diff --git a/helm-charts/common/tei/Chart.yaml b/helm-charts/common/tei/Chart.yaml index 45b3cb734..f2494dc9b 100644 --- a/helm-charts/common/tei/Chart.yaml +++ b/helm-charts/common/tei/Chart.yaml @@ -7,4 +7,4 @@ description: The Helm chart for HuggingFace Text Embedding Inference Server type: application version: 0.8.0 # The HF TEI version -appVersion: "1.2" +appVersion: "cpu-1.5" diff --git a/helm-charts/common/tei/README.md b/helm-charts/common/tei/README.md index a218a9afc..14d647f49 100644 --- a/helm-charts/common/tei/README.md +++ b/helm-charts/common/tei/README.md @@ -40,4 +40,4 @@ curl http://localhost:2081/embed -X POST -d '{"inputs":"What is Deep Learning?"} | EMBEDDING_MODEL_ID | string | `"BAAI/bge-base-en-v1.5"` | Models id from https://huggingface.co/, or predownloaded model directory | | global.modelUseHostPath | string | `"/mnt/opea-models"` | Cached models directory, tei will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory. Set this to null/empty will force it to download model. | | image.repository | string | `"ghcr.io/huggingface/text-embeddings-inference"` | | -| image.tag | string | `"cpu-1.2"` | | +| image.tag | string | `"cpu-1.5"` | | diff --git a/helm-charts/common/tei/templates/deployment.yaml b/helm-charts/common/tei/templates/deployment.yaml index f3f72a0a9..381226323 100644 --- a/helm-charts/common/tei/templates/deployment.yaml +++ b/helm-charts/common/tei/templates/deployment.yaml @@ -45,6 +45,8 @@ spec: {{- end }} image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/helm-charts/common/tei/values.yaml b/helm-charts/common/tei/values.yaml index 66de346d4..54545d809 100644 --- a/helm-charts/common/tei/values.yaml +++ b/helm-charts/common/tei/values.yaml @@ -14,7 +14,7 @@ image: repository: ghcr.io/huggingface/text-embeddings-inference pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - tag: "cpu-1.2" + tag: "cpu-1.5" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/teirerank/Chart.yaml b/helm-charts/common/teirerank/Chart.yaml index 2ce22f50c..5a28094f8 100644 --- a/helm-charts/common/teirerank/Chart.yaml +++ b/helm-charts/common/teirerank/Chart.yaml @@ -7,4 +7,4 @@ description: The Helm chart for HuggingFace Text Embedding Inference Server type: application version: 0.8.0 # The HF TEI version -appVersion: "1.2" +appVersion: "cpu-1.5" diff --git a/helm-charts/common/teirerank/README.md b/helm-charts/common/teirerank/README.md index 0cf86c751..b3cb2f193 100644 --- a/helm-charts/common/teirerank/README.md +++ b/helm-charts/common/teirerank/README.md @@ -43,4 +43,4 @@ curl http://localhost:2082/rerank \ | RERANK_MODEL_ID | string | `"BAAI/bge-reranker-base"` | Models id from https://huggingface.co/, or predownloaded model directory | | global.modelUseHostPath | string | `"/mnt/opea-models"` | Cached models directory, teirerank will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory. Set this to null/empty will force it to download model. | | image.repository | string | `"ghcr.io/huggingface/text-embeddings-inference"` | | -| image.tag | string | `"cpu-1.2"` | | +| image.tag | string | `"cpu-1.5"` | | diff --git a/helm-charts/common/teirerank/templates/deployment.yaml b/helm-charts/common/teirerank/templates/deployment.yaml index 1bbb87f3d..ff2c84a8e 100644 --- a/helm-charts/common/teirerank/templates/deployment.yaml +++ b/helm-charts/common/teirerank/templates/deployment.yaml @@ -45,6 +45,8 @@ spec: {{- end }} image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/helm-charts/common/teirerank/values.yaml b/helm-charts/common/teirerank/values.yaml index 73383973a..b0062f1b8 100644 --- a/helm-charts/common/teirerank/values.yaml +++ b/helm-charts/common/teirerank/values.yaml @@ -14,7 +14,7 @@ image: repository: ghcr.io/huggingface/text-embeddings-inference pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - tag: "cpu-1.2" + tag: "cpu-1.5" imagePullSecrets: [] nameOverride: "" diff --git a/microservices-connector/config/manifests/tei.yaml b/microservices-connector/config/manifests/tei.yaml index fcb52f2ed..9a76b5ffc 100644 --- a/microservices-connector/config/manifests/tei.yaml +++ b/microservices-connector/config/manifests/tei.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "BAAI/bge-base-en-v1.5" @@ -36,7 +36,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -61,7 +61,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: replicas: 1 @@ -87,8 +87,10 @@ spec: optional: true securityContext: {} - image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.2" + image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.5" imagePullPolicy: IfNotPresent + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/microservices-connector/config/manifests/tei_gaudi.yaml b/microservices-connector/config/manifests/tei_gaudi.yaml index 4ac593ce2..75626b79c 100644 --- a/microservices-connector/config/manifests/tei_gaudi.yaml +++ b/microservices-connector/config/manifests/tei_gaudi.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "BAAI/bge-base-en-v1.5" @@ -36,7 +36,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -61,7 +61,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: replicas: 1 @@ -89,6 +89,8 @@ spec: {} image: "ghcr.io/huggingface/tei-gaudi:synapse_1.16" imagePullPolicy: IfNotPresent + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/microservices-connector/config/manifests/teirerank.yaml b/microservices-connector/config/manifests/teirerank.yaml index 46836586c..4991e6e01 100644 --- a/microservices-connector/config/manifests/teirerank.yaml +++ b/microservices-connector/config/manifests/teirerank.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: teirerank-0.8.0 app.kubernetes.io/name: teirerank app.kubernetes.io/instance: teirerank - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "BAAI/bge-reranker-base" @@ -35,7 +35,7 @@ metadata: helm.sh/chart: teirerank-0.8.0 app.kubernetes.io/name: teirerank app.kubernetes.io/instance: teirerank - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -60,7 +60,7 @@ metadata: helm.sh/chart: teirerank-0.8.0 app.kubernetes.io/name: teirerank app.kubernetes.io/instance: teirerank - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: replicas: 1 @@ -86,8 +86,10 @@ spec: optional: true securityContext: {} - image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.2" + image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.5" imagePullPolicy: IfNotPresent + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume