jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

Fix ChatQnA manifest default port issue (#1033)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
lvliang-intel
2024-10-30 11:52:04 +08:00
committed by GitHub
parent 960805a57b
commit 7197286a14
18 changed files with 20 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
AudioQnA/kubernetes/intel/README.md
View File

@@ -7,14 +7,14 @@
## Deploy On Xeon ## Deploy On Xeon
``` ```
cd GenAIExamples/AudioQnA/kubernetes/intel/cpu/xeon/manifests cd GenAIExamples/AudioQnA/kubernetes/intel/cpu/xeon/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml
kubectl apply -f audioqna.yaml kubectl apply -f audioqna.yaml
``` ```
## Deploy On Gaudi ## Deploy On Gaudi
``` ```
cd GenAIExamples/AudioQnA/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/AudioQnA/kubernetes/intel/hpu/gaudi/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" audioqna.yaml
kubectl apply -f audioqna.yaml kubectl apply -f audioqna.yaml

6
ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml
View File

@@ -1252,18 +1252,12 @@ spec:
env: env:
- name: LLM_SERVER_HOST_IP - name: LLM_SERVER_HOST_IP
value: chatqna-tgi value: chatqna-tgi
- name: LLM_SERVER_PORT
value: "2080"
- name: RERANK_SERVER_HOST_IP - name: RERANK_SERVER_HOST_IP
value: chatqna-teirerank value: chatqna-teirerank
- name: RERANK_SERVER_PORT
value: "2082"
- name: RETRIEVER_SERVICE_HOST_IP - name: RETRIEVER_SERVICE_HOST_IP
value: chatqna-retriever-usvc value: chatqna-retriever-usvc
- name: EMBEDDING_SERVER_HOST_IP - name: EMBEDDING_SERVER_HOST_IP
value: chatqna-tei value: chatqna-tei
- name: EMBEDDING_SERVER_PORT
value: "2081"
- name: GUARDRAIL_SERVICE_HOST_IP - name: GUARDRAIL_SERVICE_HOST_IP
value: chatqna-guardrails-usvc value: chatqna-guardrails-usvc
- name: GUARDRAIL_SERVICE_PORT - name: GUARDRAIL_SERVICE_PORT

6
ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml
View File

@@ -994,18 +994,12 @@ spec:
env: env:
- name: LLM_SERVER_HOST_IP - name: LLM_SERVER_HOST_IP
value: chatqna-tgi value: chatqna-tgi
- name: LLM_SERVER_PORT
value: "2080"
- name: RERANK_SERVER_HOST_IP - name: RERANK_SERVER_HOST_IP
value: chatqna-teirerank value: chatqna-teirerank
- name: RERANK_SERVER_PORT
value: "2082"
- name: RETRIEVER_SERVICE_HOST_IP - name: RETRIEVER_SERVICE_HOST_IP
value: chatqna-retriever-usvc value: chatqna-retriever-usvc
- name: EMBEDDING_SERVER_HOST_IP - name: EMBEDDING_SERVER_HOST_IP
value: chatqna-tei value: chatqna-tei
- name: EMBEDDING_SERVER_PORT
value: "2081"
securityContext: securityContext:
allowPrivilegeEscalation: false allowPrivilegeEscalation: false
capabilities: capabilities:

6
ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna_bf16.yaml
View File

@@ -997,18 +997,12 @@ spec:
env: env:
- name: LLM_SERVER_HOST_IP - name: LLM_SERVER_HOST_IP
value: chatqna-tgi value: chatqna-tgi
- name: LLM_SERVER_PORT
value: "2080"
- name: RERANK_SERVER_HOST_IP - name: RERANK_SERVER_HOST_IP
value: chatqna-teirerank value: chatqna-teirerank
- name: RERANK_SERVER_PORT
value: "2082"
- name: RETRIEVER_SERVICE_HOST_IP - name: RETRIEVER_SERVICE_HOST_IP
value: chatqna-retriever-usvc value: chatqna-retriever-usvc
- name: EMBEDDING_SERVER_HOST_IP - name: EMBEDDING_SERVER_HOST_IP
