers` is a list of actions that are applied to the `Builder` instance for incremental changes.These actions are executed in the order they are added. |
|||
|
|||
To configure a chat client, you'll need a LLM provider package such as [Microsoft.Extensions.AI.OpenAI](https://www.nuget.org/packages/Microsoft.Extensions.AI.OpenAI) or [OllamaSharp](https://www.nuget.org/packages/OllamaSharp/) to configure a chat client. |
|||
|
|||
_The following example requires [OllamaSharp](https://www.nuget.org/packages/OllamaSharp/) package to be installed._ |
|||
|
|||
|
|||
Demonstration of the default workspace configuration: |
|||
```csharp |
|||
[DependsOn(typeof(AbpAIModule))] |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void PreConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
PreConfigure<AbpAIWorkspaceOptions>(options => |
|||
{ |
|||
options.Workspaces.ConfigureDefault(configuration => |
|||
{ |
|||
configuration.ConfigureChatClient(chatClientConfiguration => |
|||
{ |
|||
chatClientConfiguration.Builder = new ChatClientBuilder( |
|||
sp => new OllamaApiClient("http://localhost:11434", "mistral") |
|||
); |
|||
}); |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
|
|||
Demonstration of the isolated workspace configuration: |
|||
```csharp |
|||
[DependsOn(typeof(AbpAIModule))] |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void PreConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
PreConfigure<AbpAIWorkspaceOptions>(options => |
|||
{ |
|||
options.Workspaces.Configure<CommentSummarization>(configuration => |
|||
{ |
|||
configuration.ConfigureChatClient(chatClientConfiguration => |
|||
{ |
|||
chatClientConfiguration.Builder = new ChatClientBuilder( |
|||
sp => new OllamaApiClient("http://localhost:11434", "mistral") |
|||
); |
|||
}); |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
|
|||
## See Also |
|||
|
|||
- [Usage of Semantic Kernel](./microsoft-semantic-kernel.md) |
|||
- [AI Samples for .NET](https://learn.microsoft.com/en-us/samples/dotnet/ai-samples/ai-samples/) |
|||
@ -0,0 +1,135 @@ |
|||
# Microsoft.SemanticKernel |
|||
[Microsoft.SemanticKernel](https://learn.microsoft.com/en-us/semantic-kernel/overview/) is a library that provides a unified SDK for integrating AI services. This documentation is about the usage of this library with ABP Framework. Make sure you have read the [Artificial Intelligence](./index.md) documentation before reading this documentation. |
|||
|
|||
## Usage |
|||
|
|||
Semantic Kernel can be used by resolving `IKernelAccessor` service that carries the `Kernel` instance. Kernel might be `null` if no workspace is configured. You should check the kernel before using it. |
|||
|
|||
```csharp |
|||
public class MyService |
|||
{ |
|||
private readonly IKernelAccessor _kernelAccessor; |
|||
public MyService(IKernelAccessor kernelAccessor) |
|||
{ |
|||
_kernelAccessor = kernelAccessor; |
|||
} |
|||
|
|||
public async Task<string> GetResponseAsync(string prompt) |
|||
{ |
|||
var kernel = _kernelAccessor.Kernel; |
|||
if (kernel is null) |
|||
{ |
|||
return "No kernel configured"; |
|||
} |
|||
return await kernel.InvokeAsync(prompt); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
### Workspaces |
|||
|
|||
Workspaces are a way to configure isolated AI configurations for a named scope. You can define a workspace by decorating a class with the `WorkspaceNameAttribute` attribute that carries the workspace name. |
|||
- Workspace names must be unique. |
|||
- Workspace names cannot contain spaces _(use underscores or camelCase)_. |
|||
- Workspace names are case-sensitive. |
|||
|
|||
```csharp |
|||
using Volo.Abp.AI; |
|||
|
|||
[WorkspaceName("CommentSummarization")] |
|||
public class CommentSummarization |
|||
{ |
