- fixes health probe

- adjust the min resources
- upgrade to node 24

Author: t83714

.github/workflows/main.yml

@@ -10,11 +10,11 @@ jobs:
     name: Build, Test & Push to Docker
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - name: Use Node.js 18
-        uses: actions/setup-node@v1
+      - uses: actions/checkout@v5
+      - name: Use Node.js 24
+        uses: actions/setup-node@v5
         with:
-          node-version: 18
+          node-version: 24
 
       - name: Login to GitHub Container Registry
         run: |

.github/workflows/release.yml

@@ -12,12 +12,12 @@ jobs:
     name: Release Helm Chart
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v5
 
-      - name: Use Node.js 18
-        uses: actions/setup-node@v1
+      - name: Use Node.js 24
+        uses: actions/setup-node@v5
         with:
-          node-version: 18
+          node-version: 24
 
       - name: Login to GitHub Container Registry
         run: |

.github/workflows/set-version.yaml

@@ -21,12 +21,12 @@ jobs:
           SEMVER_REGEX="^v(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)\\.(0|[1-9][0-9]*)(\\-[0-9A-Za-z-]+(\\.[0-9A-Za-z-]+)*)?(\\+[0-9A-Za-z-]+(\\.[0-9A-Za-z-]+)*)?$"
           [[ "${SELECTED_VERSION}" =~ $SEMVER_REGEX ]] || { echo "Invalid version number '$SELECTED_VERSION'. Should be e.g. 'v2.0.0-alpha.0' with leading 'v'." ; exit 1; }
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v5
 
-      - name: Use Node.js 18
-        uses: actions/setup-node@v3
+      - name: Use Node.js 24
+        uses: actions/setup-node@v5
         with:
-          node-version: 18
+          node-version: 24
 
       - name: Install Utilities
         run: yarn install

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "typescript.tsdk": "node_modules/typescript/lib"
+}

Dockerfile

@@ -1,4 +1,4 @@
-FROM node:18-alpine
+FROM node:24-alpine
 
 RUN mkdir -p /usr/src/app
 COPY . /usr/src/app

README.md

@@ -29,12 +29,10 @@ Kubernetes: `>= 1.14.0-0`
 | defaultSemanticIndexerConfig.bulkEmbeddingsSize | int | `1` |  |
 | defaultSemanticIndexerConfig.bulkIndexSize | int | `50` |  |
 | defaultSemanticIndexerConfig.chunkSizeLimit | int | `512` |  |
-| defaultSemanticIndexerConfig.chunkSizeLimit | int | `512` |  |
 | defaultSemanticIndexerConfig.id | string | `"csv-semantic-indexer"` |  |
 | defaultSemanticIndexerConfig.indexName | string | `"semantic-index"` |  |
 | defaultSemanticIndexerConfig.indexVersion | int | `1` |  |
 | defaultSemanticIndexerConfig.overlap | int | `50` |  |
-| defaultSemanticIndexerConfig.overlap | int | `50` |  |
 | embeddingApiURL | string | `"http://magda-embedding-api"` |  |
 | global | object | `{"image":{},"rollingUpdate":{},"searchEngine":{"defaultDatasetBucket":"magda-datasets","semanticIndexer":{"indexName":null,"indexVersion":null,"knnVectorFieldConfig":{"compressionLevel":"32x","dimension":768,"efConstruction":100,"efSearch":100,"m":16,"mode":"on_disk","spaceType":"l2"},"numberOfReplicas":0,"numberOfShards":1}}}` | only for providing appropriate default value for helm lint |
 | global.searchEngine.semanticIndexer.knnVectorFieldConfig.compressionLevel | string | `"32x"` | The compression_level mapping parameter selects a quantization encoder that reduces vector memory consumption by the given factor. |
@@ -51,8 +49,9 @@ Kubernetes: `>= 1.14.0-0`
 | minioConfig.useSSL | bool | `false` |  |
 | opensearchURL | string | `"http://opensearch:9200"` |  |
 | port | int | `6305` | Service port configuration |
-| resources.limits.cpu | string | `"100m"` |  |
-| resources.requests.cpu | string | `"50m"` |  |
+| resources.limits.cpu | string | `"500m"` |  |
+| resources.limits.memory | string | `"512Mi"` |  |
+| resources.requests.cpu | string | `"100m"` |  |
 | resources.requests.memory | string | `"200Mi"` |  |
 | semanticIndexer.bulkEmbeddingsSize | int | `nil` | number of string we request embedding api to process in one request |
 | semanticIndexer.bulkIndexSize | int | `nil` | Number of documents we send to OpenSearch for bulk processing in a single request |

deploy/magda-csv-semantic-indexer/Chart.lock

@@ -0,0 +1,6 @@
+dependencies:
+- name: magda-common
+  repository: oci://ghcr.io/magda-io/charts
+  version: 5.2.0
+digest: sha256:4bc98b935ac3e2d4d8a3e8c153ea069cc8c9c6df8c0b0a2fe5baba45d6547641
+generated: "2025-10-13T12:44:16.882913+11:00"

deploy/magda-csv-semantic-indexer/templates/deployment.yaml

@@ -31,11 +31,14 @@ spec:
             "--chunkSizeLimit", "{{ .Values.semanticIndexer.chunkSizeLimit | default .Values.defaultSemanticIndexerConfig.chunkSizeLimit }}",
             "--overlap", "{{ .Values.semanticIndexer.overlap | default .Values.defaultSemanticIndexerConfig.overlap }}"
         ]
+        ports:
+        - containerPort: {{ int .Values.port }}
+          name: http
 {{- if .Values.global.enableLivenessProbes }}
         livenessProbe:
           httpGet:
             path: "/healthz"
-            port: 80
+            port: {{ .Values.port }}
           initialDelaySeconds: 10
           periodSeconds: 10
           timeoutSeconds: 10

deploy/magda-csv-semantic-indexer/values.yaml

@@ -42,8 +42,6 @@ defaultSemanticIndexerConfig:
   overlap: 50
   indexName: "semantic-index"
   indexVersion: 1
-  chunkSizeLimit: 512
-  overlap: 50
   bulkEmbeddingsSize: 1
   bulkIndexSize: 50
 
@@ -85,7 +83,8 @@ defaultAdminUserId: "00000000-0000-4000-8000-000000000000"
 
 resources:
   requests:
-    cpu: 50m
+    cpu: 100m
     memory: 200Mi
   limits:
-    cpu: 100m
+    cpu: 500m
+    memory: 512Mi

dev-config.json

@@ -0,0 +1,12 @@
+{
+    "internalUrl": "http://magda-csv-semantic-indexer",
+    "registryUrl": "http://localhost:6101/v0",
+    "registryReadonlyURL": "http://localhost:6101/v0",
+    "semanticIndexerConfig": "../../../../dev-indexer-config.json",
+    "minioConfig": "../../../../dev-minio-config.json",
+    "opensearchApiURL": "http://localhost:9200",
+    "embeddingApiURL": "http://localhost:3000",
+    "jwtSecret": "replace_me",
+    "minioAccessKey": "reaplce_me",
+    "minioSecretKey": "replace_me"
+}