# LiteLLM

LiteLLM is the cluster-local LLM proxy for OpenWebUI. It routes requests to the
external llama.cpp OpenAI-compatible endpoint at
`http://framework-llm.open-webui.svc.cluster.local:8080/v1`.

The public dashboard is exposed at `https://litellm.noxxos.nl` through
LiteLLM's native Authentik SSO. API clients should use LiteLLM bearer keys.

## Secrets

Create the LiteLLM secrets before syncing. The Helm chart references these
secrets directly, so the LiteLLM pod will fail with `secret "litellm-sso" not
found` until the SSO secret exists in the `litellm` namespace.

Create the LiteLLM master key and salt:

```bash
kubectl create namespace litellm
kubectl -n litellm create secret generic litellm-secrets \
  --from-literal=master-key='sk-<litellm-master-key>' \
  --from-literal=salt-key='<random-high-entropy-salt>'
```

OpenWebUI needs a copy of the LiteLLM key in its own namespace:

```bash
kubectl -n open-webui create secret generic litellm-secrets \
  --from-literal=openwebui-api-keys='0p3n-w3bu!;sk-<litellm-master-key>'
```

`openwebui-api-keys` is semicolon-separated because OpenWebUI is configured with
two OpenAI-compatible endpoints: its internal Pipelines service first, then
LiteLLM.

Create an Authentik OAuth2/OIDC provider and application for LiteLLM.

External URL:

```text
https://litellm.noxxos.nl
```

Allowed redirect URI:

```text
https://litellm.noxxos.nl/sso/callback
```

Launch URL:

```text
https://litellm.noxxos.nl/ui
```

Include the scopes `openid profile email litellm_role`.

Create an Authentik scope mapping named `litellm_role`:

```python
if ak_is_group_member(request.user, name="admins"):
    return {"litellm_role": "proxy_admin"}
return {"litellm_role": "internal_user"}
```

Then create the LiteLLM SSO secret before syncing the app:

```bash
kubectl -n litellm create secret generic litellm-sso \
  --from-literal=GENERIC_CLIENT_SECRET='<authentik-client-secret>'
```