diff --git a/helm-charts/chatqna/nv-values.yaml b/helm-charts/chatqna/nv-values.yaml index 93abd8952..b9fc70dee 100644 --- a/helm-charts/chatqna/nv-values.yaml +++ b/helm-charts/chatqna/nv-values.yaml @@ -1,4 +1,4 @@ -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2025 Intel Corporation # SPDX-License-Identifier: Apache-2.0 # To override values in subchart tgi @@ -9,7 +9,7 @@ tgi: accelDevice: "nvidia" image: repository: ghcr.io/huggingface/text-generation-inference - tag: "2.2.0" + tag: "2.4.1" resources: limits: nvidia.com/gpu: 1 diff --git a/helm-charts/common/tei/Chart.yaml b/helm-charts/common/tei/Chart.yaml index f53d27474..e3711651d 100644 --- a/helm-charts/common/tei/Chart.yaml +++ b/helm-charts/common/tei/Chart.yaml @@ -1,4 +1,4 @@ -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2025 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v2 @@ -11,4 +11,4 @@ dependencies: repository: "file://../commonlib" version: 0-latest # The HF TEI version -appVersion: "cpu-1.5" +appVersion: "cpu-1.6" diff --git a/helm-charts/common/tei/README.md b/helm-charts/common/tei/README.md index b21c2eb25..88516ce84 100644 --- a/helm-charts/common/tei/README.md +++ b/helm-charts/common/tei/README.md @@ -40,6 +40,6 @@ 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-1.5"` | | +| image.tag | string | `"cpu-1.6"` | | | autoscaling.enabled | bool | `false` | Enable HPA autoscaling for the service deployment based on metrics it provides. See [HPA instructions](../../HPA.md) before enabling! | | global.monitoring | bool | `false` | Enable usage metrics for the service. Required for HPA. See [monitoring instructions](../../monitoring.md) before enabling! | diff --git a/helm-charts/common/tei/values.yaml b/helm-charts/common/tei/values.yaml index b3d029360..fbbaf39e1 100644 --- a/helm-charts/common/tei/values.yaml +++ b/helm-charts/common/tei/values.yaml @@ -1,4 +1,4 @@ -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2025 Intel Corporation # SPDX-License-Identifier: Apache-2.0 # Default values for tei. @@ -27,7 +27,7 @@ image: # Uncomment the following line to set desired image pull policy if needed, as one of Always, IfNotPresent, Never. # pullPolicy: "" # Overrides the image tag whose default is the chart appVersion. - tag: "cpu-1.5" + tag: "cpu-1.6" # empty for CPU accelDevice: "" diff --git a/helm-charts/common/teirerank/Chart.yaml b/helm-charts/common/teirerank/Chart.yaml index 590092f33..04ea4f06d 100644 --- a/helm-charts/common/teirerank/Chart.yaml +++ b/helm-charts/common/teirerank/Chart.yaml @@ -1,4 +1,4 @@ -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2025 Intel Corporation # SPDX-License-Identifier: Apache-2.0 apiVersion: v2 @@ -11,4 +11,4 @@ dependencies: repository: "file://../commonlib" version: 0-latest # The HF TEI version -appVersion: "cpu-1.5" +appVersion: "cpu-1.6" diff --git a/helm-charts/common/teirerank/README.md b/helm-charts/common/teirerank/README.md index 79202497d..2c52eb951 100644 --- a/helm-charts/common/teirerank/README.md +++ b/helm-charts/common/teirerank/README.md @@ -43,6 +43,6 @@ 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-1.5"` | | +| image.tag | string | `"cpu-1.6"` | | | autoscaling.enabled | bool | `false` | Enable HPA autoscaling for the service deployment based on metrics it provides. See [HPA instructions](../../HPA.md) before enabling! | | global.monitoring | bool | `false` | Enable usage metrics for the service. Required for HPA. See [monitoring instructions](../../monitoring.md) before enabling! | diff --git a/helm-charts/common/teirerank/values.yaml b/helm-charts/common/teirerank/values.yaml index 97fa1ca39..c356b8a6a 100644 --- a/helm-charts/common/teirerank/values.yaml +++ b/helm-charts/common/teirerank/values.yaml @@ -1,4 +1,4 @@ -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2025 Intel Corporation # SPDX-License-Identifier: Apache-2.0 # Default values for teirerank. @@ -27,7 +27,7 @@ image: # Uncomment the following line to set desired image pull policy if needed, as one of Always, IfNotPresent, Never. # pullPolicy: "" # Overrides the image tag whose default is the chart appVersion. - tag: "cpu-1.5" + tag: "cpu-1.6" # empty for CPU accelDevice: "" diff --git a/helm-charts/common/tgi/nv-values.yaml b/helm-charts/common/tgi/nv-values.yaml index d073ffb9c..2195e0cdb 100644 --- a/helm-charts/common/tgi/nv-values.yaml +++ b/helm-charts/common/tgi/nv-values.yaml @@ -1,4 +1,4 @@ -# Copyright (C) 2024 Intel Corporation +# Copyright (C) 2025 Intel Corporation # SPDX-License-Identifier: Apache-2.0 # Default values for tgi. @@ -9,7 +9,7 @@ accelDevice: "nvidia" image: repository: ghcr.io/huggingface/text-generation-inference - tag: "2.2.0" + tag: "2.4.1" resources: limits: