Update Code and README for GenAIComps Refactor (#1285)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
Signed-off-by: ZePan110 <ze.pan@intel.com>
Signed-off-by: WenjiaoYue <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>

Author: chensuyue

.github/workflows/_get-test-matrix.yml

@@ -60,9 +60,11 @@ jobs:
             base_commit=$(git rev-parse HEAD~1) # push event
           fi
           merged_commit=$(git log -1 --format='%H')
+          echo "print all changed files..."
+          git diff --name-only ${base_commit} ${merged_commit}
           changed_files="$(git diff --name-only ${base_commit} ${merged_commit} | \
           grep -vE '${{ inputs.diff_excluded_files }}')" || true
-          echo "changed_files=$changed_files"
+          echo "filtered changed_files=$changed_files"
           export changed_files=$changed_files
           export test_mode=${{ inputs.test_mode }}
           export WORKSPACE=${{ github.workspace }}

AudioQnA/docker_image_build/build.yaml

@@ -44,7 +44,7 @@ services:
   llm-tgi:
     build:
       context: GenAIComps
-      dockerfile: comps/llms/text-generation/tgi/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
     extends: audioqna
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
   speecht5-gaudi:

AudioQnA/tests/test_compose_on_rocm.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Advanced Micro Devices, Inc.
 # SPDX-License-Identifier: Apache-2.0
 
-set -ex
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"

AvatarChatbot/docker_compose/intel/hpu/gaudi/README.md

@@ -19,7 +19,7 @@ docker build -t opea/whisper-gaudi:latest --build-arg https_proxy=$https_proxy -
 
 ### 3. Build LLM Image
 
-Intel Xeon optimized image hosted in huggingface repo will be used for TGI service: ghcr.io/huggingface/tgi-gaudi:2.0.6 (https://github.com/huggingface/tgi-gaudi)
+Intel Gaudi optimized image hosted in huggingface repo will be used for TGI service: ghcr.io/huggingface/tgi-gaudi:2.0.6 (https://github.com/huggingface/tgi-gaudi)
 
 ### 4. Build TTS Image
 

AvatarChatbot/docker_image_build/build.yaml

@@ -32,7 +32,7 @@ services:
   llm-tgi:
     build:
       context: GenAIComps
-      dockerfile: comps/llms/text-generation/tgi/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
     extends: avatarchatbot
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
   speecht5-gaudi:

AvatarChatbot/tests/test_compose_on_gaudi.sh

@@ -72,7 +72,6 @@ function start_services() {
 
     # Start Docker Containers
     docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
-
     n=0
     until [[ "$n" -ge 200 ]]; do
        docker logs tgi-gaudi-server > $LOG_PATH/tgi_service_start.log
@@ -82,7 +81,6 @@ function start_services() {
        sleep 5s
        n=$((n+1))
     done
-
     echo "All services are up and running"
     sleep 5s
 }

AvatarChatbot/tests/test_compose_on_xeon.sh

@@ -82,7 +82,6 @@ function start_services() {
        n=$((n+1))
     done
     echo "All services are up and running"
-    sleep 5s
 }
 
 

ChatQnA/README.md

@@ -297,7 +297,7 @@ Here is an example of `Nike 2023` pdf.
 
 ```bash
 # download pdf file
-wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
+wget https://raw.githubusercontent.com/opea-project/GenAIComps/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf
 # upload pdf file with dataprep
 curl -X POST "http://${host_ip}:6007/v1/dataprep" \
     -H "Content-Type: multipart/form-data" \

ChatQnA/docker_compose/amd/gpu/rocm/README.md

@@ -63,7 +63,7 @@ Prepare and upload test document
 
 ```
 # download pdf file
-wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
+wget https://raw.githubusercontent.com/opea-project/GenAIComps/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf
 # upload pdf file with dataprep
 curl -X POST "http://${host_ip}:6007/v1/dataprep" \
     -H "Content-Type: multipart/form-data" \
@@ -138,7 +138,7 @@ cd ../../../..
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:

ChatQnA/docker_compose/intel/cpu/aipc/README.md

@@ -55,7 +55,7 @@ docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 6 Docker Images:
@@ -188,7 +188,7 @@ For details on how to verify the correctness of the response, refer to [how-to-v
 
 ```bash
 # download pdf file
-wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
+wget https://raw.githubusercontent.com/opea-project/GenAIComps/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf
 
 # upload pdf file with dataprep
 curl -X POST "http://${host_ip}:6007/v1/dataprep" \

ChatQnA/docker_compose/intel/cpu/xeon/README.md

@@ -161,7 +161,7 @@ docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:
@@ -356,12 +356,12 @@ For details on how to verify the correctness of the response, refer to [how-to-v
 
 If you want to update the default knowledge base, you can use the following commands:
 
-Update Knowledge Base via Local File [nke-10k-2023.pdf](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/redis/data/nke-10k-2023.pdf). Or
-click [here](https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf) to download the file via any web browser.
+Update Knowledge Base via Local File [nke-10k-2023.pdf](https://github.com/opea-project/GenAIComps/blob/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf). Or
+click [here](https://raw.githubusercontent.com/opea-project/GenAIComps/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf) to download the file via any web browser.
 Or run this command to get the file on a terminal.
 
 ```bash
-wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
+wget https://raw.githubusercontent.com/opea-project/GenAIComps/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf
 
 ```
 

ChatQnA/docker_compose/intel/cpu/xeon/README_pinecone.md

@@ -164,7 +164,7 @@ docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:
@@ -347,8 +347,8 @@ For details on how to verify the correctness of the response, refer to [how-to-v
 
 If you want to update the default knowledge base, you can use the following commands:
 
-Update Knowledge Base via Local File [nke-10k-2023.pdf](https://github.com/opea-project/GenAIComps/blob/main/comps/retrievers/redis/data/nke-10k-2023.pdf). Or
-click [here](https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf) to download the file via any web browser.
+Update Knowledge Base via Local File [nke-10k-2023.pdf](https://github.com/opea-project/GenAIComps/blob/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf). Or
+click [here](https://raw.githubusercontent.com/opea-project/GenAIComps/v1.1/comps/retrievers/redis/data/nke-10k-2023.pdf) to download the file via any web browser.
 Or run this command to get the file on a terminal.
 
 ```bash

ChatQnA/docker_compose/intel/cpu/xeon/README_qdrant.md

@@ -122,7 +122,7 @@ cd ../../../..
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:

ChatQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -151,7 +151,7 @@ docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:

ChatQnA/docker_compose/nvidia/gpu/README.md

@@ -148,7 +148,7 @@ cd ../../..
 
 ```bash
 cd GenAIComps
-docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/3rd_parties/nginx/src/Dockerfile .
 ```
 
 Then run the command `docker images`, you will have the following 5 Docker Images:

ChatQnA/docker_image_build/build.yaml

@@ -44,7 +44,7 @@ services:
   embedding-tei:
     build:
       context: GenAIComps
-      dockerfile: comps/embeddings/tei/langchain/Dockerfile
+      dockerfile: comps/embeddings/src/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/embedding-tei:${TAG:-latest}
   retriever-redis:
@@ -68,25 +68,25 @@ services:
   reranking-tei:
     build:
       context: GenAIComps
-      dockerfile: comps/reranks/tei/Dockerfile
+      dockerfile: comps/reranks/src/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/reranking-tei:${TAG:-latest}
   llm-tgi:
     build:
       context: GenAIComps
-      dockerfile: comps/llms/text-generation/tgi/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
   llm-ollama:
     build:
       context: GenAIComps
-      dockerfile: comps/llms/text-generation/ollama/langchain/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/llm-ollama:${TAG:-latest}
   llm-vllm:
     build:
       context: GenAIComps
-      dockerfile: comps/llms/text-generation/vllm/langchain/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/llm-vllm:${TAG:-latest}
   dataprep-redis:
@@ -128,6 +128,6 @@ services:
   nginx:
     build:
       context: GenAIComps
-      dockerfile: comps/nginx/Dockerfile
+      dockerfile: comps/3rd_parties/nginx/src/Dockerfile
     extends: chatqna
     image: ${REGISTRY:-opea}/nginx:${TAG:-latest}

ChatQnA/tests/test_compose_on_rocm.sh

@@ -76,6 +76,8 @@ function start_services() {
         sleep 1s
         n=$((n+1))
     done
+
+    echo "all containers start!"
 }
 
 function validate_service() {

CodeGen/docker_compose/amd/gpu/rocm/README.md

@@ -10,7 +10,7 @@ git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
 
 ### Build Docker image
-docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
 ```
 
 ### Build the MegaService Docker Image

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

@@ -15,6 +15,12 @@ services:
       https_proxy: ${https_proxy}
       HUGGING_FACE_HUB_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
       HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:${CODEGEN_TGI_SERVICE_PORT:-8028}/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     shm_size: 1g
     devices:
       - /dev/kfd:/dev/kfd
@@ -31,15 +37,17 @@ services:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: codegen-llm-server
     depends_on:
-      - codegen-tgi-service
+      codegen-tgi-service:
+        condition: service_healthy
     ports:
       - "${CODEGEN_LLM_SERVICE_PORT:-9000}:9000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: "http://codegen-tgi-service"
+      LLM_ENDPOINT: "http://codegen-tgi-service"
+      LLM_MODEL_ID: ${CODEGEN_LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   codegen-backend-server:

CodeGen/docker_compose/intel/cpu/xeon/README.md

@@ -19,7 +19,7 @@ Should the Docker image you seek not yet be available on Docker Hub, you can bui
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
 ```
 
 ### 2. Build the MegaService Docker Image

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

@@ -15,20 +15,28 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
   llm:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: llm-tgi-server
     depends_on:
-      - tgi-service
+      tgi-service:
+        condition: service_healthy
     ports:
       - "9000:9000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   codegen-xeon-backend-server:

CodeGen/docker_compose/intel/hpu/gaudi/README.md

@@ -11,7 +11,7 @@ First of all, you need to build the Docker images locally. This step can be igno
 ```bash
 git clone https://github.com/opea-project/GenAIComps.git
 cd GenAIComps
-docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/src/text-generation/Dockerfile .
 ```
 
 ### 2. Build the MegaService Docker Image

CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -20,6 +20,11 @@ services:
       LIMIT_HPU_GRAPH: true
       USE_FLASH_ATTENTION: true
       FLASH_ATTENTION_RECOMPUTE: true
+    healthcheck:
+      test: ["CMD-SHELL", "sleep 500 && exit 0"]
+      interval: 1s
+      timeout: 505s
+      retries: 1
     runtime: habana
     cap_add:
       - SYS_NICE
@@ -29,15 +34,17 @@ services:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: llm-tgi-gaudi-server
     depends_on:
-      - tgi-service
+      tgi-service:
+        condition: service_healthy
     ports:
       - "9000:9000"
     ipc: host
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   codegen-gaudi-backend-server:

CodeGen/docker_image_build/build.yaml

@@ -26,6 +26,6 @@ services:
   llm-tgi:
     build:
       context: GenAIComps
-      dockerfile: comps/llms/text-generation/tgi/Dockerfile
+      dockerfile: comps/llms/src/text-generation/Dockerfile
     extends: codegen
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}

CodeGen/tests/test_compose_on_gaudi.sh

@@ -34,6 +34,7 @@ function start_services() {
     export MEGA_SERVICE_HOST_IP=${ip_address}
     export LLM_SERVICE_HOST_IP=${ip_address}
     export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:7778/v1/codegen"
+    export host_ip=${ip_address}
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 

CodeGen/tests/test_compose_on_rocm.sh

@@ -39,6 +39,7 @@ function start_services() {
     export CODEGEN_BACKEND_SERVICE_PORT=7778
     export CODEGEN_BACKEND_SERVICE_URL="http://${ip_address}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen"
     export CODEGEN_UI_SERVICE_PORT=5173
+    export host_ip=${ip_address}
 
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env