Fix ChatQnA manifest default port issue (#1033)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
2024-10-30 11:52:04 +08:00
parent 960805a57b
commit 7197286a14
18 changed files with 20 additions and 50 deletions
--- a/AudioQnA/kubernetes/intel/README.md
+++ b/AudioQnA/kubernetes/intel/README.md
@@ -7,14 +7,14 @@

 ## Deploy On Xeon
 ```
-cd GenAIExamples/AudioQnA/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/AudioQnA/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml
 kubectl apply -f audioqna.yaml
 ```
 ## Deploy On Gaudi
 ```
-cd GenAIExamples/AudioQnA/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/AudioQnA/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml
 kubectl apply -f audioqna.yaml
--- a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml
+++ b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml
@@ -1252,18 +1252,12 @@ spec:
          env:
            - name: LLM_SERVER_HOST_IP
              value: chatqna-tgi
-            - name: LLM_SERVER_PORT
-              value: "2080"
            - name: RERANK_SERVER_HOST_IP
              value: chatqna-teirerank
-            - name: RERANK_SERVER_PORT
-              value: "2082"
            - name: RETRIEVER_SERVICE_HOST_IP
              value: chatqna-retriever-usvc
            - name: EMBEDDING_SERVER_HOST_IP
              value: chatqna-tei
-            - name: EMBEDDING_SERVER_PORT
-              value: "2081"
            - name: GUARDRAIL_SERVICE_HOST_IP
              value: chatqna-guardrails-usvc
            - name: GUARDRAIL_SERVICE_PORT
--- a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml
+++ b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml
@@ -994,18 +994,12 @@ spec:
          env:
            - name: LLM_SERVER_HOST_IP
              value: chatqna-tgi
-            - name: LLM_SERVER_PORT
-              value: "2080"
            - name: RERANK_SERVER_HOST_IP
              value: chatqna-teirerank
-            - name: RERANK_SERVER_PORT
-              value: "2082"
            - name: RETRIEVER_SERVICE_HOST_IP
              value: chatqna-retriever-usvc
            - name: EMBEDDING_SERVER_HOST_IP
              value: chatqna-tei
-            - name: EMBEDDING_SERVER_PORT
-              value: "2081"
          securityContext:
            allowPrivilegeEscalation: false
            capabilities:
--- a/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna_bf16.yaml
+++ b/ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna_bf16.yaml
@@ -997,18 +997,12 @@ spec:
          env:
            - name: LLM_SERVER_HOST_IP
              value: chatqna-tgi
-            - name: LLM_SERVER_PORT
-              value: "2080"
            - name: RERANK_SERVER_HOST_IP
              value: chatqna-teirerank
-            - name: RERANK_SERVER_PORT
-              value: "2082"
            - name: RETRIEVER_SERVICE_HOST_IP
              value: chatqna-retriever-usvc
            - name: EMBEDDING_SERVER_HOST_IP
              value: chatqna-tei
-            - name: EMBEDDING_SERVER_PORT
-              value: "2081"
          securityContext:
            allowPrivilegeEscalation: false
            capabilities:
--- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml
+++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml
@@ -1257,18 +1257,12 @@ spec:
          env:
            - name: LLM_SERVER_HOST_IP
              value: chatqna-tgi
-            - name: LLM_SERVER_PORT
-              value: "2080"
            - name: RERANK_SERVER_HOST_IP
              value: chatqna-teirerank
-            - name: RERANK_SERVER_PORT
-              value: "2082"
            - name: RETRIEVER_SERVICE_HOST_IP
              value: chatqna-retriever-usvc
            - name: EMBEDDING_SERVER_HOST_IP
              value: chatqna-tei
-            - name: EMBEDDING_SERVER_PORT
-              value: "2081"
            - name: GUARDRAIL_SERVICE_HOST_IP
              value: chatqna-guardrails-usvc
            - name: GUARDRAIL_SERVICE_PORT
--- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml
+++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml
@@ -997,18 +997,12 @@ spec:
          env:
            - name: LLM_SERVER_HOST_IP
              value: chatqna-tgi
-            - name: LLM_SERVER_PORT
-              value: "2080"
            - name: RERANK_SERVER_HOST_IP
              value: chatqna-teirerank
-            - name: RERANK_SERVER_PORT
-              value: "2082"
            - name: RETRIEVER_SERVICE_HOST_IP
              value: chatqna-retriever-usvc
            - name: EMBEDDING_SERVER_HOST_IP
              value: chatqna-tei
-            - name: EMBEDDING_SERVER_PORT
-              value: "2081"
          securityContext:
            allowPrivilegeEscalation: false
            capabilities:
--- a/ChatQnA/tests/test_manifest_on_gaudi.sh
+++ b/ChatQnA/tests/test_manifest_on_gaudi.sh
@@ -161,7 +161,7 @@ case "$1" in
        if [ $ret -ne 0 ]; then
            exit $ret
        fi
-        pushd ChatQnA/kubernetes/intel/hpu/gaudi/manifests
+        pushd ChatQnA/kubernetes/intel/hpu/gaudi/manifest
        set +e
        install_and_validate_chatqna_guardrail
        popd
--- a/ChatQnA/tests/test_manifest_on_xeon.sh
+++ b/ChatQnA/tests/test_manifest_on_xeon.sh
@@ -161,7 +161,7 @@ case "$1" in
        if [ $ret -ne 0 ]; then
            exit $ret
        fi
-        pushd ChatQnA/kubernetes/intel/cpu/xeon/manifests
+        pushd ChatQnA/kubernetes/intel/cpu/xeon/manifest
        set +e
        install_and_validate_chatqna_guardrail
        popd
--- a/CodeGen/kubernetes/intel/README.md
+++ b/CodeGen/kubernetes/intel/README.md
@@ -12,7 +12,7 @@
 ## Deploy On Xeon

 ```
-cd GenAIExamples/CodeGen/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/CodeGen/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 export MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
@@ -23,7 +23,7 @@ kubectl apply -f codegen.yaml
 ## Deploy On Gaudi

 ```
-cd GenAIExamples/CodeGen/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/CodeGen/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
 kubectl apply -f codegen.yaml
--- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md
+++ b/CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md
@@ -17,7 +17,7 @@ Before deploying the react-codegen.yaml file, ensure that you have the following
    ```
    # You may set the HUGGINGFACEHUB_API_TOKEN via method:
    export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
-    cd GenAIExamples/CodeGen/kubernetes/intel/cpu/xeon/manifests/ui/
+    cd GenAIExamples/CodeGen/kubernetes/intel/cpu/xeon/manifest/ui/
    sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-codegen.yaml
    ```
    b. Set the proxies based on your network configuration
--- a/CodeTrans/kubernetes/intel/README.md
+++ b/CodeTrans/kubernetes/intel/README.md
@@ -21,7 +21,7 @@ Change the `MODEL_ID` in `codetrans.yaml` for your needs.
 ## Deploy On Xeon

 ```bash
-cd GenAIExamples/CodeTrans/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/CodeTrans/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codetrans.yaml
 kubectl apply -f codetrans.yaml
@@ -30,7 +30,7 @@ kubectl apply -f codetrans.yaml
 ## Deploy On Gaudi

 ```bash
-cd GenAIExamples/CodeTrans/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/CodeTrans/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codetrans.yaml
 kubectl apply -f codetrans.yaml
--- a/DocSum/kubernetes/intel/README.md
+++ b/DocSum/kubernetes/intel/README.md
@@ -11,7 +11,7 @@
 ## Deploy On Xeon

