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
2026-02-07 20:59:03 +03:00
parent 3a769a27cd
commit 8b3f31409e
65 changed files with 16133 additions and 7 deletions
--- a/helm/skill-seekers/Chart.yaml
+++ b/helm/skill-seekers/Chart.yaml
@@ -0,0 +1,32 @@
+apiVersion: v2
+name: skill-seekers
+description: A Helm chart for Skill Seekers - Convert documentation to AI skills
+type: application
+version: 1.0.0
+appVersion: "2.9.0"
+
+keywords:
+  - ai
+  - documentation
+  - skills
+  - mcp
+  - vector-database
+  - claude
+  - gemini
+  - openai
+
+home: https://skillseekersweb.com
+sources:
+  - https://github.com/your-org/skill-seekers
+
+maintainers:
+  - name: Skill Seekers Team
+    email: noreply@skillseekers.dev
+
+icon: https://skillseekersweb.com/icon.png
+
+dependencies: []
+
+annotations:
+  category: AI/ML
+  licenses: MIT
--- a/helm/skill-seekers/templates/NOTES.txt
+++ b/helm/skill-seekers/templates/NOTES.txt
@@ -0,0 +1,144 @@
+🎉 Skill Seekers {{ .Chart.AppVersion }} has been installed!
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+📦 DEPLOYMENT SUMMARY
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Release Name:      {{ .Release.Name }}
+Namespace:         {{ .Release.Namespace }}
+Chart Version:     {{ .Chart.Version }}
+App Version:       {{ .Chart.AppVersion }}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+🚀 SERVICES DEPLOYED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+{{- if .Values.mcpServer.enabled }}
+✅ MCP Server ({{ .Values.mcpServer.replicaCount }} replicas)
+   - Port: {{ .Values.mcpServer.service.port }}
+   {{- if .Values.mcpServer.autoscaling.enabled }}
+   - Autoscaling: {{ .Values.mcpServer.autoscaling.minReplicas }}-{{ .Values.mcpServer.autoscaling.maxReplicas }} replicas
+   {{- end }}
+{{- end }}
+
+{{- if .Values.vectorDatabases.weaviate.enabled }}
+✅ Weaviate Vector Database
+   - Port: {{ .Values.vectorDatabases.weaviate.service.port }}
+   {{- if .Values.vectorDatabases.weaviate.persistence.enabled }}
+   - Storage: {{ .Values.vectorDatabases.weaviate.persistence.size }}
+   {{- end }}
+{{- end }}
+
+{{- if .Values.vectorDatabases.qdrant.enabled }}
+✅ Qdrant Vector Database
+   - HTTP Port: {{ .Values.vectorDatabases.qdrant.service.httpPort }}
+   - gRPC Port: {{ .Values.vectorDatabases.qdrant.service.grpcPort }}
+   {{- if .Values.vectorDatabases.qdrant.persistence.enabled }}
+   - Storage: {{ .Values.vectorDatabases.qdrant.persistence.size }}
+   {{- end }}
+{{- end }}
+
+{{- if .Values.vectorDatabases.chroma.enabled }}
+✅ Chroma Vector Database
+   - Port: {{ .Values.vectorDatabases.chroma.service.port }}
+   {{- if .Values.vectorDatabases.chroma.persistence.enabled }}
+   - Storage: {{ .Values.vectorDatabases.chroma.persistence.size }}
+   {{- end }}
+{{- end }}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+🔗 ACCESSING YOUR SERVICES
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+{{- if .Values.mcpServer.enabled }}
+MCP Server:
+  {{- if eq .Values.mcpServer.service.type "ClusterIP" }}
+  # Port-forward to access locally
+  kubectl port-forward -n {{ .Release.Namespace }} svc/{{ include "skill-seekers.fullname" . }}-mcp {{ .Values.mcpServer.service.port }}:{{ .Values.mcpServer.service.port }}
+
+  # Then connect to: http://localhost:{{ .Values.mcpServer.service.port }}
+  {{- else if eq .Values.mcpServer.service.type "LoadBalancer" }}
+  # Get external IP
+  kubectl get svc -n {{ .Release.Namespace }} {{ include "skill-seekers.fullname" . }}-mcp
+  {{- else if eq .Values.mcpServer.service.type "NodePort" }}
+  # Get node port
+  kubectl get svc -n {{ .Release.Namespace }} {{ include "skill-seekers.fullname" . }}-mcp
+  {{- end }}
+{{- end }}
+
+{{- if .Values.ingress.enabled }}
+Ingress:
+  {{- range .Values.ingress.hosts }}
+  - https://{{ .host }}
+  {{- end }}
+{{- end }}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+📊 MONITORING
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+# View pod status
+kubectl get pods -n {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }}
+
+# View logs
+kubectl logs -n {{ .Release.Namespace }} -l app.kubernetes.io/component=mcp-server --tail=100 -f
+
+# View events
+kubectl get events -n {{ .Release.Namespace }} --sort-by='.lastTimestamp'
+
+{{- if .Values.mcpServer.autoscaling.enabled }}
+# View autoscaler status
+kubectl get hpa -n {{ .Release.Namespace }} {{ include "skill-seekers.fullname" . }}-mcp
+{{- end }}
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+🔧 CONFIGURATION
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+{{- if not .Values.secrets.anthropicApiKey }}
+⚠️  WARNING: ANTHROPIC_API_KEY not set
+   Set it with:
+   helm upgrade {{ .Release.Name }} skill-seekers/skill-seekers \
+     --set secrets.anthropicApiKey="sk-ant-..." \
+     --reuse-values
+{{- end }}
+
+View current configuration:
+  helm get values {{ .Release.Name }} -n {{ .Release.Namespace }}
+
+Update configuration:
+  helm upgrade {{ .Release.Name }} skill-seekers/skill-seekers \
+    --set key=value \
+    --reuse-values
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+📚 NEXT STEPS
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+1. Configure API Keys (if not already set):
+   kubectl create secret generic {{ include "skill-seekers.fullname" . }} \
+     --from-literal=ANTHROPIC_API_KEY="sk-ant-..." \
+     -n {{ .Release.Namespace }}
+
+2. Test MCP Server Connection:
+   curl http://localhost:{{ .Values.mcpServer.service.port }}/health
+
+3. Use Skill Seekers CLI:
+   kubectl exec -it -n {{ .Release.Namespace }} \
+     deployment/{{ include "skill-seekers.fullname" . }}-mcp -- \
+     skill-seekers --help
+
+4. Export to Vector Databases:
+   kubectl exec -it -n {{ .Release.Namespace }} \
+     deployment/{{ include "skill-seekers.fullname" . }}-mcp -- \
+     skill-seekers package /data/myskill --target weaviate
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+📖 DOCUMENTATION
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+- Project: https://github.com/yourusername/skill-seekers
+- Docs:    https://skillseekersweb.com
+- Issues:  https://github.com/yourusername/skill-seekers/issues
+
+Happy skill seeking! 🚀
--- a/helm/skill-seekers/templates/_helpers.tpl
+++ b/helm/skill-seekers/templates/_helpers.tpl
@@ -0,0 +1,60 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "skill-seekers.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+*/}}
+{{- define "skill-seekers.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "skill-seekers.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "skill-seekers.labels" -}}
+helm.sh/chart: {{ include "skill-seekers.chart" . }}
+{{ include "skill-seekers.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "skill-seekers.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "skill-seekers.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "skill-seekers.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "skill-seekers.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/chroma-deployment.yaml
+++ b/helm/skill-seekers/templates/chroma-deployment.yaml
@@ -0,0 +1,49 @@
+{{- if .Values.vectorDatabases.chroma.enabled -}}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-chroma
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: chroma
+spec:
+  replicas: {{ .Values.vectorDatabases.chroma.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "skill-seekers.selectorLabels" . | nindent 6 }}
+      app.kubernetes.io/component: chroma
+  template:
+    metadata:
+      labels:
+        {{- include "skill-seekers.selectorLabels" . | nindent 8 }}
+        app.kubernetes.io/component: chroma
+    spec:
+      containers:
+      - name: chroma
+        image: "{{ .Values.vectorDatabases.chroma.image.repository }}:{{ .Values.vectorDatabases.chroma.image.tag }}"
+        imagePullPolicy: {{ .Values.vectorDatabases.chroma.image.pullPolicy }}
+        ports:
+        - name: http
+          containerPort: 8000
+          protocol: TCP
+        env:
+        - name: IS_PERSISTENT
+          value: "TRUE"
+        - name: PERSIST_DIRECTORY
+          value: "/chroma/chroma"
+        - name: ANONYMIZED_TELEMETRY
+          value: "FALSE"
+        resources:
+          {{- toYaml .Values.vectorDatabases.chroma.resources | nindent 12 }}
+        volumeMounts:
+        - name: data
+          mountPath: /chroma/chroma
+      volumes:
+      - name: data
+        {{- if .Values.vectorDatabases.chroma.persistence.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ include "skill-seekers.fullname" . }}-chroma-data
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/configmap.yaml
+++ b/helm/skill-seekers/templates/configmap.yaml
@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+data:
+  {{- range $key, $value := .Values.env }}
+  {{ $key }}: {{ $value | quote }}
+  {{- end }}
+  SKILL_SEEKERS_HOME: "/data"
+  SKILL_SEEKERS_OUTPUT: "/output"
--- a/helm/skill-seekers/templates/hpa.yaml
+++ b/helm/skill-seekers/templates/hpa.yaml
@@ -0,0 +1,33 @@
+{{- if .Values.mcpServer.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-mcp
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: mcp-server
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "skill-seekers.fullname" . }}-mcp
+  minReplicas: {{ .Values.mcpServer.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.mcpServer.autoscaling.maxReplicas }}
+  metrics:
+  {{- if .Values.mcpServer.autoscaling.targetCPUUtilizationPercentage }}
+  - type: Resource
+    resource:
+      name: cpu
+      target:
+        type: Utilization
+        averageUtilization: {{ .Values.mcpServer.autoscaling.targetCPUUtilizationPercentage }}
+  {{- end }}
+  {{- if .Values.mcpServer.autoscaling.targetMemoryUtilizationPercentage }}
+  - type: Resource
+    resource:
+      name: memory
+      target:
+        type: Utilization
+        averageUtilization: {{ .Values.mcpServer.autoscaling.targetMemoryUtilizationPercentage }}
+  {{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/ingress.yaml
+++ b/helm/skill-seekers/templates/ingress.yaml
@@ -0,0 +1,41 @@
+{{- if .Values.ingress.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if .Values.ingress.className }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            pathType: {{ .pathType }}
+            backend:
+              service:
+                name: {{ include "skill-seekers.fullname" $ }}-{{ .backend.service.name }}
+                port:
+                  number: {{ .backend.service.port }}
+          {{- end }}
+    {{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/mcp-deployment.yaml
+++ b/helm/skill-seekers/templates/mcp-deployment.yaml
@@ -0,0 +1,99 @@
+{{- if .Values.mcpServer.enabled -}}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-mcp
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: mcp-server
+spec:
+  {{- if not .Values.mcpServer.autoscaling.enabled }}
+  replicas: {{ .Values.mcpServer.replicaCount }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "skill-seekers.selectorLabels" . | nindent 6 }}
+      app.kubernetes.io/component: mcp-server
+  template:
+    metadata:
+      annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+        checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }}
+        {{- with .Values.mcpServer.podAnnotations }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+      labels:
+        {{- include "skill-seekers.selectorLabels" . | nindent 8 }}
+        app.kubernetes.io/component: mcp-server
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "skill-seekers.serviceAccountName" . }}
+      securityContext:
+        {{- toYaml .Values.mcpServer.podSecurityContext | nindent 8 }}
+      containers:
+      - name: mcp-server
+        securityContext:
+          {{- toYaml .Values.mcpServer.securityContext | nindent 12 }}
+        image: "{{ .Values.mcpServer.image.repository }}:{{ .Values.mcpServer.image.tag | default .Chart.AppVersion }}"
+        imagePullPolicy: {{ .Values.mcpServer.image.pullPolicy }}
+        ports:
+        - name: http
+          containerPort: {{ .Values.mcpServer.service.targetPort }}
+          protocol: TCP
+        envFrom:
+        - configMapRef:
+            name: {{ include "skill-seekers.fullname" . }}
+        - secretRef:
+            name: {{ include "skill-seekers.fullname" . }}
+        livenessProbe:
+          {{- toYaml .Values.mcpServer.livenessProbe | nindent 12 }}
+        readinessProbe:
+          {{- toYaml .Values.mcpServer.readinessProbe | nindent 12 }}
+        resources:
+          {{- toYaml .Values.mcpServer.resources | nindent 12 }}
+        volumeMounts:
+        - name: data
+          mountPath: /data
+        - name: output
+          mountPath: /output
+        - name: configs
+          mountPath: /configs
+          readOnly: true
+      volumes:
+      - name: data
+        {{- if .Values.persistence.data.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ .Values.persistence.data.existingClaim | default (printf "%s-data" (include "skill-seekers.fullname" .)) }}
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+      - name: output
+        {{- if .Values.persistence.output.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ .Values.persistence.output.existingClaim | default (printf "%s-output" (include "skill-seekers.fullname" .)) }}
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+      - name: configs
+        {{- if .Values.persistence.configs.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ .Values.persistence.configs.existingClaim | default (printf "%s-configs" (include "skill-seekers.fullname" .)) }}
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+      {{- with .Values.mcpServer.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.mcpServer.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.mcpServer.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/pvc.yaml
+++ b/helm/skill-seekers/templates/pvc.yaml
@@ -0,0 +1,110 @@
+{{- if .Values.persistence.data.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-data
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+spec:
+  accessModes:
+    - {{ .Values.persistence.data.accessMode }}
+  {{- if .Values.persistence.data.storageClass }}
+  storageClassName: {{ .Values.persistence.data.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.persistence.data.size }}
+{{- end }}
+---
+{{- if .Values.persistence.output.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-output
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+spec:
+  accessModes:
+    - {{ .Values.persistence.output.accessMode }}
+  {{- if .Values.persistence.output.storageClass }}
+  storageClassName: {{ .Values.persistence.output.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.persistence.output.size }}
+{{- end }}
+---
+{{- if .Values.persistence.configs.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-configs
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+spec:
+  accessModes:
+    - {{ .Values.persistence.configs.accessMode }}
+  {{- if .Values.persistence.configs.storageClass }}
+  storageClassName: {{ .Values.persistence.configs.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.persistence.configs.size }}
+{{- end }}
+---
+{{- if and .Values.vectorDatabases.weaviate.enabled .Values.vectorDatabases.weaviate.persistence.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-weaviate-data
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: weaviate
+spec:
+  accessModes:
+    - ReadWriteOnce
+  {{- if .Values.vectorDatabases.weaviate.persistence.storageClass }}
+  storageClassName: {{ .Values.vectorDatabases.weaviate.persistence.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.vectorDatabases.weaviate.persistence.size }}
+{{- end }}
+---
+{{- if and .Values.vectorDatabases.qdrant.enabled .Values.vectorDatabases.qdrant.persistence.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-qdrant-data
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: qdrant
+spec:
+  accessModes:
+    - ReadWriteOnce
+  {{- if .Values.vectorDatabases.qdrant.persistence.storageClass }}
+  storageClassName: {{ .Values.vectorDatabases.qdrant.persistence.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.vectorDatabases.qdrant.persistence.size }}
+{{- end }}
+---
+{{- if and .Values.vectorDatabases.chroma.enabled .Values.vectorDatabases.chroma.persistence.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-chroma-data
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: chroma
+spec:
+  accessModes:
+    - ReadWriteOnce
+  {{- if .Values.vectorDatabases.chroma.persistence.storageClass }}
+  storageClassName: {{ .Values.vectorDatabases.chroma.persistence.storageClass | quote }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.vectorDatabases.chroma.persistence.size }}
+{{- end }}
--- a/helm/skill-seekers/templates/qdrant-deployment.yaml
+++ b/helm/skill-seekers/templates/qdrant-deployment.yaml
@@ -0,0 +1,50 @@
+{{- if .Values.vectorDatabases.qdrant.enabled -}}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-qdrant
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: qdrant
+spec:
+  replicas: {{ .Values.vectorDatabases.qdrant.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "skill-seekers.selectorLabels" . | nindent 6 }}
+      app.kubernetes.io/component: qdrant
+  template:
+    metadata:
+      labels:
+        {{- include "skill-seekers.selectorLabels" . | nindent 8 }}
+        app.kubernetes.io/component: qdrant
+    spec:
+      containers:
+      - name: qdrant
+        image: "{{ .Values.vectorDatabases.qdrant.image.repository }}:{{ .Values.vectorDatabases.qdrant.image.tag }}"
+        imagePullPolicy: {{ .Values.vectorDatabases.qdrant.image.pullPolicy }}
+        ports:
+        - name: http
+          containerPort: 6333
+          protocol: TCP
+        - name: grpc
+          containerPort: 6334
+          protocol: TCP
+        env:
+        - name: QDRANT__SERVICE__HTTP_PORT
+          value: "6333"
+        - name: QDRANT__SERVICE__GRPC_PORT
+          value: "6334"
+        resources:
+          {{- toYaml .Values.vectorDatabases.qdrant.resources | nindent 12 }}
+        volumeMounts:
+        - name: data
+          mountPath: /qdrant/storage
+      volumes:
+      - name: data
+        {{- if .Values.vectorDatabases.qdrant.persistence.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ include "skill-seekers.fullname" . }}-qdrant-data
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/secret.yaml
+++ b/helm/skill-seekers/templates/secret.yaml
@@ -0,0 +1,20 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+type: Opaque
+data:
+  {{- if .Values.secrets.anthropicApiKey }}
+  ANTHROPIC_API_KEY: {{ .Values.secrets.anthropicApiKey | b64enc | quote }}
+  {{- end }}
+  {{- if .Values.secrets.googleApiKey }}
+  GOOGLE_API_KEY: {{ .Values.secrets.googleApiKey | b64enc | quote }}
+  {{- end }}
+  {{- if .Values.secrets.openaiApiKey }}
+  OPENAI_API_KEY: {{ .Values.secrets.openaiApiKey | b64enc | quote }}
+  {{- end }}
+  {{- if .Values.secrets.githubToken }}
+  GITHUB_TOKEN: {{ .Values.secrets.githubToken | b64enc | quote }}
+  {{- end }}
--- a/helm/skill-seekers/templates/service.yaml
+++ b/helm/skill-seekers/templates/service.yaml
@@ -0,0 +1,83 @@
+{{- if .Values.mcpServer.enabled -}}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-mcp
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: mcp-server
+spec:
+  type: {{ .Values.mcpServer.service.type }}
+  ports:
+  - port: {{ .Values.mcpServer.service.port }}
+    targetPort: {{ .Values.mcpServer.service.targetPort }}
+    protocol: {{ .Values.mcpServer.service.protocol }}
+    name: http
+  selector:
+    {{- include "skill-seekers.selectorLabels" . | nindent 4 }}
+    app.kubernetes.io/component: mcp-server
+{{- end }}
+---
+{{- if .Values.vectorDatabases.weaviate.enabled -}}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-weaviate
