Add web retriever component (#164)

* Add web retriever component This is the retriever component for example SearchQnA Signed-off-by: Dolpher Du <[email protected]>
opea-project · Jul 11, 2024 · 892c15f · 892c15f
1 parent 2fcbb0d
commit 892c15f
Show file tree

Hide file tree

Showing 8 changed files with 346 additions and 0 deletions.
diff --git a/helm-charts/common/web-retriever/.helmignore b/helm-charts/common/web-retriever/.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/
diff --git a/helm-charts/common/web-retriever/Chart.yaml b/helm-charts/common/web-retriever/Chart.yaml
@@ -0,0 +1,10 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v2
+name: web-retriever
+description: The Helm chart for deploying web retriever as microservice
+type: application
+version: 0.8.0
+# The web retriever microservice server version
+appVersion: "1.0.0"
diff --git a/helm-charts/common/web-retriever/README.md b/helm-charts/common/web-retriever/README.md
@@ -0,0 +1,41 @@
+# web-retriever
+
+Helm chart for deploying Web Retriever microservice.
+
+Web retriever depends on tei, you should set TEI_EMBEDDING_ENDPOINT endpoints before start.
+
+## Installing the Chart
+
+To install the chart, run the following:
+
+```console
+export TEI_EMBEDDING_ENDPOINT="http://tei"
+export GOOGLE_API_KEY="yourownkey"
+export GOOGLE_CSE_ID="yourownid"
+helm install web-retriever web-retriever --set TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT} \
+--set GOOGLE_API_KEY=${GOOGLE_API_KEY} \
+--set GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
+```
+
+## Verify
+
+Use port-forward to access it from localhost.
+
+```console
+kubectl port-forward service/web-retriever 1234:7077 &
+your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://localhost:1234/v1/web_retrieval \
+  -X POST \
+  -d "{\"text\":\"What is OPEA?\",\"embedding\":${your_embedding}}" \
+  -H 'Content-Type: application/json'
+```
+
+## Values
+
+| Key                    | Type   | Default                              | Description |
+| ---------------------- | ------ | ------------------------------------ | ----------- |
+| image.repository       | string | `"opea/web-retriever-chroma:latest"` |             |
+| service.port           | string | `"7077"`                             |             |
+| TEI_EMBEDDING_ENDPOINT | string | `""`                                 |             |
+| GOOGLE_API_KEY         | string | `""`                                 |             |
+| GOOGLE_CSE_ID          | string | `""`                                 |             |
diff --git a/helm-charts/common/web-retriever/templates/_helpers.tpl b/helm-charts/common/web-retriever/templates/_helpers.tpl
@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "web-retriever.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 "web-retriever.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 "web-retriever.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "web-retriever.labels" -}}
+helm.sh/chart: {{ include "web-retriever.chart" . }}
+{{ include "web-retriever.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "web-retriever.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "web-retriever.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "web-retriever.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "web-retriever.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
diff --git a/helm-charts/common/web-retriever/templates/deployment.yaml b/helm-charts/common/web-retriever/templates/deployment.yaml
@@ -0,0 +1,100 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "web-retriever.fullname" . }}
+  labels:
+    {{- include "web-retriever.labels" . | nindent 4 }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "web-retriever.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "web-retriever.selectorLabels" . | nindent 8 }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Release.Name }}
+          env:
+            - name: TEI_EMBEDDING_ENDPOINT
+              {{- if .Values.TEI_EMBEDDING_ENDPOINT }}
+              value: {{ .Values.TEI_EMBEDDING_ENDPOINT | quote}}
+              {{- else }}
+              value: "http://{{ .Release.Name }}-tei"
+              {{- end }}
+            - name: GOOGLE_API_KEY
+              value: {{ .Values.GOOGLE_API_KEY }}
+            - name: GOOGLE_CSE_ID
+              value: {{ .Values.GOOGLE_CSE_ID }}
+            - name: EASYOCR_MODULE_PATH
+              value: "/tmp/.EasyOCR"
+            - name: http_proxy
+              value: {{ .Values.global.http_proxy }}
+            - name: https_proxy
+              value: {{ .Values.global.https_proxy }}
+            - name: no_proxy
+              value: {{ .Values.global.no_proxy }}
+            - name: HF_HOME
+              value: "/tmp/.cache/huggingface"
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: web-retriever
+              containerPort: 7077
+              protocol: TCP
+          volumeMounts:
+            - mountPath: /tmp
+              name: tmp
+          startupProbe:
+            exec:
+              command:
+              - curl
+              {{- if .Values.TEI_EMBEDDING_ENDPOINT }}
+              - {{ .Values.TEI_EMBEDDING_ENDPOINT }}
+              {{- else }}
+              - http://{{ .Release.Name }}-tei
+              {{- end }}
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 120
+#          livenessProbe:
+#            httpGet:
+#              path: /
+#              port: 7000
+#          readinessProbe:
+#            httpGet:
+#              path: /
+#              port: 7000
+          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 }}
diff --git a/helm-charts/common/web-retriever/templates/service.yaml b/helm-charts/common/web-retriever/templates/service.yaml
@@ -0,0 +1,18 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "web-retriever.fullname" . }}
+  labels:
+    {{- include "web-retriever.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: 7077
+      protocol: TCP
+      name: web-retriever
+  selector:
+    {{- include "web-retriever.selectorLabels" . | nindent 4 }}
diff --git a/helm-charts/common/web-retriever/templates/tests/test-pod.yaml b/helm-charts/common/web-retriever/templates/tests/test-pod.yaml
@@ -0,0 +1,26 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "web-retriever.fullname" . }}-testpod"
+  labels:
+    {{- include "web-retriever.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+    #"helm.sh/hook-delete-policy": "hook-succeeded, hook-failure"
+spec:
+  containers:
+    - name: curl
+      #image: alpine/curl
+      image: python:3.10.14
+      command: ['sh', '-c']
+      args:
+        - |
+          your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)");
+          curl http://{{ include "web-retriever.fullname" . }}:{{ .Values.service.port }}/v1/web_retrieval \
+          -X POST \
+          -d "{\"text\":\"What is OPEA?\",\"embedding\":${your_embedding}}" \
+                -H 'Content-Type: application/json'
+  restartPolicy: Never
diff --git a/helm-charts/common/web-retriever/values.yaml b/helm-charts/common/web-retriever/values.yaml
@@ -0,0 +1,66 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Default values for web-retriever.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+TEI_EMBEDDING_ENDPOINT: ""
+GOOGLE_API_KEY: ""
+GOOGLE_CSE_ID: ""
+
+image:
+  repository: opea/web-retriever-chroma:latest
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  # tag: "1.0"
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+podAnnotations: {}
+
+podSecurityContext: {}
+  # fsGroup: 2000
+
+securityContext:
+  readOnlyRootFilesystem: true
+  allowPrivilegeEscalation: false
+  runAsNonRoot: true
+  runAsUser: 1000
+  capabilities:
+    drop:
+    - ALL
+  seccompProfile:
+    type: RuntimeDefault
+
+service:
+  type: ClusterIP
+  # The default port for retriever service is 7000
+  port: 7077
+
+resources: {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 100m
+  #   memory: 128Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+global:
+  http_proxy:
+  https_proxy:
+  no_proxy: