update image build for 2 new examples (#729)

Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>

Author: chensuyue

DocIndexRetriever/docker/Dockerfile

@@ -18,7 +18,7 @@ WORKDIR /home/user/GenAIComps
 RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir -r /home/user/GenAIComps/requirements.txt
 
-COPY GenAIExamples/DocIndexRetriever/docker/retrieval_tool.py /home/user/retrieval_tool.py
+COPY ./retrieval_tool.py /home/user/retrieval_tool.py
 
 ENV PYTHONPATH=$PYTHONPATH:/home/user/GenAIComps
 

DocIndexRetriever/docker/README.md

@@ -35,7 +35,8 @@ DocRetriever are the most widely adopted use case for leveraging the different m
 ```bash
 cd ..
 git clone https://github.com/opea-project/GenAIExamples.git
-docker build --no-cache -t opea/doc-index-retriever:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f GenAIExamples/DocIndexRetriever/docker/Dockerfile .
+cd GenAIExamples/DocIndexRetriever/docker
+docker build --no-cache -t opea/doc-index-retriever:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./Dockerfile .
 ```
 
 ## 3. Start all the services Docker Containers

DocIndexRetriever/docker/docker_build_compose.yaml

@@ -0,0 +1,36 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  doc-index-retriever:
+    build:
+      args:
+        http_proxy: ${http_proxy}
+        https_proxy: ${https_proxy}
+        no_proxy: ${no_proxy}
+      dockerfile: ./Dockerfile
+    image: ${REGISTRY:-opea}/doc-index-retriever:${TAG:-latest}
+  embedding-tei:
+    build:
+      context: GenAIComps
+      dockerfile: comps/embeddings/langchain/docker/Dockerfile
+    extends: doc-index-retriever
+    image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
+  retriever-redis:
+    build:
+      context: GenAIComps
+      dockerfile: comps/retrievers/langchain/redis/docker/Dockerfile
+    extends: chatqna
+    image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
+  reranking-tei:
+    build:
+      context: GenAIComps
+      dockerfile: comps/reranks/tei/docker/Dockerfile
+    extends: doc-index-retriever
+    image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
+  dataprep-on-ray-redis:
+    build:
+      context: GenAIComps
+      dockerfile: comps/dataprep/redis/langchain_ray/docker/Dockerfile
+    extends: doc-index-retriever
+    image: ${REGISTRY:-opea}/dataprep-on-ray-redis:${TAG:-latest}

DocIndexRetriever/docker/gaudi/docker_compose.yaml

@@ -82,7 +82,7 @@ services:
     image: opea/reranking-tei:latest
     container_name: reranking-tei-server
     ports:
-      - "18000:8000"
+      - "8000:8000"
     ipc: host
     entrypoint: python local_reranking.py
     environment:

DocIndexRetriever/docker/xeon/docker_compose.yaml

@@ -1,4 +1,3 @@
-
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
@@ -9,34 +8,38 @@ services:
     image: redis/redis-stack:7.2.0-v9
     container_name: redis-vector-db
     ports:
-      - "16379:6379"
+      - "6379:6379"
       - "8001:8001"
   dataprep-redis-service:
-    image: opea/dataprep-on-ray-redis:latest
+    image: opea/dataprep-redis:latest
     container_name: dataprep-redis-server
     depends_on:
       - redis-vector-db
     ports:
       - "6007:6007"
+      - "6008:6008"
+      - "6009:6009"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
     container_name: tei-embedding-server
     ports:
-      - "8090:80"
+      - "6006:80"
     volumes:
       - "./data:/data"
     shm_size: 1g
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-    command: --model-id ${EMBEDDING_MODEL_ID}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
   embedding:
     image: opea/embedding-tei:latest
     container_name: embedding-tei-server
@@ -49,6 +52,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
       LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
@@ -68,17 +72,40 @@ services:
       https_proxy: ${https_proxy}
       REDIS_URL: ${REDIS_URL}
       INDEX_NAME: ${INDEX_NAME}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
       LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
       LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
       LANGCHAIN_PROJECT: "opea-retriever-service"
     restart: unless-stopped
+
+  tei-reranking-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
+    container_name: tei-reranking-server
+    ports:
+      - "8808:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
+
   reranking:
     image: opea/reranking-tei:latest
-    container_name: reranking-tei-server
+    container_name: reranking-tei-xeon-server
+    volumes:
+      - ${WORKDIR}/GenAIComps/comps/:/home/user/comps
+    depends_on:
+      - tei-reranking-service
     ports:
-      - "18000:8000"
+      - "8000:8000"
     ipc: host
-    entrypoint: python local_reranking.py
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
@@ -99,6 +126,7 @@ services:
       - tei-embedding-service
       - embedding
       - retriever
+      - tei-reranking-service
       - reranking
     ports:
       - "8889:8889"

