Unify service ports in compose and READMEs

comps/embeddings/deployment/docker_compose/compose.yaml

@@ -28,7 +28,7 @@ services:
     image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
     container_name: tei-embedding-server
     ports:
-      - "${EMBEDDER_PORT:-10201}:6000"
+      - "${EMBEDDER_PORT:-6000}:6000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
@@ -45,7 +45,7 @@ services:
     image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
     container_name: ovms-embedding-server
     ports:
-      - "${EMBEDDER_PORT:-10201}:6000"
+      - "${EMBEDDER_PORT:-6000}:6000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
@@ -60,7 +60,7 @@ services:
     image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
     container_name: pg-embedding-server
     ports:
-      - ${EMBEDDER_PORT:-10202}:6000
+      - ${EMBEDDER_PORT:-6000}:6000
     ipc: host
     environment:
       no_proxy: ${no_proxy}
@@ -75,7 +75,7 @@ services:
     image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
     container_name: clip-embedding-server
     ports:
-      - ${EMBEDDER_PORT:-10203}:6000
+      - ${EMBEDDER_PORT:-6000}:6000
     ipc: host
     environment:
       no_proxy: ${no_proxy}

comps/rerankings/deployment/docker_compose/compose.yaml

@@ -10,7 +10,7 @@ services:
     image: ${REGISTRY:-opea}/reranking:${TAG:-latest}
     container_name: reranking-server
     ports:
-      - ${RERANK_PORT:-10700}:8000
+      - ${RERANK_PORT:-8000}:8000
     ipc: host
     environment:
       no_proxy: ${no_proxy}
@@ -51,7 +51,7 @@ services:
     image: ${REGISTRY:-opea}/reranking:${TAG:-latest}
     container_name: reranking-ovms-server
     ports:
-      - "${RERANK_PORT:-10201}:8000"
+      - "${RERANK_PORT:-8000}:8000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}

comps/rerankings/src/README_ovms.md

@@ -26,7 +26,7 @@ It speedup starting the service and avoids copying the model from Internet each
 - For Xeon CPU:
 
   ```bash
-  your_port=12005
+  your_port=8001
   docker run -p $your_port:8001 -v ./models:/models --name ovms-rerank-serving \
   openvino/model_server:2025.0 --port 8001 --config_path /models/config_reranking.json
   ```
@@ -53,11 +53,11 @@ It speedup starting the service and avoids copying the model from Internet each
 2. Run the reranking microservice and connect it to the OVMS service:
 
    ```bash
-    export OVMS_RERANKING_PORT=12005
+    export OVMS_RERANKING_PORT=8001
     export OVMS_RERANKING_ENDPOINT="http://localhost:${OVMS_RERANKING_PORT}"
     export MODEL_ID=BAAI/bge-reranker-large
 
-   docker run -d --rm --name="reranking-ovms-server" -e LOGFLAG=True  -p 10700:8000 --ipc=host -e OVMS_RERANKING_ENDPOINT=$OVMS_RERANKING_ENDPOINT -e RERANK_COMPONENT_NAME="OPEA_OVMS_RERANKING" -e MODEL_ID=$MODEL_ID opea/reranking:comps
+   docker run -d --rm --name="reranking-ovms-server" -e LOGFLAG=True  -p 8000:8000 --ipc=host -e OVMS_RERANKING_ENDPOINT=$OVMS_RERANKING_ENDPOINT -e RERANK_COMPONENT_NAME="OPEA_OVMS_RERANKING" -e MODEL_ID=$MODEL_ID opea/reranking:comps
    ```
 
 ## 📦 3. Start Microservice with docker compose
@@ -71,7 +71,7 @@ Deploy both the OVMS Reranking Service and the Reranking Microservice using Dock
    ```bash
     export MODEL_ID="BAAI/bge-reranker-large"
     export OVMS_RERANKING_PORT=12005
-    export RERANK_PORT=10700
+    export RERANK_PORT=8000
     export host_ip=$(hostname -I | awk '{print $1}')
     export OVMS_RERANKING_ENDPOINT="http://${host_ip}:${OVMS_RERANKING_PORT}"
     export TAG=comps
@@ -99,7 +99,7 @@ Deploy both the OVMS Reranking Service and the Reranking Microservice using Dock
 - Verify the reranking service is running:
 
   ```bash
-    curl http://localhost:10700/v1/health_check \
+    curl http://localhost:8000/v1/health_check \
     -X GET \
     -H 'Content-Type: application/json'
   ```
@@ -109,14 +109,14 @@ Deploy both the OVMS Reranking Service and the Reranking Microservice using Dock
 - Execute reranking process by providing query and documents
 
   ```bash
-  curl http://localhost:10700/v1/reranking -X POST -H 'Content-Type: application/json' \
+  curl http://localhost:8000/v1/reranking -X POST -H 'Content-Type: application/json' \
     -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}'
   ```
 
   - You can add the parameter `top_n` to specify the return number of the reranker model, default value is 1.
 
