Helm Chart for AgentQnA

helm-charts/agentqna/.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/

helm-charts/agentqna/Chart.yaml

@@ -0,0 +1,43 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v2
+name: agentqna
+description: The Helm chart to deploy AgentQnA
+type: application
+dependencies:
+  - name: agent
+    version: 1.0.0
+    alias: worker
+    repository: "file://../common/agent"
+  - name: agent
+    version: 1.0.0
+    alias: supervisor
+    repository: "file://../common/agent"
+  - name: tgi
+    version: 1.0.0
+    repository: "file://../common/tgi"
+    condition: tgi.enabled
+  - name: tei
+    version: 1.0.0
+    repository: "file://../common/tei"
+  - name: embedding-usvc
+    version: 1.0.0
+    repository: "file://../common/embedding-usvc"
+  - name: teirerank
+    version: 1.0.0
+    repository: "file://../common/teirerank"
+  - name: reranking-usvc
+    version: 1.0.0
+    repository: "file://../common/reranking-usvc"
+  - name: redis-vector-db
+    version: 1.0.0
+    repository: "file://../common/redis-vector-db"
+  - name: retriever-usvc
+    version: 1.0.0
+    repository: "file://../common/retriever-usvc"
+  - name: data-prep
+    version: 1.0.0
+    repository: "file://../common/data-prep"
+version: 1.0.0
+appVersion: "v1.0"

helm-charts/agentqna/README.md

@@ -0,0 +1,26 @@
+# AgentQnA
+
+Helm chart for deploying AgentQnA service.
+
+## Deploy
+
+helm repo add opea https://opea-project.github.io/GenAIInfra
+
+helm install agentqna opea/agentqna --set global.HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} --set tgi.enabled=True
+
+## Verify
+
+To verify the installation, run the command `kubectl get pod` to make sure all pods are running.
+
+### Verify the workload through curl command
+
+Run the command `kubectl port-forward svc/agentqna-supervisor 9090:9090` to expose the service for access.
+
+Open another terminal and run the following command to verify the service if working:
+
+```console
+curl http://localhost:9090/v1/chat/completions \
+    -X POST \
+    -H "Content-Type: application/json" \
+    -d '{"query": "Most recent album by Michael Jackson"}'
+```

helm-charts/agentqna/gaudi-values.yaml

@@ -0,0 +1,37 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Accelerate inferencing in heaviest components to improve performance
+# by overriding their subchart values
+
+tgi:
+  accelDevice: "gaudi"
+  image:
+    repository: ghcr.io/huggingface/tgi-gaudi
+    tag: "2.0.5"
+  resources:
+    limits:
+      habana.ai/gaudi: 4
+  MAX_INPUT_LENGTH: "4096"
+  MAX_TOTAL_TOKENS: "8192"
+  CUDA_GRAPHS: ""
+  OMPI_MCA_btl_vader_single_copy_mechanism: "none"
+  PT_HPU_ENABLE_LAZY_COLLECTIVES: "true"
+  ENABLE_HPU_GRAPH: "true"
+  LIMIT_HPU_GRAPH: "true"
+  USE_FLASH_ATTENTION: "true"
+  FLASH_ATTENTION_RECOMPUTE: "true"
+  extraCmdArgs: ["--sharded","true","--num-shard","4"]
+  livenessProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+  readinessProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+  startupProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120

helm-charts/agentqna/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "agentqna.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 "agentqna.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 "agentqna.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "agentqna.labels" -}}
+helm.sh/chart: {{ include "agentqna.chart" . }}
+{{ include "agentqna.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "agentqna.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "agentqna.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "agentqna.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "agentqna.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

helm-charts/agentqna/templates/crag.yaml

@@ -0,0 +1,94 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ .Release.Name }}-crag
+  labels:
+    {{- include "agentqna.labels" . | nindent 4 }}
+    app: {{ .Release.Name }}-crag
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "agentqna.selectorLabels" . | nindent 6 }}
+      app: {{ .Release.Name }}-crag
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "agentqna.selectorLabels" . | nindent 8 }}
+        app: {{ .Release.Name }}-crag
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Release.Name }}
+          env:
+            {{- if .Values.LOGFLAG }}
+            - name: LOGFLAG
+              value: {{ .Values.LOGFLAG | quote }}
+            {{- end }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.crag.image.repository }}:{{ .Values.crag.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.crag.image.pullPolicy }}
+          volumeMounts:
+            - mountPath: /tmp
+              name: tmp
+          ports:
+            - name: crag
+              containerPort: 8000
+              protocol: TCP
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      volumes:
+        - name: tmp
+          emptyDir: {}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- if .Values.evenly_distributed }}
+      topologySpreadConstraints:
+        - maxSkew: 1
+          topologyKey: kubernetes.io/hostname
+          whenUnsatisfiable: ScheduleAnyway
+          labelSelector:
+            matchLabels:
+              {{- include "agentqna.selectorLabels" . | nindent 14 }}
+              app: {{ .Release.Name }}-crag
+      {{- end }}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ .Release.Name }}-crag
+  labels:
+    {{- include "agentqna.labels" . | nindent 4 }}
+spec:
+  type: ClusterIP
+  ports:
+    - port: 8080
+      targetPort: 8000
+      protocol: TCP
+      name: crag
+  selector:
+    {{- include "agentqna.selectorLabels" . | nindent 4 }}
+    app: {{ .Release.Name }}-crag