Updated SearchQnA to use nginx like ChatQnA (#1769)

edlee123 · web-flow · commit e9153b82bbf4 · 2025-05-20T14:15:46.000+08:00
Signed-off-by: Ed Lee &lt;16417837+edlee123@users.noreply.github.com&gt;
diff --git a/SearchQnA/README.md b/SearchQnA/README.md
@@ -30,66 +30,38 @@ The architecture of the SearchQnA Application is illustrated below:
 The SearchQnA example is implemented using the component-level microservices defined in [GenAIComps](https://github.com/opea-project/GenAIComps). The flow chart below shows the information flow between different microservices for this example.
 
 ```mermaid
----
-config:
-  flowchart:
-    nodeSpacing: 400
-    rankSpacing: 100
-    curve: linear
-  themeVariables:
-    fontSize: 50px
----
+%% Orange are microservices from third parties that are 'wrapped' as OPEA components.
 flowchart LR
-    %% Colors %%
-    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef invisible fill:transparent,stroke:transparent;
-    style SearchQnA-MegaService stroke:#000000
-
-    %% Subgraphs %%
-    subgraph SearchQnA-MegaService["SearchQnA MegaService "]
-        direction LR
-        EM([Embedding MicroService]):::blue
-        RET([Web Retrieval MicroService]):::blue
-        RER([Rerank MicroService]):::blue
-        LLM([LLM MicroService]):::blue
-    end
-    subgraph UserInterface[" User Interface "]
-        direction LR
-        a([User Input Query]):::orchid
-        UI([UI server<br>]):::orchid
-    end
-
-
-
-    TEI_RER{{Reranking service<br>}}
-    TEI_EM{{Embedding service <br>}}
-    VDB{{Vector DB<br><br>}}
-    R_RET{{Web Retriever service <br>}}
-    LLM_gen{{LLM Service <br>}}
-    GW([SearchQnA GateWay<br>]):::orange
-
-    %% Questions interaction
-    direction LR
-    a[User Input Query] --> UI
-    UI --> GW
-    GW <==> SearchQnA-MegaService
-    EM ==> RET
-    RET ==> RER
-    RER ==> LLM
-
-    %% Embedding service flow
-    direction LR
-    EM <-.-> TEI_EM
-    RET <-.-> R_RET
-    RER <-.-> TEI_RER
-    LLM <-.-> LLM_gen
-
+    User["User"] --> Nginx["Nginx<br>searchqna-nginx-server"]
+    Nginx --> UI["UI<br>searchqna-ui-server"] & Gateway & User
+    UI --> Nginx
+    Gateway --> Nginx & Embedding
+    Embedding --> Retriever
+    Retriever --> Reranker
+    Reranker --> LLM
+    LLM --> Gateway
+    LLM <-.-> TGI_Service["LLM<br>tgi-service"]
+    Embedding <-.-> TEI_Embedding["TEI Embedding<br>tei-embedding-server"]
+    Reranker <-.-> TEI_Reranker["TEI Reranker<br>tei-reranking-server"]
+
+     TEI_Embedding:::ext
+     TEI_Reranker:::ext
+     TGI_Service:::ext
+
+ subgraph MegaService["MegaService"]
+        LLM["LLM<br>llm-textgen-server"]
+        Reranker["Reranker<br>reranking-tei-server"]
+        Retriever["Retriever<br>web-retriever-server"]
+        Embedding["Embedding<br>embedding-server"]
+  end
+ subgraph Backend["searchqna-backend-server"]
     direction TB
-    %% Vector DB interaction
-    R_RET <-.-> VDB
-
+        MegaService
+        Gateway["Backend Endpoint"]
+ end
+    classDef default fill:#fff,stroke:#000,color:#000
+    classDef ext fill:#f9cb9c,stroke:#000,color:#000
+    style MegaService margin-top:20px,margin-bottom:20px
 ```
 
 This SearchQnA use case performs Search-augmented Question Answering across multiple platforms. Currently, we provide the example for Intel® Gaudi® 2 and Intel® Xeon® Scalable Processors, and we invite contributions from other hardware vendors to expand OPEA ecosystem.
@@ -98,8 +70,8 @@ This SearchQnA use case performs Search-augmented Question Answering across mult
 
 The table below lists the available deployment options and their implementation details for different hardware platforms.
 
