SearchQnA App - Adding files to deploy SearchQnA application on AMD GPU (#1193)

Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>
2025-01-27 09:58:55 +07:00
parent ed163087ba
commit 39abef8be8
4 changed files with 525 additions and 0 deletions
--- a/SearchQnA/docker_compose/amd/gpu/rocm/README.md
+++ b/SearchQnA/docker_compose/amd/gpu/rocm/README.md
@@ -0,0 +1,179 @@
+# Build and deploy SearchQnA Application on AMD GPU (ROCm)
+
+## Build images
+
+### Build Embedding Image
+
+```bash
+git clone https://github.com/opea-project/GenAIComps.git
+cd GenAIComps
+docker build --no-cache -t opea/embedding-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/embeddings/src/Dockerfile .
+```
+
+### Build Retriever Image
+
+```bash
+docker build --no-cache -t opea/web-retriever-chroma:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/web_retrievers/src/Dockerfile .
+```
+
+### Build Rerank Image
+
+```bash
+docker build --no-cache -t opea/reranking-tei:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/rerankings/src/Dockerfile .
+```
+
+### Build the LLM Docker Image
+
+```bash
+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
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+cd GenAIExamples/SearchQnA
+docker build --no-cache -t opea/searchqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+```
+
+### Build the UI Docker Image
+
+```bash
+cd GenAIExamples/SearchQnA/ui
+docker build --no-cache -t opea/opea/searchqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
+```
+
+## Deploy SearchQnA Application
+
+### Features of Docker compose for AMD GPUs
+
+1. Added forwarding of GPU devices to the container TGI service with instructions:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/:/dev/dri/
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+In this case, all GPUs are thrown. To reset a specific GPU, you need to use specific device names cardN and renderN.
+
+For example:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/card0:/dev/dri/card0
+  - /dev/dri/render128:/dev/dri/render128
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+To find out which GPU device IDs cardN and renderN correspond to the same GPU, use the GPU driver utility
+
+### Go to the directory with the Docker compose file
+
+```bash
+cd GenAIExamples/SearchQnA/docker_compose/amd/gpu/rocm
+```
+
+### Set environments
+
+In the file "GenAIExamples/SearchQnA/docker_compose/amd/gpu/rocm/set_env.sh " it is necessary to set the required values. Parameter assignments are specified in the comments for each variable setting command
+
+```bash
+chmod +x set_env.sh
+. set_env.sh
+```
+
+### Run services
+
+```
+docker compose up -d
+```
+
+# Validate the MicroServices and MegaService
+
+## Validate TEI service
+
+```bash
+curl http://${SEARCH_HOST_IP}:3001/embed \
+    -X POST \
+    -d '{"inputs":"What is Deep Learning?"}' \
+    -H 'Content-Type: application/json'
+```
+
+## Validate Embedding service
+
+```bash
+curl http://${SEARCH_HOST_IP}:3002/v1/embeddings\
+  -X POST \
+  -d '{"text":"hello"}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate Web Retriever service
+
+```bash
+export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+curl http://${SEARCH_HOST_IP}:3003/v1/web_retrieval \
+  -X POST \
+  -d "{\"text\":\"What is the 2024 holiday schedule?\",\"embedding\":${your_embedding}}" \
+  -H 'Content-Type: application/json'
+```
+
+## Validate TEI Reranking service
+
+```bash
+curl http://${SEARCH_HOST_IP}:3004/rerank \
+    -X POST \
+    -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
+    -H 'Content-Type: application/json'
+```
+
+## Validate Reranking service
+
+```bash
+curl http://${SEARCH_HOST_IP}:3005/v1/reranking\
+  -X POST \
+  -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate TGI service
+
+```bash
+curl http://${SEARCH_HOST_IP}:3006/generate \
+  -X POST \
+  -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate LLM service
+
+```bash
+curl http://${SEARCH_HOST_IP}:3007/v1/chat/completions\
+  -X POST \
+  -d '{"query":"What is Deep Learning?","max_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":true}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate MegaService
+
+```bash
+curl http://${SEARCH_HOST_IP}:3008/v1/searchqna -H "Content-Type: application/json" -d '{
+     "messages": "What is the latest news? Give me also the source link.",
+     "stream": "True"
+     }'
+```
--- a/SearchQnA/docker_compose/amd/gpu/rocm/compose.yaml
+++ b/SearchQnA/docker_compose/amd/gpu/rocm/compose.yaml
@@ -0,0 +1,173 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  search-tei-embedding-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    container_name: search-tei-embedding-server
+    ports:
