a70ba1f75a
* Partial implementation of phase-0 * Partial implementation of phase-1 * add report * add postgress * Revert "add postgress" This reverts commit 27778dc6bb3906b5220dd386e47fe32ca7415332. * remove junk * Cleaned up annd setup docs * update docs * moved report * Updated load_markdown_files function: Now returns tuples with (content, title, relative_path) instead of just (content, title) * fixes to load docs script and more env variables for llm configuration * update prod values * update docs * apolo docs support with linking * update docs to reflect url conventions and mapping with docs * Adds ingress and forwardAuth configurations Adds ingress configuration to expose the application. Adds forwardAuth configuration to enable user authentication. Includes middleware to strip headers. * Adds ingress and forward authentication middleware support
120 lines
No EOL
2.7 KiB
YAML
120 lines
No EOL
2.7 KiB
YAML
# Production Values
|
|
# Optimized for production with HA, scaling, and monitoring
|
|
|
|
# Environment configuration
|
|
env:
|
|
LLM_MODEL: "gpt-4o"
|
|
WEBUI_TITLE: "Apolo Copilot - LightRAG"
|
|
WEBUI_DESCRIPTION: "Production LightRAG for Apolo Documentation"
|
|
|
|
# OpenAI API Configuration
|
|
LLM_BINDING: "openai"
|
|
LLM_BINDING_HOST: "https://api.openai.com/v1"
|
|
EMBEDDING_BINDING: "openai"
|
|
EMBEDDING_BINDING_HOST: "https://api.openai.com/v1"
|
|
EMBEDDING_MODEL: "text-embedding-ada-002"
|
|
EMBEDDING_DIM: "1536"
|
|
|
|
# Concurrency settings (conservative for API stability)
|
|
MAX_ASYNC: "4"
|
|
MAX_PARALLEL_INSERT: "2"
|
|
|
|
# LLM Configuration
|
|
ENABLE_LLM_CACHE: "true"
|
|
ENABLE_LLM_CACHE_FOR_EXTRACT: "true"
|
|
TIMEOUT: "240"
|
|
TEMPERATURE: "0"
|
|
MAX_TOKENS: "32768"
|
|
|
|
# Production resources
|
|
resources:
|
|
limits:
|
|
cpu: 4000m
|
|
memory: 8Gi
|
|
requests:
|
|
cpu: 1000m
|
|
memory: 2Gi
|
|
|
|
# Production storage with fast storage class
|
|
persistence:
|
|
ragStorage:
|
|
size: 100Gi
|
|
storageClass: "fast-ssd" # Adjust for your cluster
|
|
inputs:
|
|
size: 50Gi
|
|
storageClass: "fast-ssd"
|
|
|
|
# PostgreSQL with production resources
|
|
postgresql:
|
|
# Use pgvector image for vector support
|
|
image:
|
|
registry: docker.io
|
|
repository: pgvector/pgvector
|
|
tag: pg16
|
|
auth:
|
|
password: "secure-production-password" # Use external secret in real production
|
|
primary:
|
|
persistence:
|
|
size: 200Gi
|
|
storageClass: "fast-ssd"
|
|
resources:
|
|
limits:
|
|
cpu: 2000m
|
|
memory: 4Gi
|
|
requests:
|
|
cpu: 500m
|
|
memory: 1Gi
|
|
|
|
# OpenAI API key (use external secret manager in production)
|
|
secrets:
|
|
openaiApiKey: "${OPENAI_API_KEY}"
|
|
|
|
# Enable ingress for production
|
|
ingress:
|
|
enabled: true
|
|
className: "nginx"
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: "letsencrypt-prod"
|
|
nginx.ingress.kubernetes.io/proxy-body-size: "100m"
|
|
nginx.ingress.kubernetes.io/ssl-redirect: "true"
|
|
hosts:
|
|
- host: lightrag.yourdomain.com
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
tls:
|
|
- secretName: lightrag-tls
|
|
hosts:
|
|
- lightrag.yourdomain.com
|
|
|
|
# Enable autoscaling for production
|
|
autoscaling:
|
|
enabled: true
|
|
minReplicas: 2
|
|
maxReplicas: 10
|
|
targetCPUUtilizationPercentage: 70
|
|
targetMemoryUtilizationPercentage: 80
|
|
|
|
# Production security context
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
fsGroup: 1000
|
|
|
|
podSecurityContext:
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
|
|
# Node affinity for production workloads
|
|
affinity:
|
|
podAntiAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- weight: 100
|
|
podAffinityTerm:
|
|
labelSelector:
|
|
matchExpressions:
|
|
- key: app.kubernetes.io/name
|
|
operator: In
|
|
values:
|
|
- lightrag-minimal
|
|
topologyKey: kubernetes.io/hostname |