Update all examples yaml files of GMC in GenAIExample (#436)

* Update all examples yaml files of GMC in GenAIExample.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

ChatQnA/kubernetes/chatQnA_gaudi.yaml

@@ -23,6 +23,7 @@ spec:
           serviceName: embedding-svc
           config:
             endpoint: /v1/embeddings
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc
       - name: TeiEmbeddingGaudi
         internalService:
           serviceName: tei-embedding-gaudi-svc
@@ -33,6 +34,8 @@ spec:
           serviceName: retriever-svc
           config:
             endpoint: /v1/retrieval
+            REDIS_URL: redis-vector-db
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc
       - name: VectorDB
         internalService:
           serviceName: redis-vector-db
@@ -43,6 +46,7 @@ spec:
           serviceName: reranking-svc
           config:
             endpoint: /v1/reranking
+            TEI_RERANKING_ENDPOINT: tei-reranking-svc
       - name: TeiReranking
         internalService:
           serviceName: tei-reranking-svc
@@ -55,6 +59,7 @@ spec:
           serviceName: llm-svc
           config:
             endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-gaudi-svc
       - name: TgiGaudi
         internalService:
           serviceName: tgi-gaudi-svc

ChatQnA/kubernetes/chatQnA_switch_gaudi.yaml

@@ -0,0 +1,124 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: gmc.opea.io/v1alpha3
+kind: GMConnector
+metadata:
+  labels:
+    app.kubernetes.io/name: gmconnector
+    app.kubernetes.io/managed-by: kustomize
+    gmc/platform: gaudi
+  name: switch
+  namespace: switch
+spec:
+  routerConfig:
+    name: router
+    serviceName: router-service
+  nodes:
+    root:
+      routerType: Sequence
+      steps:
+      - name: Embedding
+        nodeName: node1
+      - name: Reranking
+        data: $response
+        internalService:
+          serviceName: reranking-svc
+          config:
+            endpoint: /v1/reranking
+            TEI_RERANKING_ENDPOINT: tei-reranking-svc
+      - name: TeiReranking
+        internalService:
+          serviceName: tei-reranking-svc
+          config:
+            endpoint: /rerank
+          isDownstreamService: true
+      - name: Llm
+        data: $response
+        nodeName: node2
+    node1:
+      routerType: Switch
+      steps:
+        - name: Embedding
+          condition: embedding-model-id==large
+          internalService:
+            serviceName: embedding-svc-large
+            config:
+              endpoint: /v1/embeddings
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc-bge15
+        - name: Embedding
+          condition: embedding-model-id==small
+          internalService:
+            serviceName: embedding-svc-small
+            config:
+              endpoint: /v1/embeddings
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc-bge-small
+        - name: TeiEmbeddingGaudi
+          internalService:
+            serviceName: tei-embedding-gaudi-svc-bge15
+            config:
+              MODEL_ID: BAAI/bge-base-en-v1.5
+            isDownstreamService: true
+        - name: TeiEmbeddingGaudi
+          internalService:
+            serviceName: tei-embedding-gaudi-svc-bge-small
+            config:
+              MODEL_ID: BAAI/bge-base-en-v1.5
+            isDownstreamService: true
+        - name: Retriever
+          condition: embedding-model-id==large
+          data: $response
+          internalService:
+            serviceName: retriever-svc-large
+            config:
+              endpoint: /v1/retrieval
+              REDIS_URL: redis-vector-db-large
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc-bge15
+        - name: Retriever
+          condition: embedding-model-id==small
+          data: $response
+          internalService:
+            serviceName: retriever-svc-small
+            config:
+              endpoint: /v1/retrieval
+              REDIS_URL: redis-vector-db-small
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc-bge-small
+        - name: VectorDB
+          internalService:
+            serviceName: redis-vector-db-large
+            isDownstreamService: true
+        - name: VectorDB
+          internalService:
+            serviceName: redis-vector-db-small
+            isDownstreamService: true
+    node2:
+      routerType: Switch
+      steps:
+        - name: Llm
+          condition: model-id==intel
+          internalService:
+            serviceName: llm-svc-intel
+            config:
+              endpoint: /v1/chat/completions
+              TGI_LLM_ENDPOINT: tgi-gaudi-service-intel
+        - name: Llm
+          condition: model-id==llama
+          internalService:
+            serviceName: llm-svc-llama
+            config:
+              endpoint: /v1/chat/completions
+              TGI_LLM_ENDPOINT: tgi-gaudi-service-llama
+        - name: TgiGaudi
+          internalService:
+            serviceName: tgi-gaudi-service-intel
+            config:
+              endpoint: /generate
+              MODEL_ID: Intel/neural-chat-7b-v3-3
+            isDownstreamService: true
+        - name: TgiGaudi
+          internalService:
+            serviceName: tgi-gaudi-service-llama
+            config:
+              endpoint: /generate
+              MODEL_ID: openlm-research/open_llama_3b
+            isDownstreamService: true

ChatQnA/kubernetes/chatQnA_switch_xeon.yaml

@@ -0,0 +1,124 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: gmc.opea.io/v1alpha3
+kind: GMConnector
+metadata:
+  labels:
+    app.kubernetes.io/name: gmconnector
+    app.kubernetes.io/managed-by: kustomize
+    gmc/platform: xeon
+  name: switch
+  namespace: switch
+spec:
+  routerConfig:
+    name: router
+    serviceName: router-service
+  nodes:
+    root:
+      routerType: Sequence
+      steps:
+      - name: Embedding
+        nodeName: node1
+      - name: Reranking
+        data: $response
+        internalService:
+          serviceName: reranking-svc
+          config:
+            endpoint: /v1/reranking
+            TEI_RERANKING_ENDPOINT: tei-reranking-svc
+      - name: TeiReranking
+        internalService:
+          serviceName: tei-reranking-svc
+          config:
+            endpoint: /rerank
+          isDownstreamService: true
+      - name: Llm
+        data: $response
+        nodeName: node2
+    node1:
+      routerType: Switch
+      steps:
+        - name: Embedding
+          condition: embedding-model-id==large
+          internalService:
+            serviceName: embedding-svc-large
+            config:
+              endpoint: /v1/embeddings
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-svc-bge15
+        - name: Embedding
+          condition: embedding-model-id==small
+          internalService:
+            serviceName: embedding-svc-small
+            config:
+              endpoint: /v1/embeddings
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-svc-bge-small
+        - name: TeiEmbedding
+          internalService:
+            serviceName: tei-embedding-svc-bge15
+            config:
+              MODEL_ID: BAAI/bge-base-en-v1.5
+            isDownstreamService: true
+        - name: TeiEmbedding
+          internalService:
+            serviceName: tei-embedding-svc-bge-small
+            config:
+              MODEL_ID: BAAI/bge-base-en-v1.5
+            isDownstreamService: true
+        - name: Retriever
+          condition: embedding-model-id==large
+          data: $response
+          internalService:
+            serviceName: retriever-svc-large
+            config:
+              endpoint: /v1/retrieval
+              REDIS_URL: redis-vector-db-large
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-svc-bge15
+        - name: Retriever
+          condition: embedding-model-id==small
+          data: $response
+          internalService:
+            serviceName: retriever-svc-small
+            config:
+              endpoint: /v1/retrieval
+              REDIS_URL: redis-vector-db-small
+              TEI_EMBEDDING_ENDPOINT: tei-embedding-svc-bge-small
+        - name: VectorDB
+          internalService:
+            serviceName: redis-vector-db-large
+            isDownstreamService: true
+        - name: VectorDB
+          internalService:
+            serviceName: redis-vector-db-small
+            isDownstreamService: true
+    node2:
+      routerType: Switch
+      steps:
+        - name: Llm
+          condition: model-id==intel
+          internalService:
+            serviceName: llm-svc-intel
+            config:
+              endpoint: /v1/chat/completions
+              TGI_LLM_ENDPOINT: tgi-service-intel
+        - name: Llm
+          condition: model-id==llama
+          internalService:
+            serviceName: llm-svc-llama
+            config:
+              endpoint: /v1/chat/completions
+              TGI_LLM_ENDPOINT: tgi-service-llama
+        - name: Tgi
+          internalService:
+            serviceName: tgi-service-intel
+            config:
+              endpoint: /generate
+              MODEL_ID: Intel/neural-chat-7b-v3-3
+            isDownstreamService: true
+        - name: Tgi
+          internalService:
+            serviceName: tgi-service-llama
+            config:
+              endpoint: /generate
+              MODEL_ID: bigscience/bloom-560m
+            isDownstreamService: true

ChatQnA/kubernetes/chatQnA_xeon.yaml

@@ -23,6 +23,7 @@ spec:
           serviceName: embedding-svc
           config:
             endpoint: /v1/embeddings
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-svc
       - name: TeiEmbedding
         internalService:
           serviceName: tei-embedding-svc
@@ -33,6 +34,8 @@ spec:
           serviceName: retriever-svc
           config:
             endpoint: /v1/retrieval
+            REDIS_URL: redis-vector-db
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-svc
       - name: VectorDB
         internalService:
           serviceName: redis-vector-db
@@ -43,6 +46,7 @@ spec:
           serviceName: reranking-svc
           config:
             endpoint: /v1/reranking
+            TEI_RERANKING_ENDPOINT: tei-reranking-svc
       - name: TeiReranking
         internalService:
           serviceName: tei-reranking-svc
@@ -55,6 +59,7 @@ spec:
           serviceName: llm-svc
           config:
             endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-service-m
       - name: Tgi
         internalService:
           serviceName: tgi-service-m

ChatQnA/tests/test_gmc_on_gaudi.sh

@@ -64,7 +64,7 @@ function validate_chatqna() {
    echo "Checking response results, make sure the output is reasonable. "
    local status=false
    if [[ -f $LOG_PATH/curl_chatqna.log ]] && \
-   [[ $(grep -c "billion" $LOG_PATH/curl_chatqna.log) != 0 ]]; then
+   [[ $(grep -c "[DONE]" $LOG_PATH/curl_chatqna.log) != 0 ]]; then
        status=true
    fi
    if [ $status == false ]; then

ChatQnA/tests/test_gmc_on_xeon.sh

@@ -65,7 +65,7 @@ function validate_chatqna() {
    echo "Checking response results, make sure the output is reasonable. "
    local status=false
    if [[ -f $LOG_PATH/curl_chatqna.log ]] && \
-   [[ $(grep -c "billion" $LOG_PATH/curl_chatqna.log) != 0 ]]; then
+   [[ $(grep -c "[DONE]" $LOG_PATH/curl_chatqna.log) != 0 ]]; then
        status=true
    fi
    if [ $status == false ]; then

CodeGen/kubernetes/README.md

@@ -0,0 +1,40 @@
+<h1 align="center" id="title">Deploy CodeGen in a Kubernetes Cluster</h1>
+
+This document outlines the deployment process for a Code Generation (CodeGen) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
+
+Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+
+If you have only Intel Xeon machines you could use the codegen_xeon.yaml file or if you have a Gaudi cluster you could use codegen_gaudi.yaml
+In the below example we illustrate on Xeon.
+
+## Deploy the RAG application
+
+1. Create the desired namespace if it does not already exist and deploy the application
+```bash
+export APP_NAMESPACE=CT
+kubectl create ns $APP_NAMESPACE
+sed -i "s|namespace: codegen|namespace: $APP_NAMESPACE|g"  ./codegen_xeon.yaml
+kubectl apply -f ./codegen_xeon.yaml
+```
+
+2. Check if the application is up and ready
+```bash
+kubectl get pods -n $APP_NAMESPACE
+```
+
+3. Deploy a client pod for testing
+```bash
+kubectl create deployment client-test -n $APP_NAMESPACE --image=python:3.8.13 -- sleep infinity
+```
+
+4. Check that client pod is ready
+```bash
+    kubectl get pods -n $APP_NAMESPACE
+```
+
+5. Send request to application
+```bash
+export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
+export accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='codegen')].status.accessUrl}")
+kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -X POST -d '{"query": "def print_hello_world():"}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_codegen.log
+```

CodeGen/kubernetes/codegen_gaudi.yaml

@@ -24,10 +24,11 @@ spec:
           serviceName: llm-service
           config:
             endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-gaudi-svc
       - name: TgiGaudi
         internalService:
           serviceName: tgi-gaudi-svc
           config:
-            LLM_MODEL_ID: ise-uiuc/Magicoder-S-DS-6.7B
+            MODEL_ID: ise-uiuc/Magicoder-S-DS-6.7B
             endpoint: /generate
           isDownstreamService: true

CodeGen/kubernetes/codegen_xeon.yaml

@@ -24,10 +24,11 @@ spec:
           serviceName: llm-service
           config:
             endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-service
       - name: Tgi
         internalService:
           serviceName: tgi-service
           config:
-            LLM_MODEL_ID: ise-uiuc/Magicoder-S-DS-6.7B
+            MODEL_ID: ise-uiuc/Magicoder-S-DS-6.7B
             endpoint: /generate
           isDownstreamService: true

CodeGen/tests/test_gmc_on_gaudi.sh

@@ -44,7 +44,7 @@ function validate_codegen() {
     echo "Checking response results, make sure the output is reasonable. "
     local status=false
     if [[ -f $LOG_PATH/gmc_codegen.log ]] && \
-    [[ $(grep -c "print" $LOG_PATH/gmc_codegen.log) != 0 ]]; then
+    [[ $(grep -c "[DONE]" $LOG_PATH/gmc_codegen.log) != 0 ]]; then
         status=true
     fi
     if [ $status == false ]; then

CodeGen/tests/test_gmc_on_xeon.sh

@@ -44,7 +44,7 @@ function validate_codegen() {
     echo "Checking response results, make sure the output is reasonable. "
     local status=false
     if [[ -f $LOG_PATH/gmc_codegen.log ]] && \
-    [[ $(grep -c "print" $LOG_PATH/gmc_codegen.log) != 0 ]]; then
+    [[ $(grep -c "[DONE]" $LOG_PATH/gmc_codegen.log) != 0 ]]; then
         status=true
     fi
     if [ $status == false ]; then

CodeTrans/kubernetes/codetrans_gaudi.yaml

@@ -24,10 +24,11 @@ spec:
           serviceName: codetrans-service
           config:
             endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-gaudi-svc
       - name: TgiGaudi
         internalService:
           serviceName: tgi-gaudi-svc
           config:
-            LLM_MODEL_ID: HuggingFaceH4/mistral-7b-grok
+            MODEL_ID: HuggingFaceH4/mistral-7b-grok
             endpoint: /generate
           isDownstreamService: true

CodeTrans/kubernetes/codetrans_xeon.yaml

@@ -24,10 +24,11 @@ spec:
           serviceName: codetrans-service
           config:
             endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-service
       - name: Tgi
         internalService:
           serviceName: tgi-service
           config:
-            LLM_MODEL_ID: HuggingFaceH4/mistral-7b-grok
+            MODEL_ID: HuggingFaceH4/mistral-7b-grok
             endpoint: /generate
           isDownstreamService: true

DocSum/kubernetes/docsum_gaudi.yaml

@@ -18,13 +18,14 @@ spec:
     root:
       routerType: Sequence
       steps:
-      - name: DocSumGaudi
+      - name: DocSum
         data: $response
         internalService:
           serviceName: docsum-llm-uservice
           config:
             endpoint: /v1/chat/docsum
             PORT: "9009"
+            TGI_LLM_ENDPOINT: tgi-gaudi-svc
       - name: TgiGaudi
         internalService:
           serviceName: tgi-gaudi-svc

DocSum/kubernetes/docsum_xeon.yaml

@@ -25,6 +25,7 @@ spec:
           config:
             endpoint: /v1/chat/docsum
             PORT: "9009"
+            TGI_LLM_ENDPOINT: tgi-svc
       - name: Tgi
         internalService:
           serviceName: tgi-svc