From d68c5add0da9eb0e41bce5d2c19d97b83808ecb3 Mon Sep 17 00:00:00 2001 From: chensuyue Date: Tue, 19 Aug 2025 17:10:28 +0800 Subject: [PATCH 1/4] Upgrade qdrant version Signed-off-by: chensuyue --- helm-charts/common/data-prep/Chart.yaml | 2 +- helm-charts/common/data-prep/qdrant-values.yaml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/helm-charts/common/data-prep/Chart.yaml b/helm-charts/common/data-prep/Chart.yaml index 829b6885d..801ecb677 100644 --- a/helm-charts/common/data-prep/Chart.yaml +++ b/helm-charts/common/data-prep/Chart.yaml @@ -22,7 +22,7 @@ dependencies: repository: https://zilliztech.github.io/milvus-helm/ condition: milvus.enabled - name: qdrant - version: 1.13.1 + version: 1.15.3 repository: https://qdrant.github.io/qdrant-helm condition: qdrant.enabled - name: commonlib diff --git a/helm-charts/common/data-prep/qdrant-values.yaml b/helm-charts/common/data-prep/qdrant-values.yaml index c086e41c7..d0038469d 100644 --- a/helm-charts/common/data-prep/qdrant-values.yaml +++ b/helm-charts/common/data-prep/qdrant-values.yaml @@ -9,7 +9,7 @@ milvus: enabled: false qdrant: enabled: true - tag: "v1.13.1" + tag: "v1.15.3" config: cluster: enabled: false From 9ec70761da4c9eddbe25ced0d5f6c0a19a8a18e2 Mon Sep 17 00:00:00 2001 From: chensuyue Date: Tue, 19 Aug 2025 14:43:03 +0800 Subject: [PATCH 2/4] Update CodeTrans default model align with docker compose Signed-off-by: chensuyue --- helm-charts/codetrans/README.md | 6 +++--- helm-charts/codetrans/values.yaml | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/helm-charts/codetrans/README.md b/helm-charts/codetrans/README.md index 38d1d4cbc..24cd4c106 100644 --- a/helm-charts/codetrans/README.md +++ b/helm-charts/codetrans/README.md @@ -14,7 +14,7 @@ scripts/update_dependency.sh helm dependency update codetrans export HFTOKEN="insert-your-huggingface-token-here" export MODELDIR="/mnt/opea-models" -export MODELNAME="mistralai/Mistral-7B-Instruct-v0.3" +export MODELNAME="Qwen/Qwen2.5-Coder-7B-Instruct" # To use CPU with vLLM helm install codetrans codetrans --set global.HF_TOKEN=${HFTOKEN} --set global.modelUseHostPath=${MODELDIR} --set llm-uservcie.LLM_MODEL_ID=${MODELNAME} --set vllm.LLM_MODEL_ID=${MODELNAME} -f codetrans/cpu-values.yaml # To use CPU with TGI @@ -31,7 +31,7 @@ helm install codetrans codetrans --set global.HF_TOKEN=${HFTOKEN} --set global.m ### IMPORTANT NOTE -1. To use model `mistralai/Mistral-7B-Instruct-v0.3`, you should first goto the [huggingface model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) to apply for the model access first. You need to make sure your huggingface token has at least read access to that model. +1. To use model `Qwen/Qwen2.5-Coder-7B-Instruct`, you should first goto the [huggingface model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) to apply for the model access first. You need to make sure your huggingface token has at least read access to that model. 2. Make sure your `MODELDIR` exists on the node where your workload is schedueled so you can cache the downloaded model for next time use. Otherwise, set `global.modelUseHostPath` to 'null' if you don't want to cache the model. @@ -70,5 +70,5 @@ Open a browser to access `http://:${port}` to play with the | ----------------- | ------ | -------------------------------------- | -------------------------------------------------------------------------------------- | | image.repository | string | `"opea/codetrans"` | | | service.port | string | `"7777"` | | -| tgi.LLM_MODEL_ID | string | `"mistralai/Mistral-7B-Instruct-v0.3"` | Models id from https://huggingface.co/, or predownloaded model directory | +| tgi.LLM_MODEL_ID | string | `"Qwen/Qwen2.5-Coder-7B-Instruct"` | Models id from https://huggingface.co/, or predownloaded model directory | | global.monitoring | bool | `false` | Enable usage metrics for the service components. See ../monitoring.md before enabling! | diff --git a/helm-charts/codetrans/values.yaml b/helm-charts/codetrans/values.yaml index 24f0a96bb..37885baa4 100644 --- a/helm-charts/codetrans/values.yaml +++ b/helm-charts/codetrans/values.yaml @@ -60,15 +60,15 @@ affinity: {} # To override values in subchart tgi tgi: enabled: false - LLM_MODEL_ID: mistralai/Mistral-7B-Instruct-v0.3 + LLM_MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct vllm: enabled: true - LLM_MODEL_ID: mistralai/Mistral-7B-Instruct-v0.3 + LLM_MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct llm-uservice: TEXTGEN_BACKEND: vLLM - LLM_MODEL_ID: mistralai/Mistral-7B-Instruct-v0.3 + LLM_MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct nginx: service: From 8e0e52902f31af9e1f071e8288a0ee5b1a7c4279 Mon Sep 17 00:00:00 2001 From: "pre-commit-ci[bot]" <66853113+pre-commit-ci[bot]@users.noreply.github.com> Date: Wed, 20 Aug 2025 07:22:13 +0000 Subject: [PATCH 3/4] [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --- helm-charts/codetrans/README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/helm-charts/codetrans/README.md b/helm-charts/codetrans/README.md index 24cd4c106..53bdb53e2 100644 --- a/helm-charts/codetrans/README.md +++ b/helm-charts/codetrans/README.md @@ -66,9 +66,9 @@ Open a browser to access `http://:${port}` to play with the ## Values -| Key | Type | Default | Description | -| ----------------- | ------ | -------------------------------------- | -------------------------------------------------------------------------------------- | -| image.repository | string | `"opea/codetrans"` | | -| service.port | string | `"7777"` | | +| Key | Type | Default | Description | +| ----------------- | ------ | ---------------------------------- | -------------------------------------------------------------------------------------- | +| image.repository | string | `"opea/codetrans"` | | +| service.port | string | `"7777"` | | | tgi.LLM_MODEL_ID | string | `"Qwen/Qwen2.5-Coder-7B-Instruct"` | Models id from https://huggingface.co/, or predownloaded model directory | -| global.monitoring | bool | `false` | Enable usage metrics for the service components. See ../monitoring.md before enabling! | +| global.monitoring | bool | `false` | Enable usage metrics for the service components. See ../monitoring.md before enabling! | From 5066b955c965c17d813313df9e97902d3da543bd Mon Sep 17 00:00:00 2001 From: chensuyue Date: Wed, 20 Aug 2025 22:19:19 +0800 Subject: [PATCH 4/4] update readme Signed-off-by: chensuyue --- helm-charts/codetrans/README.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/helm-charts/codetrans/README.md b/helm-charts/codetrans/README.md index 53bdb53e2..082e1a953 100644 --- a/helm-charts/codetrans/README.md +++ b/helm-charts/codetrans/README.md @@ -31,9 +31,7 @@ helm install codetrans codetrans --set global.HF_TOKEN=${HFTOKEN} --set global.m ### IMPORTANT NOTE -1. To use model `Qwen/Qwen2.5-Coder-7B-Instruct`, you should first goto the [huggingface model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) to apply for the model access first. You need to make sure your huggingface token has at least read access to that model. - -2. Make sure your `MODELDIR` exists on the node where your workload is schedueled so you can cache the downloaded model for next time use. Otherwise, set `global.modelUseHostPath` to 'null' if you don't want to cache the model. +Make sure your `MODELDIR` exists on the node where your workload is scheduled so you can cache the downloaded model for next time use. Otherwise, set `global.modelUseHostPath` to 'null' if you don't want to cache the model. ## Verify