helm: Enhance dataprep to support local embedding and getfile

- By setting TEI_EMBEDDING_ENDPOINT to empty and EMBED_MODEL to non-empty, data-prep can support local embedding. - Support getfile and delete URL Signed-off-by: Lianhao Lu <[email protected]>
opea-project · Aug 6, 2024 · 73b5b65 · 73b5b65
1 parent 847878a
commit 73b5b65
Show file tree

Hide file tree

Showing 8 changed files with 111 additions and 25 deletions.
diff --git a/helm-charts/common/data-prep/README.md b/helm-charts/common/data-prep/README.md
@@ -4,14 +4,43 @@ Helm chart for deploying data-prep microservice.
 
 data-prep will use redis and tei service, please specify the endpoints.
 
-## Installing the Chart
+## (Option1): Installing the chart separately:
 
-To install the chart, run the following:
+First, you need to install the tei and redis-vector-db chart, please refer to the [tei](../tei) and [redis-vector-db](../redis-vector-db) for more information.
+
+After you've deployted the tei and redis-vector-db chart successfully, please run `kubectl get svc` to get the service endpoint and URL respectively, i.e. `http://tei`, `redis://redis-vector-db:6379`.
+
+To install data-prep chart, run the following:
 
 ```console
+cd GenAIInfra/helm-charts/common/data-prep
 export REDIS_URL="redis://redis-vector-db:6379"
 export TEI_EMBEDDING_ENDPOINT="http://tei"
-helm install dataprep data-prep --set REDIS_URL=${REDIS_URL} --set TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT}
+helm dependency update
+helm install data-prep . --set REDIS_URL=${REDIS_URL} --set TEI_EMBEDDING_ENDPOINT=${TEI_EMBEDDING_ENDPOINT}
+```
+
+## (Option2): Installing the chart with dependencies automatically:
+
+```console
+cd GenAIInfra/helm-charts/common/data-prep
+helm dependency update
+helm install data-prep . --set autodependency.enabled=true
+```
+
+## Verify
+
+To verify the installation, run the command `kubectl get pod` to make sure all pods are running.
+
+Then run the command `kubectl port-forward svc/data-prep 6007:6007` to expose the data-prep service for access.
+
+Open another terminal and run the following command to verify the service if working:
+
+```console
+curl http://localhost:6007/v1/dataprep  \
+    -X POST \
+    -H "Content-Type: multipart/form-data" \
+    -F "files=@./README.md"
 ```
 
 ## Values

diff --git a/helm-charts/common/data-prep/templates/NOTES.txt b/helm-charts/common/data-prep/templates/NOTES.txt
diff --git a/helm-charts/common/data-prep/templates/configmap.yaml b/helm-charts/common/data-prep/templates/configmap.yaml
@@ -10,15 +10,16 @@ metadata:
 data:
   {{- if .Values.TEI_EMBEDDING_ENDPOINT }}
   TEI_ENDPOINT: {{ .Values.TEI_EMBEDDING_ENDPOINT | quote}}
-  {{- else }}
+  {{- else if not .Values.EMBED_MODEL }}
   TEI_ENDPOINT: "http://{{ .Release.Name }}-tei"
   {{- end }}
+  EMBED_MODEL: {{ .Values.EMBED_MODEL | quote }}
   {{- if .Values.REDIS_URL }}
   REDIS_URL: {{ .Values.REDIS_URL | quote}}
   {{- else }}
   REDIS_URL: "redis://{{ .Release.Name }}-redis-vector-db:6379"
   {{- end }}
-  INDEX_NAME: "rag-redis"
+  INDEX_NAME: {{ .Values.INDEX_NAME | quote }}
   HUGGINGFACEHUB_API_TOKEN: {{ .Values.global.HUGGINGFACEHUB_API_TOKEN | quote}}
   HF_HOME: "/tmp/.cache/huggingface"
   http_proxy: {{ .Values.global.http_proxy | quote }}

diff --git a/helm-charts/common/data-prep/templates/deployment.yaml b/helm-charts/common/data-prep/templates/deployment.yaml
@@ -45,6 +45,12 @@ spec:
             - name: data-prep
               containerPort: 6007
               protocol: TCP
+            # The following need to be modified after GenAIComps bug #282 is resolved.
+            # https://github.com/opea-project/GenAIComps/issues/282
+            - containerPort: 6008
+              protocol: TCP
+            - containerPort: 6009
+              protocol: TCP
           volumeMounts:
             - mountPath: /tmp
               name: tmp

