Feat helm

.github/workflows/helm.yaml

@@ -0,0 +1,54 @@
+name: Publish Helm Chart
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+    paths:
+      - "charts/**"
+env:
+  HELM_REGISTRY: ghcr.io
+  HELM_ORG: linagora
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Helm
+        uses: azure/setup-helm@v4
+        with:
+          version: v3.14.4
+
+      - name: Set chart version
+        run: |
+          BASE_VERSION=$(yq '.version' charts/openrag-stack/Chart.yaml)
+
+          if [[ "${GITHUB_REF_NAME}" == "main" ]]; then
+            # Keep version as-is for stable
+            CHART_VERSION="$BASE_VERSION"
+          else
+            # Append branch for dev builds
+            CHART_VERSION="${BASE_VERSION}-dev"
+            yq -i ".version = \"${CHART_VERSION}\"" charts/openrag-stack/Chart.yaml
+          fi
+
+          echo "CHART_VERSION=$CHART_VERSION" >> $GITHUB_ENV
+          echo "Using chart version: $CHART_VERSION"
+
+      - name: Helm dependency update
+        run: helm dependency update charts/openrag-stack
+
+      - name: Package chart
+        run: helm package charts/openrag-stack --destination .
+
+      - name: Login to GHCR
+        run: |
+          echo "${{ secrets.GITHUB_TOKEN }}" | helm registry login $HELM_REGISTRY -u ${{ github.actor }} --password-stdin
+
+      - name: Push chart
+        run: |
+          helm push openrag-stack-${CHART_VERSION}.tgz oci://$HELM_REGISTRY/$HELM_ORG

.gitignore

@@ -67,3 +67,6 @@ services/*
 *.json
 *.csv
 *.pkl
+
+#helm
+charts/openrag-stack/charts/*.tgz

Dockerfile.ray

@@ -12,6 +12,7 @@ RUN apt-get update && apt-get install -y \
     make \
     ssh \ 
     rsync \
+    wget \
     libpq-dev python3-dev \
     && rm -rf /var/lib/apt/lists/*
 
@@ -35,7 +36,7 @@ COPY pyproject.toml uv.lock ./
 RUN pip3 install uv && \
     uv python install 3.12.7 && \
     uv python pin 3.12.7 
-    # && \uv sync --no-dev
+# && \uv sync --no-dev
 COPY entrypoint.sh /app/entrypoint.sh
 RUN chmod +x /app/entrypoint.sh
 
@@ -46,10 +47,10 @@ WORKDIR /app/openrag
 COPY openrag/ .
 
 # Copy assests & config
-COPY public/ /app/public/
 COPY prompts/ /app/prompts/
 COPY .hydra_config/ /app/.hydra_config/
 
 RUN apt install -y 
+RUN ln -s /app/.venv/bin/ray /usr/local/bin/ray
 
 ENV PYTHONPATH=/app/openrag/

charts/openrag-stack/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

charts/openrag-stack/Chart.lock

@@ -0,0 +1,15 @@
+dependencies:
+- name: kuberay-operator
+  repository: https://ray-project.github.io/kuberay-helm/
+  version: 1.4.0
+- name: postgresql
+  repository: https://charts.bitnami.com/bitnami
+  version: 15.5.23
+- name: milvus
+  repository: https://zilliztech.github.io/milvus-helm/
+  version: 5.0.0
+- name: vllm-stack
+  repository: https://vllm-project.github.io/production-stack
+  version: 0.1.7
+digest: sha256:eb9f465f19be0d6d6c563c4eda6dc0f7b8e9331209420f14f01587f2ca29f965
+generated: "2025-09-04T13:28:20.5556128Z"

charts/openrag-stack/Chart.yaml

@@ -0,0 +1,39 @@
+apiVersion: v2
+name: openrag-stack
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.2.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.2.0"
+
+dependencies:
+  - name: kuberay-operator
+    version: "1.4.0"
+    repository: "https://ray-project.github.io/kuberay-helm/"
+  - name: postgresql
+    version: "15.5.23"
+    repository: "https://charts.bitnami.com/bitnami"
+  - name: milvus
+    version: "5.0.0"
+    repository: "https://zilliztech.github.io/milvus-helm/"
+  - name: vllm-stack
+    alias: vllm
+    version: ">=0.1.7"
+    repository: "https://vllm-project.github.io/production-stack"

charts/openrag-stack/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "openrag-stack.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "openrag-stack.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 "openrag-stack.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "openrag-stack.labels" -}}
+helm.sh/chart: {{ include "openrag-stack.chart" . }}
+{{ include "openrag-stack.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "openrag-stack.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "openrag-stack.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "openrag-stack.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "openrag-stack.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

charts/openrag-stack/templates/configmap-env.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: rag-env
+data:
+{{- range $key, $value := .Values.env.config }}
+  {{ $key }}: "{{ tpl (printf "%v" $value) $ }}"
+{{- end }}

charts/openrag-stack/templates/infinity.yaml

@@ -0,0 +1,60 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ .Release.Name }}-reranker
+  labels:
+    app.kubernetes.io/name: reranker
+    app.kubernetes.io/instance: {{ .Release.Name }}
+spec:
+  replicas: {{ .Values.reranker.replicas }}
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: reranker
+      app.kubernetes.io/instance: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: reranker
+        app.kubernetes.io/instance: {{ .Release.Name }}
+    spec:
+      runtimeClassName: {{ .Values.reranker.runtimeClassName }}
+      containers:
+        - name: reranker
+          image: "{{ .Values.reranker.image.repository }}:{{ .Values.reranker.image.tag }}"
+          args:
+            - "v2"
+            - "--model-id"
+            - "{{ .Values.reranker.model.id }}"
+            - "--port"
+            - "{{ .Values.reranker.service.port }}"
+          ports:
+            - containerPort: {{ .Values.reranker.service.port }}
+          resources:
+            {{- toYaml .Values.reranker.resources | nindent 12 }}
+          volumeMounts:
+            - name: hf-cache
+              mountPath: /app/.cache/huggingface
+          envFrom:
+            - configMapRef:
+                name: rag-env
+      volumes:
+        - name: hf-cache
+          persistentVolumeClaim:
+            claimName: rag-model-weights
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ .Release.Name }}-reranker
+  labels:
+    app.kubernetes.io/name: reranker
+    app.kubernetes.io/instance: {{ .Release.Name }}
+spec:
+  selector:
+    app.kubernetes.io/name: reranker
+    app.kubernetes.io/instance: {{ .Release.Name }}
+  ports:
+    - protocol: TCP
+      port: {{ .Values.reranker.service.port }}
+      targetPort: {{ .Values.reranker.service.port }}
+  type: {{ .Values.reranker.service.type }}

charts/openrag-stack/templates/ingress.yaml

@@ -0,0 +1,26 @@
+{{- if .Values.ingress.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "openrag-stack.fullname" . }}-ingress
+  annotations:
+    nginx.ingress.kubernetes.io/rewrite-target: /$1
+    nginx.ingress.kubernetes.io/use-regex: "true"  
+spec:
+  ingressClassName: {{ .Values.ingress.className | quote }}
+  rules:
+    - http:
+        paths:
+          {{- if .Values.ingress.paths.openrag.enabled }}
+          - path: /(.*)
+            pathType: ImplementationSpecific
+            backend:
+              service:
+                name: raycluster-head-svc
+                port:
+                  number: {{ .Values.env.config.RAY_SERVE_PORT }}
+          {{- end }}
+      {{- with .Values.ingress.host }}
+      host: {{ . | quote }}
+      {{- end }}
+{{- end }}