-| Category               | Deployment Option      | Description                                                    |
-| ---------------------- | ---------------------- | -------------------------------------------------------------- |
-| On-premise Deployments | Docker Compose (Xeon)  | [DocSum deployment on Xeon](./docker_compose/intel/cpu/xeon)   |
-|                        | Docker Compose (Gaudi) | [DocSum deployment on Gaudi](./docker_compose/intel/hpu/gaudi) |
-|                        | Docker Compose (ROCm)  | [DocSum deployment on AMD ROCm](./docker_compose/amd/gpu/rocm) |
+| Category               | Deployment Option      | Description                                                                 |
+| ---------------------- | ---------------------- | --------------------------------------------------------------------------- |
+| On-premise Deployments | Docker Compose (Xeon)  | [SearchQnA deployment on Xeon](./docker_compose/intel/cpu/xeon/README.md)   |
+|                        | Docker Compose (Gaudi) | [SearchQnA deployment on Gaudi](./docker_compose/intel/hpu/gaudi/README.md) |
+|                        | Docker Compose (ROCm)  | [SearchQnA deployment on AMD ROCm](./docker_compose/amd/gpu/rocm/README.md) |
diff --git a/SearchQnA/docker_compose/amd/gpu/rocm/compose.yaml b/SearchQnA/docker_compose/amd/gpu/rocm/compose.yaml
@@ -170,7 +170,25 @@ services:
       no_proxy: ${no_proxy}
       https_proxy: ${https_proxy}
       http_proxy: ${http_proxy}
-      BACKEND_BASE_URL: ${SEARCH_BACKEND_SERVICE_ENDPOINT}
+    ipc: host
+    restart: always
+  search-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: search-nginx-server
+    depends_on:
+      - search-backend-server
+      - search-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=search-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=search
+      - BACKEND_SERVICE_IP=search-backend-server
+      - BACKEND_SERVICE_PORT=8888
     ipc: host
     restart: always
 
diff --git a/SearchQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml b/SearchQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml
@@ -176,10 +176,27 @@ services:
       no_proxy: ${no_proxy}
       https_proxy: ${https_proxy}
       http_proxy: ${http_proxy}
-      BACKEND_BASE_URL: ${SEARCH_BACKEND_SERVICE_ENDPOINT}
     ipc: host
     restart: always
-
+  search-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: search-nginx-server
+    depends_on:
+      - search-backend-server
+      - search-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=search-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=search
+      - BACKEND_SERVICE_IP=search-backend-server
+      - BACKEND_SERVICE_PORT=8888
+    ipc: host
+    restart: always
 networks:
   default:
     driver: bridge
diff --git a/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml b/SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -168,10 +168,27 @@ services:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
-      - BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
     ipc: host
     restart: always
-
+  searchqna-xeon-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: searchqna-xeon-nginx-server
+    depends_on:
+      - searchqna-xeon-backend-server
+      - searchqna-xeon-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=searchqna-xeon-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=searchqna
+      - BACKEND_SERVICE_IP=searchqna-xeon-backend-server
+      - BACKEND_SERVICE_PORT=8888
+    ipc: host
+    restart: always
 
 networks:
   default:
diff --git a/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -187,7 +187,25 @@ services:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
       - http_proxy=${http_proxy}
-      - BACKEND_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
+    ipc: host
+    restart: always
+  searchqna-gaudi-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: searchqna-gaudi-nginx-server
+    depends_on:
+      - searchqna-gaudi-backend-server
+      - searchqna-gaudi-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=searchqna-gaudi-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=searchqna
+      - BACKEND_SERVICE_IP=searchqna-gaudi-backend-server
+      - BACKEND_SERVICE_PORT=8888
     ipc: host
     restart: always
 
diff --git a/SearchQnA/docker_image_build/build.yaml b/SearchQnA/docker_image_build/build.yaml
@@ -46,3 +46,9 @@ services:
       context: GenAIComps
       dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
     image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
+  nginx:
+    build:
+      context: GenAIComps
+      dockerfile: comps/third_parties/nginx/src/Dockerfile
+    extends: searchqna
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
diff --git a/SearchQnA/tests/test_compose_on_gaudi.sh b/SearchQnA/tests/test_compose_on_gaudi.sh
@@ -32,7 +32,7 @@ function build_docker_images() {
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
diff --git a/SearchQnA/tests/test_compose_on_rocm.sh b/SearchQnA/tests/test_compose_on_rocm.sh
@@ -20,7 +20,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
diff --git a/SearchQnA/tests/test_compose_on_xeon.sh b/SearchQnA/tests/test_compose_on_xeon.sh
@@ -32,7 +32,7 @@ function build_docker_images() {
     git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
diff --git a/SearchQnA/tests/test_compose_vllm_on_rocm.sh b/SearchQnA/tests/test_compose_vllm_on_rocm.sh
@@ -20,7 +20,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen vllm-rocm"
+    service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen vllm-rocm nginx"
     docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
diff --git a/SearchQnA/ui/svelte/.env b/SearchQnA/ui/svelte/.env
@@ -1 +1 @@
-BACKEND_BASE_URL = 'http://backend_address:3008/v1/searchqna'
+BACKEND_BASE_URL = '/v1/searchqna'
diff --git a/SearchQnA/ui/svelte/playwright.config.ts b/SearchQnA/ui/svelte/playwright.config.ts
@@ -38,7 +38,7 @@ export default defineConfig({
 		/* Maximum time each action such as `click()` can take. Defaults to 0 (no limit). */
 		actionTimeout: 0,
 		/* Base URL to use in actions like `await page.goto('/')`. */
-		baseURL: "http://localhost:5173",
+		baseURL: "http://localhost:80",
 
 		/* Collect trace when retrying the failed test. See https://playwright.dev/docs/trace-viewer */
 		trace: "on-first-retry",