|||
} |
|||
``` |
|||
|
|||
> [!NOTE] |
|||
> If you don't specify the workspace name, the full name of the class will be used as the workspace name. |
|||
|
|||
You can resolve generic versions of `IKernelAccessor` service for a specific workspace as generic arguments. If Kernel is not configured for a workspace, you will get `null` from the accessor service. You should check the accessor before using it. This applies only for specified workspaces. Another workspace may have a configured Kernel. |
|||
|
|||
|
|||
`IKernelAccessor<TWorkSpace>` can be resolved to access a specific workspace's kernel. This is a typed kernel accessor and each workspace can have its own kernel configuration. |
|||
|
|||
Example of resolving a typed kernel accessor: |
|||
```csharp |
|||
public class MyService |
|||
{ |
|||
private readonly IKernelAccessor<CommentSummarization> _kernelAccessor; |
|||
} |
|||
public async Task<string> GetResponseAsync(string prompt) |
|||
{ |
|||
var kernel = _kernelAccessor.Kernel; |
|||
if (kernel is null) |
|||
{ |
|||
return "No kernel configured"; |
|||
} |
|||
return await kernel.InvokeAsync(prompt); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
## Configuration |
|||
|
|||
`AbpAIWorkspaceOptions` configuration is used to configure AI workspaces and their configurations. You can configure the default workspace and also configure isolated workspaces by using the this options class.It has to be configured **before the services are configured** in the `PreConfigure` method of your module class. It is important since the services are registered after the configuration is applied. |
|||
|
|||
- `AbpAIWorkspaceOptions` has a `Workspaces` property that is type of `WorkspaceConfigurationDictionary` which is a dictionary of workspace names and their configurations. It provides `Configure<T>` and `ConfigureDefault` methods to configure the default workspace and also configure isolated workspaces by using the workspace type. |
|||
|
|||
- Configure method passes `WorkspaceConfiguration` object to the configure action. You can configure the `Kernel` by using the `ConfigureKernel` method. |
|||
|
|||
- `ConfigureKernel()` method passes `KernelConfiguration` parameter to the configure action. You can configure the `Builder` and `BuilderConfigurers` by using the `ConfigureBuilder` method. |
|||
- `Builder` is set once and is used to build the `Kernel` instance. |
|||
- `BuilderConfigurers` is a list of actions that are applied to the `Builder` instance for incremental changes.These actions are executed in the order they are added. |
|||
|
|||
To configure a kernel, you'll need a kernel connector package such as [Microsoft.SemanticKernel.Connectors.OpenAI](Microsoft.SemanticKernel.Connectors.OpenAI) to configure a kernel to use a specific LLM provider. |
|||
|
|||
_The following example requires [Microsoft.SemanticKernel.Connectors.AzureOpenAI](Microsoft.SemanticKernel.Connectors.AzureOpenAI) package to be installed._ |
|||
|
|||
Demonstration of the default workspace configuration: |
|||
```csharp |
|||
[DependsOn(typeof(AbpAIModule))] |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void PreConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
PreConfigure<AbpAIOptions>(options => |
|||
{ |
|||
options.Workspaces.ConfigureDefault(configuration => |
|||
{ |
|||
configuration.ConfigureKernel(kernelConfiguration => |
|||
{ |
|||
kernelConfiguration.Builder = Kernel.CreateBuilder() |
|||
.AddAzureOpenAIChatClient("...", "..."); |
|||
}); |
|||
// Note: Chat client is not configured here |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
Demonstration of the isolated workspace configuration: |
|||
```csharp |
|||
[DependsOn(typeof(AbpAIModule))] |
|||
public class MyProjectModule : AbpModule |