value: chatqna-tei value: chatqna-tei
- name: EMBEDDING_SERVER_PORT
value: "2081"
securityContext: securityContext:
allowPrivilegeEscalation: false allowPrivilegeEscalation: false
capabilities: capabilities:

6
ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-guardrails.yaml
View File

@@ -1257,18 +1257,12 @@ spec:
env: env:
- name: LLM_SERVER_HOST_IP - name: LLM_SERVER_HOST_IP
value: chatqna-tgi value: chatqna-tgi
- name: LLM_SERVER_PORT
value: "2080"
- name: RERANK_SERVER_HOST_IP - name: RERANK_SERVER_HOST_IP
value: chatqna-teirerank value: chatqna-teirerank
- name: RERANK_SERVER_PORT
value: "2082"
- name: RETRIEVER_SERVICE_HOST_IP - name: RETRIEVER_SERVICE_HOST_IP
value: chatqna-retriever-usvc value: chatqna-retriever-usvc
- name: EMBEDDING_SERVER_HOST_IP - name: EMBEDDING_SERVER_HOST_IP
value: chatqna-tei value: chatqna-tei
- name: EMBEDDING_SERVER_PORT
value: "2081"
- name: GUARDRAIL_SERVICE_HOST_IP - name: GUARDRAIL_SERVICE_HOST_IP
value: chatqna-guardrails-usvc value: chatqna-guardrails-usvc
- name: GUARDRAIL_SERVICE_PORT - name: GUARDRAIL_SERVICE_PORT

6
ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna.yaml
View File

@@ -997,18 +997,12 @@ spec:
env: env:
- name: LLM_SERVER_HOST_IP - name: LLM_SERVER_HOST_IP
value: chatqna-tgi value: chatqna-tgi
- name: LLM_SERVER_PORT
value: "2080"
- name: RERANK_SERVER_HOST_IP - name: RERANK_SERVER_HOST_IP
value: chatqna-teirerank value: chatqna-teirerank
- name: RERANK_SERVER_PORT
value: "2082"
- name: RETRIEVER_SERVICE_HOST_IP - name: RETRIEVER_SERVICE_HOST_IP
value: chatqna-retriever-usvc value: chatqna-retriever-usvc
- name: EMBEDDING_SERVER_HOST_IP - name: EMBEDDING_SERVER_HOST_IP
value: chatqna-tei value: chatqna-tei
- name: EMBEDDING_SERVER_PORT
value: "2081"
securityContext: securityContext:
allowPrivilegeEscalation: false allowPrivilegeEscalation: false
capabilities: capabilities:

2
ChatQnA/tests/test_manifest_on_gaudi.sh
View File

@@ -161,7 +161,7 @@ case "$1" in
if [ $ret -ne 0 ]; then if [ $ret -ne 0 ]; then
exit $ret exit $ret
fi fi
pushd ChatQnA/kubernetes/intel/hpu/gaudi/manifests pushd ChatQnA/kubernetes/intel/hpu/gaudi/manifest
set +e set +e
install_and_validate_chatqna_guardrail install_and_validate_chatqna_guardrail
popd popd

2
ChatQnA/tests/test_manifest_on_xeon.sh
View File

@@ -161,7 +161,7 @@ case "$1" in
if [ $ret -ne 0 ]; then if [ $ret -ne 0 ]; then
exit $ret exit $ret
fi fi
pushd ChatQnA/kubernetes/intel/cpu/xeon/manifests pushd ChatQnA/kubernetes/intel/cpu/xeon/manifest
set +e set +e
install_and_validate_chatqna_guardrail install_and_validate_chatqna_guardrail
popd popd

4
CodeGen/kubernetes/intel/README.md
View File

@@ -12,7 +12,7 @@
## Deploy On Xeon ## 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 HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
export MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct" export MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
@@ -23,7 +23,7 @@ kubectl apply -f codegen.yaml
## Deploy On Gaudi ## Deploy On Gaudi
``` ```
cd GenAIExamples/CodeGen/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/CodeGen/kubernetes/intel/hpu/gaudi/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml
kubectl apply -f codegen.yaml kubectl apply -f codegen.yaml

