| .. | ||
| examples | ||
| templates | ||
| tests | ||
| .helmignore | ||
| Chart.yaml | ||
| DNS_CONFIGURATION.md | ||
| readme.md | ||
| values.yaml | ||
LibreChat Helm Chart
This Librechat Helm Chart provides an easy, light weight template to deploy LibreChat on Kubernetes
Variables
In this Chart, LibreChat will only work with environment Variables. You can Specify Vars and Secret using an existing Secret (This can be generated by creating an Env File and converting it to a Kubernetes Secret --from-env-file)
Setup
- Generate Variables
Generate
CREDS_KEY,JWT_SECRET,JWT_REFRESH_SECRETandMEILI_MASTER_KEYusingopenssl rand -hex 32andCREDS_IVusing openssl rand -hex 16. place them in a secret like this (If you want to change the secret name, remember to change it in your helm values):
apiVersion: v1
kind: Secret
metadata:
name: librechat-credentials-env
namespace: <librechat-chart-namespace>
type: Opaque
stringData:
CREDS_KEY: <generated value>
JWT_SECRET: <generated value>
JWT_REFRESH_SECRET: <generated value>
MEILI_MASTER_KEY: <generated value>
- Add Credentials to the Secret Dependant of the Model you want to use, create Credentials in your provider and add them to the Secret:
apiVersion: v1
kind: Secret
. . . .
OPENAI_API_KEY: <your secret value>
-
Apply the Secret to the Cluster
-
Fill out values.yaml and apply the Chart to the Cluster
Admin Panel SSO
When deploying the admin panel at a separate URL, set librechat.adminPanelUrl
to the external admin panel base URL. It may include a path, but it should not
end with a trailing / because LibreChat appends /auth/... callback paths.
librechat:
adminPanelUrl: https://admin.example.com/admin
This renders ADMIN_PANEL_URL for LibreChat's admin OAuth flow. For OpenID SSO,
also register this LibreChat callback URL with your identity provider:
https://<librechat-domain>/api/admin/oauth/openid/callback
Langfuse Fanout
The chart can optionally deploy an OpenTelemetry Collector that forwards tenant-scoped Langfuse traces to both a central Langfuse project and the tenant Langfuse project. It is disabled by default.
When enabled, the chart also sets LANGFUSE_FANOUT_ENABLED and
LANGFUSE_FANOUT_COLLECTOR_URL for the LibreChat app unless those values are
already provided in librechat.configEnv.
Set librechat.configEnv.LANGFUSE_FANOUT_TENANT_EXPORT_DISABLED=true to keep
central trace export flowing through the collector while disabling tenant trace
and score export. When omitted, false, or blank, tenant export remains available
if tenant keys and a known destination are configured.
Langfuse tenant base URLs are selected from the startup-configured destination
map rendered into LibreChat and the collector. Tenant API keys can still be added
through tenant app configuration at runtime without restarting either component.
Collector batching can be tuned with langfuseFanout.batchTimeout and
langfuseFanout.batchSendSize; defaults are 1s and 128.
See otel/langfuse-fanout/README.md
for the central Langfuse secret and values example.