You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Generating code with large language models (LLMs) is a rapidly growing area of interest for developers. While LLMs are often capable of generating working code it can be a challenge to generate code for consistently evolving frameworks like Angular.
3
+
4
+
Advanced instructions and prompting are an emerging standard for supporting modern code generation with domain specific details. This section contains curated content and resources to support more accurate code generation for Angular and LLMs.
5
+
6
+
## Providing Context with `llms.txt`
7
+
`llms.txt` is a proposed standard for websites designed to help LLMs better understand and process their content. The Angular team has developed two versions of this file to help LLMs and tools that use LLMs for code generation to create better Angular code:
8
+
9
+
*[`llms.txt`](/llms.txt) - an index file providing links to key files and resources.
10
+
*[`llms-full.txt`](/llms-full.txt) - a more robust compiled set of resources describing how Angular works and how to build Angular applications.
11
+
12
+
Be sure [to check out the overview page](/ai) for more information on how to integrate AI into your Angular applications.
Copy file name to clipboardExpand all lines: adev/src/content/ai/overview.md
+4-4Lines changed: 4 additions & 4 deletions
Original file line number
Diff line number
Diff line change
@@ -11,7 +11,7 @@ Developing features like these would have previously required deep domain expert
11
11
* Strong, signal-based architecture designed to dynamically manage data and state
12
12
* Angular integrates seamlessly with AI SDKs and APIs
13
13
14
-
This guide demonstrates how you can use [Genkit](/ai#build-ai-powered-applications-with-genkit-and-angular), [Firebase AI Logic](https://firebase.google.com/products/firebase-ai-logic), and the [Gemini API](https://ai.google.dev/) to infuse your Angular apps with AI today. This guide will jumpstart your AI-powered web app development journey by explaining how to begin integrating AI into Angular apps. This guide also shares resources, such as starter kits, example code, and recipes for common workflows, you can use to get up to speed quickly.
14
+
This guide demonstrates how you can use [Genkit](/ai#build-ai-powered-applications-with-genkit-and-angular), [Firebase AI Logic](/ai#build-ai-powered-applications-with-firebase-ai-logic-and-angular), and the [Gemini API](/ai#build-ai-powered-applications-with-gemini-api-and-angular) to infuse your Angular apps with AI today. This guide will jumpstart your AI-powered web app development journey by explaining how to begin integrating AI into Angular apps. This guide also shares resources, such as starter kits, example code, and recipes for common workflows, you can use to get up to speed quickly.
15
15
16
16
To get started, you should have a basic understanding of Angular. New to Angular? Try our [essentials guide](/essentials) or our [getting started tutorials](/tutorials).
17
17
@@ -20,20 +20,20 @@ NOTE: While this page features integrations and examples with Google AI products
20
20
## Getting Started
21
21
Building AI-powered applications is a new and rapidly developing field. It can be challenging to decide where to start and which technologies to choose. The following section provides three options to choose from:
22
22
23
-
1.*Genkit* gives you the choice of [supported model and interface with a unified API](https://firebase.google.com/docs/genkit) for building full-stack applications. Ideal for applications requiring sophisticated back-end AI logic, such as personalized recommendations.
23
+
1.*Genkit* gives you the choice of [supported model and interface with a unified API](https://genkit.dev) for building full-stack applications. Ideal for applications requiring sophisticated back-end AI logic, such as personalized recommendations.
24
24
25
25
1.*Firebase AI Logic* provides a secure client-side API for Google's models to build client-side only applications or mobile apps. Best for interactive AI features directly in the browser, such as real-time text analysis or basic chatbots.
26
26
27
27
1.*Gemini API* enables you to build an application that uses the methods and functionality exposed through the API surface directly, best for full-stack applications. Suitable for applications needing direct control over AI models, like custom image generation or deep data processing.
28
28
29
29
### Build AI-powered applications with Genkit and Angular
30
-
[Genkit](https://firebase.google.com/docs/genkit) is an open-source toolkit designed to help you build AI-powered features in web and mobile apps. It offers a unified interface for integrating AI models from Google, OpenAI, Anthropic, Ollama, and more, so you can explore and choose the best models for your needs. As a server-side solution, your web apps need a supported server environment, such as a node-based server in order to integrate with Genkit. Building a full-stack app using Angular SSR gives you the starting server-side code, for example.
30
+
[Genkit](https://genkit.dev) is an open-source toolkit designed to help you build AI-powered features in web and mobile apps. It offers a unified interface for integrating AI models from Google, OpenAI, Anthropic, Ollama, and more, so you can explore and choose the best models for your needs. As a server-side solution, your web apps need a supported server environment, such as a node-based server in order to integrate with Genkit. Building a full-stack app using Angular SSR gives you the starting server-side code, for example.
31
31
32
32
Here are examples of how to build with Genkit and Angular:
33
33
34
34
*[Agentic Apps with Genkit and Angular starter-kit](https://github.com/angular/examples/tree/main/genkit-angular-starter-kit)— New to building with AI? Start here with a basic app that features an agentic workflow. Perfect place to start for your first AI building experience.
35
35
36
-
*[Use Genkit in an Angular app](https://firebase.google.com/docs/genkit/angular)— Build a basic application that uses Genkit Flows, Angular and Gemini 2.0 Flash. This step-by-step walkthrough guides you through creating a full-stack Angular application with AI features.
36
+
*[Use Genkit in an Angular app](https://genkit.dev/docs/angular/)— Build a basic application that uses Genkit Flows, Angular and Gemini 2.0 Flash. This step-by-step walkthrough guides you through creating a full-stack Angular application with AI features.
37
37
38
38
*[Dynamic Story Generator app](https://github.com/angular/examples/tree/main/genkit-angular-story-generator)— Learn to build an agentic Angular app powered by Genkit, Gemini and Imagen 3 to dynamically generate a story based on user interaction featuring beautiful image panels to accompany the events that take place. Start here if you'd like to experiment with a more advanced use-case.
0 commit comments