+      - "3001:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+    command: --model-id ${SEARCH_EMBEDDING_MODEL_ID} --auto-truncate
+  search-embedding:
+    image: ${REGISTRY:-opea}/embedding:${TAG:-latest}
+    container_name: search-embedding-server
+    depends_on:
+      - search-tei-embedding-service
+    ports:
+      - "3002:6000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TEI_EMBEDDING_HOST_IP: ${SEARCH_HOST_IP}
+      TEI_EMBEDDING_ENDPOINT: ${SEARCH_TEI_EMBEDDING_ENDPOINT}
+      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+    restart: unless-stopped
+  search-web-retriever:
+    image: ${REGISTRY:-opea}/web-retriever:${TAG:-latest}
+    container_name: search-web-retriever-server
+    ports:
+      - "3003:7077"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TEI_EMBEDDING_ENDPOINT: ${SEARCH_TEI_EMBEDDING_ENDPOINT}
+      GOOGLE_API_KEY: ${SEARCH_GOOGLE_API_KEY}
+      GOOGLE_CSE_ID: ${SEARCH_GOOGLE_CSE_ID}
+    restart: unless-stopped
+  search-tei-reranking-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    container_name: search-tei-reranking-server
+    ports:
+      - "3004:80"
+    volumes:
+      - "./data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+    command: --model-id ${SEARCH_RERANK_MODEL_ID} --auto-truncate
+  search-reranking:
+    image: ${REGISTRY:-opea}/reranking:${TAG:-latest}
+    container_name: search-reranking-server
+    depends_on:
+      - search-tei-reranking-service
+    ports:
+      - "3005:8000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TEI_RERANKING_ENDPOINT: ${SEARCH_TEI_RERANKING_ENDPOINT}
+      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+    restart: unless-stopped
+  search-tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    container_name: search-tgi-service
+    ports:
+      - "3006:80"
+    volumes:
+      - "./data:/data"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGING_FACE_HUB_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+    shm_size: 1g
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/:/dev/dri/
+    cap_add:
+      - SYS_PTRACE
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+    ipc: host
+    command: --model-id ${SEARCH_LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
+  search-llm:
+    image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
+    container_name: search-llm-server
+    depends_on:
+      - search-tgi-service
+    ports:
+      - "3007:9000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: ${SEARCH_TGI_LLM_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      LLM_ENDPOINT: ${SEARCH_TGI_LLM_ENDPOINT}
+      LLM_MODEL_ID: ${SEARCH_LLM_MODEL_ID}
+      LLM_MODEL: ${SEARCH_LLM_MODEL_ID}
+      HF_TOKEN: ${SEARCH_HUGGINGFACEHUB_API_TOKEN}
+      OPENAI_API_KEY: ${SEARCH_OPENAI_API_KEY}
+    restart: unless-stopped
+  search-backend-server:
+    image: ${REGISTRY:-opea}/searchqna:${TAG:-latest}
+    container_name: search-backend-server
+    depends_on:
+      - search-tei-embedding-service
+      - search-embedding
+      - search-web-retriever
+      - search-tei-reranking-service
+      - search-reranking
+      - search-tgi-service
+      - search-llm
+    ports:
+      - "${SEARCH_BACKEND_SERVICE_PORT:-3008}:8888"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - MEGA_SERVICE_HOST_IP=${SEARCH_MEGA_SERVICE_HOST_IP}
+      - EMBEDDING_SERVICE_HOST_IP=${SEARCH_EMBEDDING_SERVICE_HOST_IP}
+      - WEB_RETRIEVER_SERVICE_HOST_IP=${SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP}
+      - RERANK_SERVICE_HOST_IP=${SEARCH_RERANK_SERVICE_HOST_IP}
+      - LLM_SERVICE_HOST_IP=${SEARCH_LLM_SERVICE_HOST_IP}
+      - EMBEDDING_SERVICE_PORT=${SEARCH_EMBEDDING_SERVICE_PORT}
+      - WEB_RETRIEVER_SERVICE_PORT=${SEARCH_WEB_RETRIEVER_SERVICE_PORT}
+      - RERANK_SERVICE_PORT=${SEARCH_RERANK_SERVICE_PORT}
+      - LLM_SERVICE_PORT=${SEARCH_LLM_SERVICE_PORT}
+    ipc: host
+    restart: always
+  search-ui-server:
+    image: ${REGISTRY:-opea}/searchqna-ui:${TAG:-latest}
+    container_name: search-ui-server
+    depends_on:
+      - search-backend-server
+    ports:
+      - "${SEARCH_FRONTEND_SERVICE_PORT:-5173}:5173"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - BACKEND_BASE_URL=${SEARCH_BACKEND_SERVICE_ENDPOINT}
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge
--- a/SearchQnA/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/SearchQnA/docker_compose/amd/gpu/rocm/set_env.sh
@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# SPDX-License-Identifier: Apache-2.0
+
+export SEARCH_HOST_IP=10.53.22.29
+export SEARCH_EXTERNAL_HOST_IP=68.69.180.77
+export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
+export SEARCH_TEI_EMBEDDING_ENDPOINT=http://${SEARCH_HOST_IP}:3001
