Skip to content

Getting Started

The AI Workspace enables you to manage AI gateways and LLM providers. This guide gets AI Workspace running locally with Docker Compose in under five minutes, then walks you through creating your first AI gateway and LLM provider.

Prerequisites

  • Docker with the Compose plugin (docker compose version)
  • Ports 5380 and 9243 available on your machine
  • curl and unzip installed

Step 1: Download AI Workspace

Run this command in your terminal to download and unzip AI Workspace:

curl -sLO https://github.com/wso2/api-platform/releases/download/portals/ai-workspace/v1.0.0-alpha2/wso2apip-ai-workspace-1.0.0-alpha2.zip && \
unzip wso2apip-ai-workspace-1.0.0-alpha2.zip

Step 2: Run the Setup Script

cd wso2apip-ai-workspace-1.0.0-alpha2
./scripts/setup.sh

The script generates everything the stack requires: the encryption and JWT signing keys (written to api-platform.env), the admin username and password (printed to the terminal only), and the TLS certificate shared by both services (written to resources/certificates/).

Save the printed admin username and password

The admin password is shown only once and is not stored in api-platform.env or anywhere else. If you lose it, rerun ./scripts/setup.sh --force to generate a new one.

Step 3: Start the Stack

docker compose up -d

Step 4: Open AI Workspace

Navigate to https://localhost:5380 and sign in with the admin credentials printed by setup.sh:

AI Workspace file-based login window with Username and Password fields

Browser trust warning?

The generated TLS certificates are self-signed. Click Advanced > Proceed to continue, then return to the workspace.

About this login

These credentials come from file-based authentication, generated by the setup script and stored in your local environment configuration. It's the quickest way to try AI Workspace, but before you move to a production or shared environment, connect a real identity provider to manage user login. See Authentication in AI Workspace.

Step 5: Create an AI Gateway

An AI gateway is the runtime that processes and routes requests between your applications and LLM providers. You need at least one gateway before configuring providers or proxies.

  1. Navigate to AI Gateways in the left navigation menu.
  2. Click + Add AI Gateway.
  3. Fill in the Name and URL, then click Add Gateway.
  4. Copy the Gateway Registration Token and save it securely immediately — it is shown only once. Then follow the setup instructions to start the gateway runtime.
  5. Once connected, the gateway status changes from Inactive to Active.

For detailed instructions, see AI Gateways.

Step 6: Configure an LLM Provider

An LLM provider connects AI Workspace to an AI service platform such as OpenAI, Anthropic, or Azure OpenAI.

  1. Navigate to LLM > Service Provider.
  2. Click + Add New Provider and select your provider type.
  3. Fill in the Name, Version, and API Key, then click Add Provider.
  4. Configure how applications authenticate when they access this provider through the gateway.
  5. Click Deploy to Gateway and select your active gateway.

For detailed instructions, see Configure LLM Provider.

What's Next

  • Manage your provider: configure connection, access control, security, rate limiting, guardrails, and models

Note

You can optionally create an LLM proxy if a specific Gen AI application or agent needs its own guardrails, authentication, exposed resources, routing, or other app-specific controls on top of providers.