2
CodeGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md
View File

@@ -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: # You may set the HUGGINGFACEHUB_API_TOKEN via method:
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" 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/${HUGGINGFACEHUB_API_TOKEN}/g" react-codegen.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-codegen.yaml
``` ```
b. Set the proxies based on your network configuration b. Set the proxies based on your network configuration

4
CodeTrans/kubernetes/intel/README.md
View File

@@ -21,7 +21,7 @@ Change the `MODEL_ID` in `codetrans.yaml` for your needs.
## Deploy On Xeon ## Deploy On Xeon
```bash ```bash
cd GenAIExamples/CodeTrans/kubernetes/intel/cpu/xeon/manifests cd GenAIExamples/CodeTrans/kubernetes/intel/cpu/xeon/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codetrans.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codetrans.yaml
kubectl apply -f codetrans.yaml kubectl apply -f codetrans.yaml
@@ -30,7 +30,7 @@ kubectl apply -f codetrans.yaml
## Deploy On Gaudi ## Deploy On Gaudi
```bash ```bash
cd GenAIExamples/CodeTrans/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/CodeTrans/kubernetes/intel/hpu/gaudi/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codetrans.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codetrans.yaml
kubectl apply -f codetrans.yaml kubectl apply -f codetrans.yaml

4
DocSum/kubernetes/intel/README.md
View File

@@ -11,7 +11,7 @@
## Deploy On Xeon ## Deploy On Xeon
``` ```
cd GenAIExamples/DocSum/kubernetes/intel/cpu/xeon/manifests cd GenAIExamples/DocSum/kubernetes/intel/cpu/xeon/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" docsum.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" docsum.yaml
kubectl apply -f docsum.yaml kubectl apply -f docsum.yaml
@@ -20,7 +20,7 @@ kubectl apply -f docsum.yaml
## Deploy On Gaudi ## Deploy On Gaudi
``` ```
cd GenAIExamples/DocSum/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/DocSum/kubernetes/intel/hpu/gaudi/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" docsum.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" docsum.yaml
kubectl apply -f docsum.yaml kubectl apply -f docsum.yaml

2
DocSum/kubernetes/intel/cpu/xeon/manifest/ui/README.md
View File

@@ -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: # You may set the HUGGINGFACEHUB_API_TOKEN via method:
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" 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/${HUGGINGFACEHUB_API_TOKEN}/g" react-docsum.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-docsum.yaml
``` ```
b. Set the proxies based on your network configuration b. Set the proxies based on your network configuration

4
FaqGen/kubernetes/intel/README.md
View File

@@ -17,7 +17,7 @@ If use gated models, you also need to provide [huggingface token](https://huggin
## Deploy On Xeon ## Deploy On Xeon
``` ```
cd GenAIExamples/FaqGen/kubernetes/intel/cpu/xeon/manifests cd GenAIExamples/FaqGen/kubernetes/intel/cpu/xeon/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqgen.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqgen.yaml
kubectl apply -f faqgen.yaml kubectl apply -f faqgen.yaml
@@ -26,7 +26,7 @@ kubectl apply -f faqgen.yaml
## Deploy On Gaudi ## Deploy On Gaudi
``` ```
cd GenAIExamples/FaqGen/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/FaqGen/kubernetes/intel/hpu/gaudi/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqgen.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqgen.yaml
kubectl apply -f faqgen.yaml kubectl apply -f faqgen.yaml

2
FaqGen/kubernetes/intel/cpu/xeon/manifest/README_react_ui.md
View File

@@ -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: # You may set the HUGGINGFACEHUB_API_TOKEN via method:
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" 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/${HUGGINGFACEHUB_API_TOKEN}/g" react-faqgen.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" react-faqgen.yaml
``` ```
b. Set the proxies based on your network configuration b. Set the proxies based on your network configuration

2
ProductivitySuite/kubernetes/intel/README.md
View File

@@ -76,7 +76,7 @@ To begin with, ensure that you have following prerequisites in place:
## 🌐 Deploying ProductivitySuite ## 🌐 Deploying ProductivitySuite
You can use yaml files in xeon folder to deploy ProductivitySuite with reactUI. 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 . kubectl apply -f .
``` ```

4
Translation/kubernetes/intel/README.md
View File

@@ -11,7 +11,7 @@
## Deploy On Xeon ## Deploy On Xeon
``` ```
cd GenAIExamples/Translation/kubernetes/intel/cpu/xeon/manifests cd GenAIExamples/Translation/kubernetes/intel/cpu/xeon/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml
kubectl apply -f translation.yaml kubectl apply -f translation.yaml
@@ -20,7 +20,7 @@ kubectl apply -f translation.yaml
## Deploy On Gaudi ## Deploy On Gaudi
``` ```
cd GenAIExamples/Translation/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/Translation/kubernetes/intel/hpu/gaudi/manifest
export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" export HUGGINGFACEHUB_API_TOKEN="YourOwnToken"
sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" translation.yaml
kubectl apply -f translation.yaml kubectl apply -f translation.yaml

4
VisualQnA/kubernetes/intel/README.md
View File

@@ -8,14 +8,14 @@
## Deploy On Xeon ## Deploy On Xeon
``` ```
cd GenAIExamples/visualqna/kubernetes/intel/cpu/xeon/manifests cd GenAIExamples/visualqna/kubernetes/intel/cpu/xeon/manifest
kubectl apply -f visualqna.yaml kubectl apply -f visualqna.yaml
``` ```
## Deploy On Gaudi ## Deploy On Gaudi
``` ```
cd GenAIExamples/visualqna/kubernetes/intel/hpu/gaudi/manifests cd GenAIExamples/visualqna/kubernetes/intel/hpu/gaudi/manifest
kubectl apply -f visualqna.yaml kubectl apply -f visualqna.yaml
``` ```