AI Server can be configured in several ways:
- install.sh Script: Run the
install.sh
script to set up the AI Server and ComfyUI Agent. - .env File: Update the
.env
file with your API keys and run the AI Server for the first time. - Admin Portal: Use the Admin Portal to add, edit, or remove AI Providers and generate AI Server API keys.
Running the Installer​
The install.sh
script is the quickest way to get AI Server up and running with the default configuration. This is ideal for local development and testing.
To run the installer:
git clone https://github.com/ServiceStack/ai-server.git
cd ai-server
cat install.sh | bash
The installer will prompt you to configure your AI Providers and optionally add the ComfyUI Agent.
.env
Configuration​
The installer populates the .env
file with the choices you made during the installation script. You can also manually configure the .env
file with your API keys and settings.
OPENAI_API_KEY=your_openai_api_key
ANTHROPIC_API_KEY=your_anthropic_api_key
AUTH_SECRET=p@55wOrd
ASSETS_BASE_URL=http://localhost:5006
After these values are set in your .env
file, you can run the AI Server for the first time via docker compose:
docker compose up
This will perform an initial setup, saving providers configuration in the SQLite database. From here, you can manage your AI Providers via the Admin Portal.
INFO
The default credentials to access the Admin Portal are p@55wOrd
, this can be changed in your .env
file by setting the AUTH_SECRET
key.
Using the Admin Portal​
The Admin Portal provides a more interactive way to manage your AI Providers after the AI Server is running.
To access the Admin Portal:
- Navigate to http://localhost:5006/admin.
- Log in with the default credentials
p@55wOrd
. - Click on the AI Providers tab to view and manage your AI Providers.
Here you can add, edit, or remove AI Providers, as well as generate API keys for each provider.
AI Server supports the following AI Providers:
- OpenAI: OpenAI Chat API
- Anthropic: Anthropic Claude API
- Google: Google Cloud AI
- OpenRouter: OpenRouter API
- Mistral: Mistral API
- GROQ: GROQ API
- Ollama: Ollama API
Media Providers can also be configured in the Admin Portal. These include:
- ComfyUI: ComfyUI Agent
- Image Generation
- Text-to-Speech
- Speech-to-Text
- Video & Image Processing
- Replicate: Replicate API
- Image Generation
- OpenAI: OpenAI API
- Image Generation
- Text-to-Speech
Generating AI Server API Keys​
API keys are used to authenticate requests to AI Server and are generated via the Admin Portal.
Here you can create new API keys, view existing keys, and revoke keys as needed.
Keys can be created with expiration dates, and restrictions to specific API endpoints, along with notes to help identify the key's purpose.
Stored File Management​
AI Server stores results of the AI operations in a pre-configured paths.
- Artifacts: AI generated images, audio, and video files, default path is
App_Data/artifacts
. - Files: Cached variants and processed files, default path is
App_Data/files
.
These paths can be configured in the .env
file by setting the ARTIFACTS_PATH
and AI_FILES_PATH
keys.