   ```bash
-  curl http://localhost:10700/v1/reranking \
+  curl http://localhost:8000/v1/reranking \
     -X POST \
     -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}], "top_n":2}' \
     -H 'Content-Type: application/json'

comps/rerankings/src/README_tei.md

@@ -67,7 +67,7 @@ This README provides set-up instructions and comprehensive details regarding the
     export host_ip=$(hostname -I | awk '{print $1}')
     export TEI_RERANKING_ENDPOINT="http://${host_ip}:${TEI_RERANKING_PORT}"
 
-   docker run -d --name="reranking-tei-server" -e LOGFLAG=True  -p 10700:8000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TEI_RERANKING_ENDPOINT=$TEI_RERANKING_ENDPOINT -e HF_TOKEN=$HF_TOKEN  -e RERANK_COMPONENT_NAME="OPEA_TEI_RERANKING"  opea/reranking:comps
+   docker run -d --name="reranking-tei-server" -e LOGFLAG=True  -p 8000:8000 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e TEI_RERANKING_ENDPOINT=$TEI_RERANKING_ENDPOINT -e HF_TOKEN=$HF_TOKEN  -e RERANK_COMPONENT_NAME="OPEA_TEI_RERANKING"  opea/reranking:comps
    ```
 
 ## 📦 2. Start Microservice with docker compose
@@ -81,7 +81,7 @@ Deploy both the TEI Reranking Service and the Reranking Microservice using Docke
    ```bash
     export RERANK_MODEL_ID="BAAI/bge-reranker-base"
     export TEI_RERANKING_PORT=12005
-    export RERANK_PORT=10700
+    export RERANK_PORT=8000
     export host_ip=$(hostname -I | awk '{print $1}')
     export TEI_RERANKING_ENDPOINT="http://${host_ip}:${TEI_RERANKING_PORT}"
     export TAG=comps
@@ -115,7 +115,7 @@ Deploy both the TEI Reranking Service and the Reranking Microservice using Docke
 - Verify the reranking service is running:
 
   ```bash
-    curl http://localhost:10700/v1/health_check \
+    curl http://localhost:8000/v1/health_check \
     -X GET \
     -H 'Content-Type: application/json'
   ```
@@ -125,7 +125,7 @@ Deploy both the TEI Reranking Service and the Reranking Microservice using Docke
 - Execute reranking process by providing query and documents
 
   ```bash
-  curl http://localhost:10700/v1/reranking \
+  curl http://localhost:8000/v1/reranking \
     -X POST \
     -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \
     -H 'Content-Type: application/json'
@@ -134,7 +134,7 @@ Deploy both the TEI Reranking Service and the Reranking Microservice using Docke
   - You can add the parameter `top_n` to specify the return number of the reranker model, default value is 1.
 
   ```bash
-  curl http://localhost:10700/v1/reranking \
+  curl http://localhost:8000/v1/reranking \
     -X POST \
     -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}], "top_n":2}' \
     -H 'Content-Type: application/json'

comps/rerankings/src/README_videoqna.md

@@ -29,7 +29,7 @@ Then we could send the `top_n` videos to the downstream LVM.
 
    ```bash
     docker run -d --name "reranking-videoqna-server" \
-      -p 10703:8000 \
+      -p 8000:8000 \
       --ipc=host \
       -e no_proxy=${no_proxy} \
       -e http_proxy=${http_proxy} \
@@ -50,7 +50,7 @@ Deploy both the Videoqna Reranking Service and the Reranking Microservice using
 
    ```bash
     export TEI_RERANKING_PORT=12006
-    export RERANK_PORT=10703
+    export RERANK_PORT=8000
     export host_ip=$(hostname -I | awk '{print $1}')
     export TEI_RERANKING_ENDPOINT="http://${host_ip}:${TEI_RERANKING_PORT}"
     export TAG=comps
@@ -75,7 +75,7 @@ Deploy both the Videoqna Reranking Service and the Reranking Microservice using
 - Verify the reranking service is running:
 
   ```bash
-  curl http://localhost:10703/v1/health_check \
+  curl http://localhost:8000/v1/health_check \
   -X GET \
   -H 'Content-Type: application/json'
   ```
@@ -85,7 +85,7 @@ Deploy both the Videoqna Reranking Service and the Reranking Microservice using
 - Execute reranking process by providing query and documents
 
   ```bash
-  curl http://localhost:10703/v1/reranking \
+  curl http://localhost:8000/v1/reranking \
     -X POST \
     -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \
     -H 'Content-Type: application/json'
@@ -94,7 +94,7 @@ Deploy both the Videoqna Reranking Service and the Reranking Microservice using
 - You can add the parameter `top_n` to specify the return number of the reranker model, default value is 1.
 
   ```bash
-  curl http://localhost:10703/v1/reranking \
+  curl http://localhost:8000/v1/reranking \
     -X POST \
     -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}], "top_n":2}' \
     -H 'Content-Type: application/json'

comps/third_parties/tei/deployment/docker_compose/compose.yaml

@@ -18,7 +18,7 @@ services:
       host_ip: ${host_ip}
       HF_TOKEN: ${HF_TOKEN}
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
       timeout: 6s
       retries: 48
@@ -38,7 +38,7 @@ services:
       https_proxy: ${https_proxy}
       host_ip: ${host_ip}
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_RERANKING_PORT}/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
       timeout: 6s
       retries: 48
@@ -66,7 +66,7 @@ services:
       - SYS_NICE
     ipc: host
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_RERANKING_PORT}/health"]
+      test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
       timeout: 6s
       retries: 48