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: weaviate
+spec:
+  type: {{ .Values.vectorDatabases.weaviate.service.type }}
+  ports:
+  - port: {{ .Values.vectorDatabases.weaviate.service.port }}
+    targetPort: 8080
+    protocol: TCP
+    name: http
+  selector:
+    {{- include "skill-seekers.selectorLabels" . | nindent 4 }}
+    app.kubernetes.io/component: weaviate
+{{- end }}
+---
+{{- if .Values.vectorDatabases.qdrant.enabled -}}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-qdrant
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: qdrant
+spec:
+  type: {{ .Values.vectorDatabases.qdrant.service.type }}
+  ports:
+  - port: {{ .Values.vectorDatabases.qdrant.service.httpPort }}
+    targetPort: 6333
+    protocol: TCP
+    name: http
+  - port: {{ .Values.vectorDatabases.qdrant.service.grpcPort }}
+    targetPort: 6334
+    protocol: TCP
+    name: grpc
+  selector:
+    {{- include "skill-seekers.selectorLabels" . | nindent 4 }}
+    app.kubernetes.io/component: qdrant
+{{- end }}
+---
+{{- if .Values.vectorDatabases.chroma.enabled -}}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-chroma
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: chroma
+spec:
+  type: {{ .Values.vectorDatabases.chroma.service.type }}
+  ports:
+  - port: {{ .Values.vectorDatabases.chroma.service.port }}
+    targetPort: 8000
+    protocol: TCP
+    name: http
+  selector:
+    {{- include "skill-seekers.selectorLabels" . | nindent 4 }}
+    app.kubernetes.io/component: chroma
+{{- end }}
--- a/helm/skill-seekers/templates/serviceaccount.yaml
+++ b/helm/skill-seekers/templates/serviceaccount.yaml
@@ -0,0 +1,12 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "skill-seekers.serviceAccountName" . }}
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+{{- end }}
--- a/helm/skill-seekers/templates/weaviate-deployment.yaml
+++ b/helm/skill-seekers/templates/weaviate-deployment.yaml
@@ -0,0 +1,55 @@
+{{- if .Values.vectorDatabases.weaviate.enabled -}}
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "skill-seekers.fullname" . }}-weaviate
+  labels:
+    {{- include "skill-seekers.labels" . | nindent 4 }}
+    app.kubernetes.io/component: weaviate
+spec:
+  replicas: {{ .Values.vectorDatabases.weaviate.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "skill-seekers.selectorLabels" . | nindent 6 }}
+      app.kubernetes.io/component: weaviate
+  template:
+    metadata:
+      labels:
+        {{- include "skill-seekers.selectorLabels" . | nindent 8 }}
+        app.kubernetes.io/component: weaviate
+    spec:
+      containers:
+      - name: weaviate
+        image: "{{ .Values.vectorDatabases.weaviate.image.repository }}:{{ .Values.vectorDatabases.weaviate.image.tag }}"
+        imagePullPolicy: {{ .Values.vectorDatabases.weaviate.image.pullPolicy }}
+        ports:
+        - name: http
+          containerPort: 8080
+          protocol: TCP
+        env:
+        - name: QUERY_DEFAULTS_LIMIT
+          value: "25"
+        - name: AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED
+          value: "true"
+        - name: PERSISTENCE_DATA_PATH
+          value: "/var/lib/weaviate"
+        - name: DEFAULT_VECTORIZER_MODULE
+          value: "none"
+        - name: ENABLE_MODULES
+          value: ""
+        - name: CLUSTER_HOSTNAME
+          value: "node1"
+        resources:
+          {{- toYaml .Values.vectorDatabases.weaviate.resources | nindent 12 }}
+        volumeMounts:
+        - name: data
+          mountPath: /var/lib/weaviate
+      volumes:
+      - name: data
+        {{- if .Values.vectorDatabases.weaviate.persistence.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ include "skill-seekers.fullname" . }}-weaviate-data
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+{{- end }}
--- a/helm/skill-seekers/values.yaml
+++ b/helm/skill-seekers/values.yaml
@@ -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"