diff --git a/helm-charts/common/data-prep/templates/service.yaml b/helm-charts/common/data-prep/templates/service.yaml
@@ -10,9 +10,11 @@ metadata:
 spec:
   type: {{ .Values.service.type }}
   ports:
-    - port: {{ .Values.service.port }}
-      targetPort: 6007
+    {{- range .Values.service.ports }}
+    - port: {{ .port }}
+      targetPort: {{ .targetPort }}
       protocol: TCP
-      name: data-prep
+      name: {{ .name }}
+    {{- end }}
   selector:
     {{- include "data-prep.selectorLabels" . | nindent 4 }}
diff --git a/helm-charts/common/data-prep/templates/tests/test-pod.yaml b/helm-charts/common/data-prep/templates/tests/test-pod.yaml
@@ -0,0 +1,34 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Pod
+metadata:
+  name: {{ include "data-prep.fullname" . }}-testpod
+  labels:
+    {{- include "data-prep.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: ['bash', '-c']
+      args:
+        - |
+          echo "test file" > /tmp/file1.txt;
+          {{- with index .Values.service.ports 0 }}
+          export port={{.port}};
+          {{- end }}
+          max_retry=20;
+          for ((i=1; i<=max_retry; i++)); do
+            curl http://{{ include "data-prep.fullname" . }}:$port/v1/dataprep -sS --fail-with-body \
+            -X POST \
+            -H "Content-Type: multipart/form-data" \
+            -F "files=@/tmp/file1.txt" && break;
+            sleep 10;
+          done;
+          if [ $i -gt $max_retry ]; then echo "dataprep test failed."; exit 1; fi
+  restartPolicy: Never
diff --git a/helm-charts/common/data-prep/values.yaml b/helm-charts/common/data-prep/values.yaml
@@ -38,8 +38,19 @@ securityContext:
 
 service:
   type: ClusterIP
+  # The following need to be modified after GenAIComps bug #282 is resolved.
+  # https://github.com/opea-project/GenAIComps/issues/282
+  ports:
   # The default port for data prep service is 6007
-  port: 6007
+  - port: 6007
+    targetPort: 6007
+    name: data-prep
+  - port: 6008
+    targetPort: 6008
+    name: data-prep-get
+  - port: 6009
+    targetPort: 6009
+    name: data-prep-delete
 
 resources: {}
   # We usually recommend not to specify default resources and to leave this as a conscious
@@ -83,8 +94,12 @@ affinity: {}
 # text embedding inference service URL, e.g. http://<service-name>:<port>
 TEI_EMBEDDING_ENDPOINT: ""
 
+# local embedder's model
+EMBED_MODEL: ""
+
 # redis DB service URL, e.g. redis://<service-name>:<port>
 REDIS_URL: ""
+INDEX_NAME: "rag-redis"
 
 global:
   http_proxy: ""

diff --git a/manifests/common/data-prep.yaml b/manifests/common/data-prep.yaml
@@ -15,6 +15,7 @@ metadata:
     app.kubernetes.io/managed-by: Helm
 data:
   TEI_ENDPOINT: "http://data-prep-tei"
+  EMBED_MODEL: ""
   REDIS_URL: "redis://data-prep-redis-vector-db:6379"
   INDEX_NAME: "rag-redis"
   HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
@@ -47,6 +48,14 @@ spec:
       targetPort: 6007
       protocol: TCP
       name: data-prep
+    - port: 6008
+      targetPort: 6008
+      protocol: TCP
+      name: data-prep-get
+    - port: 6009
+      targetPort: 6009
+      protocol: TCP
+      name: data-prep-delete
   selector:
     app.kubernetes.io/name: data-prep
     app.kubernetes.io/instance: data-prep
@@ -103,6 +112,12 @@ spec:
             - name: data-prep
               containerPort: 6007
               protocol: TCP
+            # The following need to be modified after GenAIComps bug #282 is resolved.
+            # https://github.com/opea-project/GenAIComps/issues/282
+            - containerPort: 6008
+              protocol: TCP
+            - containerPort: 6009
+              protocol: TCP
           volumeMounts:
             - mountPath: /tmp
               name: tmp