DocIndexRetriever/tests/test_docindexretriever_on_gaudi.sh

@@ -10,12 +10,11 @@ LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')
 
 function build_docker_images() {
-    cd $WORKPATH/../../
+    cd $WORKPATH/docker
     if [ ! -d "GenAIComps" ] ; then
         git clone https://github.com/opea-project/GenAIComps.git
     fi
     cd GenAIComps
-    git status
 
     docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
     docker build -t opea/retriever-redis:latest -f comps/retrievers/langchain/redis/docker/Dockerfile .
@@ -25,8 +24,8 @@ function build_docker_images() {
     docker pull ghcr.io/huggingface/tgi-gaudi:latest
     docker pull redis/redis-stack:7.2.0-v9
 
-    cd $WORKPATH/../../
-    docker build -t opea/doc-index-retriever:latest -f GenAIExamples/DocIndexRetriever/docker/Dockerfile .
+    cd $WORKPATH/docker
+    docker build -t opea/doc-index-retriever:latest -f ./Dockerfile .
 }
 
 function start_services() {

ProductivitySuite/docker/docker_build_compose.yaml

@@ -41,19 +41,19 @@ services:
       dockerfile: comps/dataprep/redis/langchain/docker/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest}
-  promptregistry-mongo:
+  promptregistry-mongo-server:
     build:
       context: GenAIComps
       dockerfile: comps/prompt_registry/mongo/docker/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/promptregistry-mongo-server:${TAG:-latest}
-  chathistory-mongo:
+  chathistory-mongo-server:
     build:
       context: GenAIComps
       dockerfile: comps/chathistory/mongo/docker/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/chathistory-mongo-server:${TAG:-latest}
-  productivity-suite-react-ui:
+  productivity-suite-react-ui-server:
     build:
       context: ui
       dockerfile: ./docker/Dockerfile.react
@@ -86,13 +86,13 @@ services:
       context: ../../FaqGen/docker/
       dockerfile: ./Dockerfile
     image: ${REGISTRY:-opea}/faqgen:${TAG:-latest}
-  llm_faqgen:
+  llm-faqgen-tgi:
     build:
       context: GenAIComps
       dockerfile: comps/llms/faq-generation/tgi/Dockerfile
     extends: faqgen
     image: ${REGISTRY:-opea}/llm-faqgen-tgi:${TAG:-latest}
-  llm_docsum_server:
+  llm-docsum-tgi:
     build:
       context: GenAIComps
       dockerfile: comps/llms/summarization/tgi/Dockerfile

ProductivitySuite/tests/test_productivitysuite_on_xeon.sh

@@ -19,8 +19,7 @@ function build_docker_images() {
     git clone https://github.com/opea-project/GenAIComps.git
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    service_list="chatqna dataprep-redis embedding-tei promptregistry-mongo llm_docsum_server llm_faqgen chathistory-mongo retriever-redis reranking-tei llm-tgi productivity-suite-react-ui codegen docsum faqgen"
-    docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
+    docker compose -f docker_build_compose.yaml build --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-generation-inference:2.1.0