fix: Enforce min_chunk_size in RAG chunker
- Filter out chunks smaller than min_chunk_size (default 100 tokens) - Exception: Keep all chunks if entire document is smaller than target size - All 15 tests passing (100% pass rate) Fixes edge case where very small chunks (e.g., 'Short.' = 6 chars) were being created despite min_chunk_size=100 setting. Test: pytest tests/test_rag_chunker.py -v
This commit is contained in:
yusyus
313
helm/skill-seekers/values.yaml
Normal file
313
helm/skill-seekers/values.yaml
Normal file
@@ -0,0 +1,313 @@
|
||||
# Default values for skill-seekers Helm chart
|
||||
# This is a YAML-formatted file.
|
||||
# Declare variables to be passed into your templates.
|
||||
|
||||
# Global configuration
|
||||
global:
|
||||
# Environment: development, staging, production
|
||||
environment: production
|
||||
|
||||
# Main application (CLI)
|
||||
app:
|
||||
enabled: true
|
||||
name: skill-seekers
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: skill-seekers
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "latest"
|
||||
|
||||
imagePullSecrets: []
|
||||
nameOverride: ""
|
||||
fullnameOverride: ""
|
||||
|
||||
serviceAccount:
|
||||
create: true
|
||||
annotations: {}
|
||||
name: ""
|
||||
|
||||
podAnnotations: {}
|
||||
podSecurityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
fsGroup: 1000
|
||||
|
||||
securityContext:
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: false
|
||||
allowPrivilegeEscalation: false
|
||||
|
||||
resources:
|
||||
limits:
|
||||
cpu: 2000m
|
||||
memory: 4Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
|
||||
nodeSelector: {}
|
||||
tolerations: []
|
||||
affinity: {}
|
||||
|
||||
# MCP Server
|
||||
mcpServer:
|
||||
enabled: true
|
||||
name: mcp-server
|
||||
replicaCount: 2
|
||||
|
||||
image:
|
||||
repository: skill-seekers-mcp
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "latest"
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 8765
|
||||
targetPort: 8765
|
||||
protocol: TCP
|
||||
|
||||
podAnnotations: {}
|
||||
podSecurityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
fsGroup: 1000
|
||||
|
||||
securityContext:
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: false
|
||||
allowPrivilegeEscalation: false
|
||||
|
||||
resources:
|
||||
limits:
|
||||
cpu: 1000m
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 250m
|
||||
memory: 512Mi
|
||||
|
||||
# Horizontal Pod Autoscaler
|
||||
autoscaling:
|
||||
enabled: true
|
||||
minReplicas: 2
|
||||
maxReplicas: 10
|
||||
targetCPUUtilizationPercentage: 70
|
||||
targetMemoryUtilizationPercentage: 80
|
||||
|
||||
# Health checks
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: 8765
|
||||
initialDelaySeconds: 30
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 5
|
||||
successThreshold: 1
|
||||
failureThreshold: 3
|
||||
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: 8765
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 5
|
||||
timeoutSeconds: 3
|
||||
successThreshold: 1
|
||||
failureThreshold: 3
|
||||
|
||||
nodeSelector: {}
|
||||
tolerations: []
|
||||
affinity: {}
|
||||
|
||||
# Environment variables (non-sensitive)
|
||||
env:
|
||||
MCP_TRANSPORT: "http"
|
||||
MCP_PORT: "8765"
|
||||
PYTHONUNBUFFERED: "1"
|
||||
PYTHONDONTWRITEBYTECODE: "1"
|
||||
|
||||
# Secrets (sensitive values)
|
||||
# Set these via --set or external secret management
|
||||
secrets:
|
||||
# Claude AI / Anthropic API
|
||||
anthropicApiKey: ""
|
||||
# Google Gemini API (optional)
|
||||
googleApiKey: ""
|
||||
# OpenAI API (optional)
|
||||
openaiApiKey: ""
|
||||
# GitHub Token (optional)
|
||||
githubToken: ""
|
||||
|
||||
# Persistent storage
|
||||
persistence:
|
||||
enabled: true
|
||||
|
||||
data:
|
||||
enabled: true
|
||||
storageClass: ""
|
||||
accessMode: ReadWriteOnce
|
||||
size: 10Gi
|
||||
existingClaim: ""
|
||||
|
||||
output:
|
||||
enabled: true
|
||||
storageClass: ""
|
||||
accessMode: ReadWriteOnce
|
||||
size: 20Gi
|
||||
existingClaim: ""
|
||||
|
||||
configs:
|
||||
enabled: true
|
||||
storageClass: ""
|
||||
accessMode: ReadOnlyMany
|
||||
size: 1Gi
|
||||
existingClaim: ""
|
||||
|
||||
# Vector Databases
|
||||
vectorDatabases:
|
||||
# Weaviate
|
||||
weaviate:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: semitechnologies/weaviate
|
||||
tag: latest
|
||||
pullPolicy: IfNotPresent
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 8080
|
||||
|
||||
resources:
|
||||
limits:
|
||||
cpu: 2000m
|
||||
memory: 4Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: ""
|
||||
size: 50Gi
|
||||
|
||||
# Qdrant
|
||||
qdrant:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: qdrant/qdrant
|
||||
tag: latest
|
||||
pullPolicy: IfNotPresent
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
httpPort: 6333
|
||||
grpcPort: 6334
|
||||
|
||||
resources:
|
||||
limits:
|
||||
cpu: 2000m
|
||||
memory: 4Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: ""
|
||||
size: 50Gi
|
||||
|
||||
# Chroma
|
||||
chroma:
|
||||
enabled: true
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
repository: ghcr.io/chroma-core/chroma
|
||||
tag: latest
|
||||
pullPolicy: IfNotPresent
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 8000
|
||||
|
||||
resources:
|
||||
limits:
|
||||
cpu: 1000m
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 250m
|
||||
memory: 512Mi
|
||||
|
||||
persistence:
|
||||
enabled: true
|
||||
storageClass: ""
|
||||
size: 30Gi
|
||||
|
||||
# Ingress configuration
|
||||
ingress:
|
||||
enabled: false
|
||||
className: "nginx"
|
||||
annotations:
|
||||
cert-manager.io/cluster-issuer: "letsencrypt-prod"
|
||||
nginx.ingress.kubernetes.io/ssl-redirect: "true"
|
||||
hosts:
|
||||
- host: skill-seekers.example.com
|
||||
paths:
|
||||
- path: /mcp
|
||||
pathType: Prefix
|
||||
backend:
|
||||
service:
|
||||
name: mcp-server
|
||||
port: 8765
|
||||
tls:
|
||||
- secretName: skill-seekers-tls
|
||||
hosts:
|
||||
- skill-seekers.example.com
|
||||
|
||||
# Service Monitor (Prometheus)
|
||||
serviceMonitor:
|
||||
enabled: false
|
||||
interval: 30s
|
||||
scrapeTimeout: 10s
|
||||
labels: {}
|
||||
|
||||
# Network Policies
|
||||
networkPolicy:
|
||||
enabled: false
|
||||
policyTypes:
|
||||
- Ingress
|
||||
- Egress
|
||||
ingress:
|
||||
- from:
|
||||
- namespaceSelector:
|
||||
matchLabels:
|
||||
name: monitoring
|
||||
egress:
|
||||
- to:
|
||||
- namespaceSelector: {}
|
||||
|
||||
# RBAC
|
||||
rbac:
|
||||
create: true
|
||||
rules: []
|
||||
|
||||
# Pod Disruption Budget
|
||||
podDisruptionBudget:
|
||||
enabled: true
|
||||
minAvailable: 1
|
||||
|
||||
# Resource Quotas
|
||||
resourceQuota:
|
||||
enabled: false
|
||||
hard:
|
||||
requests.cpu: "10"
|
||||
requests.memory: "20Gi"
|
||||
persistentvolumeclaims: "10"
|
||||
Reference in New Issue
Block a user