Update TEI docker images to CPU-1.6 (#1791)

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>

ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -27,7 +27,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN}
 
   chatqna-tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     container_name: chatqna-tei-embedding-service
     ports:
       - "${CHATQNA_TEI_EMBEDDING_PORT}:80"
@@ -62,7 +62,7 @@ services:
     restart: unless-stopped
 
   chatqna-tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     container_name: chatqna-tei-reranking-service
     ports:
       - "${CHATQNA_TEI_RERANKING_PORT}:80"

ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml

@@ -27,7 +27,7 @@ services:
       HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN}
 
   chatqna-tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     container_name: chatqna-tei-embedding-service
     ports:
       - "${CHATQNA_TEI_EMBEDDING_PORT}:80"
@@ -62,7 +62,7 @@ services:
     restart: unless-stopped
 
   chatqna-tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     container_name: chatqna-tei-reranking-service
     ports:
       - "${CHATQNA_TEI_RERANKING_PORT}:80"

ChatQnA/tests/test_compose_faqgen_on_rocm.sh

@@ -70,7 +70,7 @@ function build_docker_images() {
     docker compose -f build.yaml build ${service_list} --no-cache > "${LOG_PATH}"/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
 
     docker images && sleep 1s
 }

ChatQnA/tests/test_compose_on_rocm.sh

@@ -68,7 +68,7 @@ function build_docker_images() {
     docker compose -f build.yaml build ${service_list} --no-cache > "${LOG_PATH}"/docker_image_build.log
 
     docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
 
     docker images && sleep 1s
 }

SearchQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -5,7 +5,7 @@
 
 services:
   search-tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     container_name: search-tei-embedding-server
     ports:
       - "${SEARCH_TEI_EMBEDDING_PORT:-3001}:80"
@@ -54,7 +54,7 @@ services:
     restart: unless-stopped
 
   search-tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     container_name: search-tei-reranking-server
     ports:
       - "${SEARCH_TEI_RERANKING_PORT:-3004}:80"

SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml

@@ -3,7 +3,7 @@
 
 services:
   tei-embedding-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
     container_name: tei-embedding-server
     ports:
@@ -54,7 +54,7 @@ services:
       LOGFLAG: ${LOGFLAG}
     restart: unless-stopped
   tei-reranking-service:
-    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${RERANK_MODEL_ID} --auto-truncate"
     container_name: tei-reranking-server
     ports:

SearchQnA/tests/test_compose_on_rocm.sh

@@ -23,7 +23,7 @@ function build_docker_images() {
     service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
     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
+    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     docker pull ghcr.io/huggingface/text-generation-inference:2.4.1-rocm
     docker images && sleep 1s
 }

SearchQnA/tests/test_compose_on_xeon.sh

@@ -35,7 +35,7 @@ function build_docker_images() {
     service_list="searchqna searchqna-ui embedding web-retriever reranking llm-textgen"
     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
+    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
     docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
     docker images && sleep 1s
 }