mirror of
https://github.com/nold360/hive-apps
synced 2024-07-09 18:03:30 +00:00
69 lines
1.7 KiB
YAML
69 lines
1.7 KiB
YAML
replicaCount: 1
|
|
|
|
deployment:
|
|
image: quay.io/go-skynet/local-ai:master
|
|
env:
|
|
THREADS: 16
|
|
CONTEXT_SIZE: 512
|
|
DEBUG: "true"
|
|
modelsPath: "/models"
|
|
download_model:
|
|
# To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox
|
|
image: busybox
|
|
prompt_templates:
|
|
# To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox
|
|
image: busybox
|
|
pullPolicy: Always
|
|
imagePullSecrets: []
|
|
# - name: secret-names
|
|
|
|
# Prompt templates to include
|
|
# Note: the keys of this map will be the names of the prompt template files
|
|
promptTemplates:
|
|
{}
|
|
# ggml-gpt4all-j.tmpl: |
|
|
# The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
|
|
# ### Prompt:
|
|
# {{.Input}}
|
|
# ### Response:
|
|
|
|
# Models to download at runtime
|
|
models:
|
|
# Whether to force download models even if they already exist
|
|
forceDownload: false
|
|
|
|
# The list of URLs to download models from
|
|
# Note: the name of the file will be the name of the loaded model
|
|
list:
|
|
- url: "https://gpt4all.io/models/ggml-gpt4all-j.bin"
|
|
# basicAuth: base64EncodedCredentials
|
|
|
|
persistence:
|
|
pvc:
|
|
enabled: true
|
|
size: 6Gi
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
|
|
service:
|
|
type: ClusterIP
|
|
port: 80
|
|
|
|
ingress:
|
|
enabled: true
|
|
className: "ingress-internal"
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: vault-issuer
|
|
hosts:
|
|
- host: ai.dc
|
|
paths:
|
|
- path: /
|
|
pathType: ImplementationSpecific
|
|
tls:
|
|
- secretName: localai-tls
|
|
hosts:
|
|
- ai.dc
|
|
|
|
image:
|
|
pullPolicy: IfNotPresent
|