 ```
-cd GenAIExamples/DocSum/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/DocSum/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" docsum.yaml
 kubectl apply -f docsum.yaml
@@ -20,7 +20,7 @@ kubectl apply -f docsum.yaml
 ## Deploy On Gaudi

 ```
-cd GenAIExamples/DocSum/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/DocSum/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" docsum.yaml
 kubectl apply -f docsum.yaml
--- a/DocSum/kubernetes/intel/cpu/xeon/manifest/ui/README.md
+++ b/DocSum/kubernetes/intel/cpu/xeon/manifest/ui/README.md
@@ -16,7 +16,7 @@ Before deploying the react-docsum.yaml file, ensure that you have the following
       ```
       # You may set the HUGGINGFACEHUB_API_TOKEN via method:
       export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
-       cd GenAIExamples/DocSum/kubernetes/intel/cpu/xeon/manifests/ui/
+       cd GenAIExamples/DocSum/kubernetes/intel/cpu/xeon/manifest/ui/
       sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-docsum.yaml
       ```
    b. Set the proxies based on your network configuration
--- a/FaqGen/kubernetes/intel/README.md
+++ b/FaqGen/kubernetes/intel/README.md
@@ -17,7 +17,7 @@ If use gated models, you also need to provide [huggingface token](https://huggin
 ## Deploy On Xeon

 ```
-cd GenAIExamples/FaqGen/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/FaqGen/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqgen.yaml
 kubectl apply -f faqgen.yaml
@@ -26,7 +26,7 @@ kubectl apply -f faqgen.yaml
 ## Deploy On Gaudi

 ```
-cd GenAIExamples/FaqGen/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/FaqGen/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqgen.yaml
 kubectl apply -f faqgen.yaml
--- a/FaqGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md
+++ b/FaqGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md
@@ -16,7 +16,7 @@ Before deploying the react-faqgen.yaml file, ensure that you have the following
       ```
       # You may set the HUGGINGFACEHUB_API_TOKEN via method:
       export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
-       cd GenAIExamples/FaqGen/kubernetes/intel/cpu/xeon/manifests/ui/
+       cd GenAIExamples/FaqGen/kubernetes/intel/cpu/xeon/manifest/ui/
       sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-faqgen.yaml
       ```
    b. Set the proxies based on your network configuration
--- a/ProductivitySuite/kubernetes/intel/README.md
+++ b/ProductivitySuite/kubernetes/intel/README.md
@@ -76,7 +76,7 @@ To begin with, ensure that you have following prerequisites in place:
 ##  🌐 Deploying ProductivitySuite
 You can use yaml files in xeon folder to deploy ProductivitySuite with reactUI.
 ```
-cd GenAIExamples/ProductivitySuite/kubernetes/intel/cpu/xeon/manifests/
+cd GenAIExamples/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/
 kubectl apply -f .
 ```

--- a/Translation/kubernetes/intel/README.md
+++ b/Translation/kubernetes/intel/README.md
@@ -11,7 +11,7 @@
 ## Deploy On Xeon

 ```
-cd GenAIExamples/Translation/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/Translation/kubernetes/intel/cpu/xeon/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml
 kubectl apply -f translation.yaml
@@ -20,7 +20,7 @@ kubectl apply -f translation.yaml
 ## Deploy On Gaudi

 ```
-cd GenAIExamples/Translation/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/Translation/kubernetes/intel/hpu/gaudi/manifest
 export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
 sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml
 kubectl apply -f translation.yaml
--- a/VisualQnA/kubernetes/intel/README.md
+++ b/VisualQnA/kubernetes/intel/README.md
@@ -8,14 +8,14 @@
 ## Deploy On Xeon

 ```
-cd GenAIExamples/visualqna/kubernetes/intel/cpu/xeon/manifests
+cd GenAIExamples/visualqna/kubernetes/intel/cpu/xeon/manifest
 kubectl apply -f visualqna.yaml
 ```

 ## Deploy On Gaudi

 ```
-cd GenAIExamples/visualqna/kubernetes/intel/hpu/gaudi/manifests
+cd GenAIExamples/visualqna/kubernetes/intel/hpu/gaudi/manifest
 kubectl apply -f visualqna.yaml
 ```