121 lines
3.6 KiB
YAML
121 lines
3.6 KiB
YAML
---
|
|
apiVersion: source.toolkit.fluxcd.io/v1
|
|
kind: HelmRepository
|
|
metadata:
|
|
name: dynomite567-charts
|
|
namespace: librechat
|
|
spec:
|
|
interval: 24h
|
|
url: https://dynomite567.github.io/helm-charts/
|
|
---
|
|
apiVersion: helm.toolkit.fluxcd.io/v2
|
|
kind: HelmRelease
|
|
metadata:
|
|
name: librechat
|
|
namespace: librechat
|
|
spec:
|
|
interval: 30m
|
|
chart:
|
|
spec:
|
|
chart: librechat
|
|
version: 1.9.1
|
|
sourceRef:
|
|
kind: HelmRepository
|
|
name: dynomite567-charts
|
|
values:
|
|
global:
|
|
librechat:
|
|
existingSecretName: librechat
|
|
librechat:
|
|
configEnv:
|
|
PLUGIN_MODELS: null
|
|
ALLOW_REGISTRATION: "false"
|
|
TRUST_PROXY: "1"
|
|
DOMAIN_CLIENT: https://librechat.lumpiasty.xyz
|
|
SEARCH: "true"
|
|
existingSecretName: librechat
|
|
configYamlContent: |
|
|
version: 1.0.3
|
|
|
|
endpoints:
|
|
custom:
|
|
- name: "Llama.cpp"
|
|
apiKey: "llama"
|
|
baseURL: "http://llama.llama.svc.cluster.local:11434/v1"
|
|
models:
|
|
default: [
|
|
"DeepSeek-R1-0528-Qwen3-8B-GGUF",
|
|
"Qwen3-8B-GGUF",
|
|
"Qwen3-8B-GGUF-no-thinking",
|
|
"gemma3n-e4b",
|
|
"gemma3-12b",
|
|
"gemma3-12b-q2",
|
|
"gemma3-12b-novision",
|
|
"gemma3-4b",
|
|
"gemma3-4b-novision",
|
|
"Qwen3-4B-Thinking-2507",
|
|
"Qwen3-4B-Thinking-2507-long-ctx",
|
|
"Qwen2.5-VL-7B-Instruct-GGUF",
|
|
"Qwen2.5-VL-32B-Instruct-GGUF-IQ1_S",
|
|
"Qwen2.5-VL-32B-Instruct-GGUF-Q2_K_L",
|
|
"Qwen3-VL-2B-Instruct-GGUF",
|
|
"Qwen3-VL-2B-Instruct-GGUF-unslothish",
|
|
"Qwen3-VL-2B-Thinking-GGUF",
|
|
"Qwen3-VL-4B-Instruct-GGUF",
|
|
"Qwen3-VL-4B-Instruct-GGUF-unslothish",
|
|
"Qwen3-VL-4B-Thinking-GGUF",
|
|
"Qwen3-VL-8B-Instruct-GGUF",
|
|
"Qwen3-VL-8B-Instruct-GGUF-unslothish",
|
|
"Qwen3-VL-8B-Thinking-GGUF",
|
|
"Huihui-Qwen3-VL-8B-Instruct-abliterated-GGUF",
|
|
"Huihui-Qwen3-VL-8B-Thinking-abliterated-GGUF"
|
|
]
|
|
titleConvo: true
|
|
titleModel: "gemma3-4b-novision"
|
|
summarize: false
|
|
summaryModel: "gemma3-4b-novision"
|
|
forcePrompt: false
|
|
modelDisplayLabel: "Llama.cpp"
|
|
|
|
# ✨ IMPORTANT: let llama-swap/llama-server own all these
|
|
dropParams:
|
|
- "temperature"
|
|
- "top_p"
|
|
- "top_k"
|
|
- "presence_penalty"
|
|
- "frequency_penalty"
|
|
- "stop"
|
|
- "max_tokens"
|
|
imageVolume:
|
|
enabled: true
|
|
size: 10G
|
|
accessModes: ReadWriteOnce
|
|
storageClassName: mayastor-single-hdd
|
|
ingress:
|
|
enabled: true
|
|
className: nginx-ingress
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: letsencrypt
|
|
nginx.ingress.kubernetes.io/proxy-body-size: "0"
|
|
nginx.ingress.kubernetes.io/proxy-buffering: "false"
|
|
nginx.ingress.kubernetes.io/proxy-read-timeout: 30m
|
|
hosts:
|
|
- host: librechat.lumpiasty.xyz
|
|
paths:
|
|
- path: /
|
|
pathType: ImplementationSpecific
|
|
tls:
|
|
- hosts:
|
|
- librechat.lumpiasty.xyz
|
|
secretName: librechat-ingress
|
|
|
|
mongodb:
|
|
persistence:
|
|
storageClass: mayastor-single-hdd
|
|
|
|
meilisearch:
|
|
persistence:
|
|
storageClass: mayastor-single-hdd
|
|
auth:
|
|
existingMasterKeySecret: librechat
|