|||
{ |
|||
public override void PreConfigureServices(ServiceConfigurationContext context) |
|||
{ |
|||
PreConfigure<AbpAIOptions>(options => |
|||
{ |
|||
options.Workspaces.Configure<CommentSummarization>(configuration => |
|||
{ |
|||
configuration.ConfigureKernel(kernelConfiguration => |
|||
{ |
|||
kernelConfiguration.Builder = Kernel.CreateBuilder() |
|||
.AddAzureOpenAIChatClient("...", "..."); |
|||
}); |
|||
}); |
|||
}); |
|||
} |
|||
} |
|||
``` |
|||
|
|||
## See Also |
|||
|
|||
- [Usage of Microsoft.Extensions.AI](./microsoft-extensions-ai.md) |
|||
- [AI Samples for .NET](https://learn.microsoft.com/en-us/samples/dotnet/ai-samples/ai-samples/) |
|||
|
Before Width: | Height: | Size: 407 KiB After Width: | Height: | Size: 559 KiB |
|
Before Width: | Height: | Size: 10 KiB After Width: | Height: | Size: 25 KiB |
|
Before Width: | Height: | Size: 41 KiB After Width: | Height: | Size: 41 KiB |
@ -0,0 +1,38 @@ |
|||
using System.Linq; |
|||
using System.Threading.Tasks; |
|||
using Volo.Abp.Authorization.Permissions; |
|||
|
|||
namespace Volo.Abp.Authorization.TestServices; |
|||
|
|||
public class TestProhibitedPermissionValueProvider1 : PermissionValueProvider |
|||
{ |
|||
public TestProhibitedPermissionValueProvider1(IPermissionStore permissionStore) : base(permissionStore) |
|||
{ |
|||
} |
|||
|
|||
public override string Name => "TestProhibitedPermissionValueProvider1"; |
|||
|
|||
public override Task<PermissionGrantResult> CheckAsync(PermissionValueCheckContext context) |
|||
{ |
|||
var result = PermissionGrantResult.Undefined; |
|||
if (context.Permission.Name == "MyPermission8" || context.Permission.Name == "MyPermission9") |
|||
{ |
|||
result = PermissionGrantResult.Granted; |
|||
} |
|||
|
|||
return Task.FromResult(result); |
|||
} |
|||
|
|||
public override Task<MultiplePermissionGrantResult> CheckAsync(PermissionValuesCheckContext context) |
|||
{ |
|||
var result = new MultiplePermissionGrantResult(); |
|||
foreach (var name in context.Permissions.Select(x => x.Name)) |
|||
{ |
|||
result.Result.Add(name, name == "MyPermission8" || name == "MyPermission9" |
|||
? PermissionGrantResult.Granted |
|||
: PermissionGrantResult.Undefined); |
|||
} |
|||
|
|||
return Task.FromResult(result); |
|||
} |
|||
} |
|||
@ -0,0 +1,38 @@ |
|||
using System.Linq; |
|||
using System.Threading.Tasks; |
|||
using Volo.Abp.Authorization.Permissions; |
|||
|
|||
namespace Volo.Abp.Authorization.TestServices; |
|||
|
|||
public class TestProhibitedPermissionValueProvider2 : PermissionValueProvider |
|||
{ |
|||
public TestProhibitedPermissionValueProvider2(IPermissionStore permissionStore) : base(permissionStore) |
|||
{ |
|||
} |
|||
|
|||
public override string Name => "TestProhibitedPermissionValueProvider2"; |
|||
|
|||
public override Task<PermissionGrantResult> CheckAsync(PermissionValueCheckContext context) |
|||
{ |
|||
var result = PermissionGrantResult.Undefined; |
|||
if (context.Permission.Name == "MyPermission8" || context.Permission.Name == "MyPermission9") |
|||
{ |
|||
result = PermissionGrantResult.Prohibited; |
|||
} |
|||
|
|||
return Task.FromResult(result); |
|||
} |
|||
|
|||
public override Task<MultiplePermissionGrantResult> CheckAsync(PermissionValuesCheckContext context) |
|||
{ |
|||
var result = new MultiplePermissionGrantResult(); |
|||
foreach (var name in context.Permissions.Select(x => x.Name)) |
|||
{ |
|||
result.Result.Add(name, name == "MyPermission8" || name == "MyPermission9" |
|||
? PermissionGrantResult.Prohibited |
|||
: PermissionGrantResult.Undefined); |
|||
} |
|||
|
|||
return Task.FromResult(result); |
|||
} |
|||
} |
|||
Some files were not shown because too many files changed in this diff
Loading…
Reference in new issue