diff --git a/modules/ROOT/pages/tinymceai-on-premises-getting-started.adoc b/modules/ROOT/pages/tinymceai-on-premises-getting-started.adoc index b06de2382a..a1efce09d3 100644 --- a/modules/ROOT/pages/tinymceai-on-premises-getting-started.adoc +++ b/modules/ROOT/pages/tinymceai-on-premises-getting-started.adoc @@ -181,7 +181,7 @@ Use the matching network name in `--network` below. First, load the `.env` file: set -a && source .env && set +a ---- -Then start the AI service container: +Then start the AI service container. The `docker run` command maps the friendly `.env` names onto the service's own environment variables — for example, `AI_LICENCE_KEY` is passed to the container as `LICENSE_KEY`, and `MANAGEMENT_SECRET` as `ENVIRONMENTS_MANAGEMENT_SECRET_KEY`: [source,bash] ---- @@ -203,6 +203,13 @@ docker run --init -d -p 8000:8000 \ registry.containers.tiny.cloud/ai-service-tiny:latest ---- +[IMPORTANT] +==== +This launch command configures a single OpenAI provider, through the `PROVIDERS` value and `$OPENAI_API_KEY`. The AI service only receives the environment variables explicitly passed in the `docker run` command, so adding `PROVIDERS`, `MODELS`, or other provider settings to the `.env` file alone has no effect. + +To use any other provider — `openai-compatible` (for example Databricks, Ollama, or vLLM), Azure, Amazon Bedrock, or Google Vertex — edit the `docker run` command directly: replace the `PROVIDERS` value and add a `MODELS` array. The `MODELS` variable is required for every provider except direct OpenAI, Anthropic, and Google, which have built-in model routing. See xref:tinymceai-on-premises-providers.adoc[LLM providers] for the full `PROVIDERS` and `MODELS` configuration. +==== + NOTE: The AI service contacts `license.containers.tiny.cloud` on startup to validate the license key. Ensure this endpoint is reachable from the container. No customer data is sent during this check. TIP: If the container already exists from a previous attempt, remove it first with `docker rm -f ai-service`.