Add initial ai-server quickstart.

Author: Layoric

MyApp/_pages/ai-server/index.md

@@ -0,0 +1,50 @@
+---
+title: Overview
+description: Introduction to AI Server and its key features
+---
+
+# Overview
+
+AI Server is an independent microservice designed to provide a comprehensive suite of AI features for your applications. It serves as a private gateway to process LLM, AI, and image transformation requests, dynamically delegating tasks across multiple providers including Ollama, OpenRouter, Replicate, Comfy UI, Whisper, and ffmpeg.
+
+
+## Key Features
+
+- **Unified AI Gateway**: Centralize all your AI requests through a single self-hosted service.
+- **Multi-Provider Support**: Seamlessly integrate with Ollama, Open AI, Comfy UI, and more.
+- **Type-Safe Integrations**: Native end-to-end typed integrations for popular languages including C#, TypeScript, Python, and more.
+- **Secure Access**: API key authentication to protect your AI resources.
+- **Managed File Storage**: Built-in CDN-hostable storage for AI-generated assets.
+- **Background Job Processing**: Efficient handling of long-running AI tasks.
+- **Custom Deployment**: Run as a single Docker container, with optional GPU-equipped agents for advanced tasks.
+
+## Why Use AI Server?
+
+AI Server simplifies the integration and management of AI capabilities in your applications:
+
+1. **Centralized Management**: Manage all your AI providers and requests from a single interface.
+2. **Cost Control**: Monitor and control usage across your organization with detailed request history.
+3. **Flexibility**: Easy to scale and adapt as your AI needs evolve.
+4. **Security**: Keep your AI operations behind your firewall with a private, managed gateway.
+5. **Developer-Friendly**: Type-safe APIs and integrations for a smooth development experience.
+
+## Supported AI Capabilities
+
+- **Large Language Models**: Integrate with Open AI Chat, Ollama, and various API gateways.
+- **Image Generation and Manipulation**: Leverage Comfy UI for text-to-image, image-to-image, and more.
+- **Audio Processing**: Text-to-speech, speech-to-text, and audio manipulations.
+- **Video Processing**: Format conversions, scaling, cropping, and more with ffmpeg integration.
+
+## Getting Started for Developers
+
+1. **Setup**: Follow the Quick Start guide to deploy AI Server.
+2. **Configuration**: Use the Admin UI to add your AI providers and generate API keys.
+3. **Integration**: Choose your preferred language and use ServiceStack's Add ServiceStack Reference to generate type-safe client libraries.
+4. **Development**: Start making API calls to AI Server from your application, leveraging the full suite of AI capabilities.
+
+## Learn More
+
+- Website: [openai.servicestack.net](https://openai.servicestack.net)
+- GitHub: [github.com/ServiceStack/ai-server](https://github.com/ServiceStack/ai-server)
+
+AI Server is actively developed and continuously expanding its capabilities. Stay tuned for updates and new features as we work towards our first V1 release.

MyApp/_pages/ai-server/install/index.md

@@ -0,0 +1,62 @@
+---
+title: Quick Start
+description: Get AI Server up and running quickly
+---
+
+## Quick Start
+
+To get started with AI Server, we need can use the following steps:
+
+- **Clone the Repository**: Clone the AI Server repository from GitHub.
+- **Edit the example.env File**: Update the example.env file with your desired settings.
+- **Run the Docker Compose**: Start the AI Server with Docker Compose.
+
+### Clone the Repository
+
+Clone the AI Server repository from GitHub:
+
+```sh
+git clone https://github.com/ServiceStack/ai-server
+```
+
+### Edit the example.env File
+
+Create your own `.env` file by copying the `example.env` file:
+
+```sh
+cp example.env .env
+```
+
+And then edit the `.env` file with your desired settings:
+
+```sh
+# OpenAI API Key - Head to https://platform.openai.com/account/api-keys to get your API key
+# OPENAI_API_KEY=your-openai-api-key
+# Google Cloud API Key - Head to https://console.cloud.google.com/apis/credentials to get your API key
+# GOOGLE_API_KEY=your-google-api-key
+# OpenRouter API Key - Head to https://openrouter.io/ to get your API key
+# OPENROUTER_API_KEY=your-openrouter-api-key
+# Mistral API Key - Head to https://mistral.ai/ to get your API key
+# MISTRAL_API_KEY=your-mistral-api-key
+# GROQ API Key - Head to https://groq.com/ to get your API key
+# GROQ_API_KEY=your-groq-api-key
+# Custom Port for the AI Server
+PORT=5005
+```
+
+These keys are used during the AI Server initial database setup to configure the AI providers based on the keys you *uncomment and provide*.
+
+### Run the Docker Compose
+
+Start the AI Server with Docker Compose:
+
+```sh
+docker compose up
+```
+
+## Accessing AI Server
+
+Once the AI Server is running, you can access the Admin UI at [http://localhost:5005](http://localhost:5005) to configure your AI providers and generate API keys.
+If you first ran the AI Server with configured API Keys in your `.env` file, you providers will be automatically configured for the related services.
+
+> You can reset the process by deleting your local `App_Data` directory and rerunning `docker compose up`.