+export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'
+export SEARCH_TEI_RERANKING_ENDPOINT=http://${SEARCH_HOST_IP}:3004
+export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export SEARCH_OPENAI_API_KEY=${OPENAI_API_KEY}
+
+export SEARCH_TGI_LLM_ENDPOINT=http://${SEARCH_HOST_IP}:3006
+export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
+
+export SEARCH_MEGA_SERVICE_HOST_IP=${SEARCH_EXTERNAL_HOST_IP}
+export SEARCH_EMBEDDING_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+export SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+export SEARCH_RERANK_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+export SEARCH_LLM_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+
+export SEARCH_EMBEDDING_SERVICE_PORT=3002
+export SEARCH_WEB_RETRIEVER_SERVICE_PORT=3003
+export SEARCH_RERANK_SERVICE_PORT=3005
+export SEARCH_LLM_SERVICE_PORT=3007
+
+export SEARCH_FRONTEND_SERVICE_PORT=18143
+export SEARCH_BACKEND_SERVICE_PORT=18142
+export SEARCH_BACKEND_SERVICE_ENDPOINT=http://${SEARCH_EXTERNAL_HOST_IP}:${SEARCH_BACKEND_SERVICE_PORT}/v1/searchqna
+
+export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
+export SEARCH_GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
--- a/SearchQnA/tests/test_compose_on_rocm.sh
+++ b/SearchQnA/tests/test_compose_on_rocm.sh
@@ -0,0 +1,137 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -xe
+IMAGE_REPO=${IMAGE_REPO:-"opea"}
+IMAGE_TAG=${IMAGE_TAG:-"latest"}
+echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
+echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
+export REGISTRY=${IMAGE_REPO}
+export TAG=${IMAGE_TAG}
+
+WORKPATH=$(dirname "$PWD")
+LOG_PATH="$WORKPATH/tests"
+ip_address=$(hostname -I | awk '{print $1}')
+
+function build_docker_images() {
+    cd $WORKPATH/docker_image_build
+    git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${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"
+    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-generation-inference:2.3.1-rocm
+    docker images && sleep 1s
+}
+
+function start_services() {
+    cd $WORKPATH/docker_compose/amd/gpu/rocm/
+    export SEARCH_HOST_IP=${ip_address}
+    export SEARCH_EXTERNAL_HOST_IP=${ip_address}
+    export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
+    export SEARCH_TEI_EMBEDDING_ENDPOINT=http://${SEARCH_HOST_IP}:3001
+    export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'
+    export SEARCH_TEI_RERANKING_ENDPOINT=http://${SEARCH_HOST_IP}:3004
+    export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export SEARCH_OPENAI_API_KEY=${OPENAI_API_KEY}
+    export SEARCH_TGI_LLM_ENDPOINT=http://${SEARCH_HOST_IP}:3006
+    export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
+    export SEARCH_MEGA_SERVICE_HOST_IP=${SEARCH_EXTERNAL_HOST_IP}
+    export SEARCH_EMBEDDING_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+    export SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+    export SEARCH_RERANK_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+    export SEARCH_LLM_SERVICE_HOST_IP=${SEARCH_HOST_IP}
+    export SEARCH_EMBEDDING_SERVICE_PORT=3002
+    export SEARCH_WEB_RETRIEVER_SERVICE_PORT=3003
+    export SEARCH_RERANK_SERVICE_PORT=3005
+    export SEARCH_LLM_SERVICE_PORT=3007
+    export SEARCH_FRONTEND_SERVICE_PORT=5173
+    export SEARCH_BACKEND_SERVICE_PORT=3008
+    export SEARCH_BACKEND_SERVICE_ENDPOINT=http://${SEARCH_HOST_IP}:${SEARCH_BACKEND_SERVICE_PORT}/v1/searchqna
+    export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
+    export SEARCH_GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
+
+    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
+
+    # Start Docker Containers
+    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
+    n=0
+    until [[ "$n" -ge 100 ]]; do
+        docker logs search-tgi-service > $LOG_PATH/search-tgi-service_start.log
+        if grep -q Connected $LOG_PATH/search-tgi-service_start.log; then
+            break
+        fi
+        sleep 5s
+        n=$((n+1))
+    done
+}
+
+
+function validate_megaservice() {
+    result=$(http_proxy="" curl http://${ip_address}:3008/v1/searchqna -XPOST -d '{"messages": "What is black myth wukong?", "stream": "False"}' -H 'Content-Type: application/json')
+    echo $result
+
+    if [[ $result == *"the"* ]]; then
+        docker logs search-web-retriever-server
+        docker logs search-backend-server
+        echo "Result correct."
+    else
+        docker logs search-web-retriever-server
+        docker logs search-backend-server
+        echo "Result wrong."
+        exit 1
+    fi
+
+}
+
+function validate_frontend() {
+    cd $WORKPATH/ui/svelte
+    local conda_env_name="OPEA_e2e"
+    export PATH=${HOME}/miniconda3/bin/:$PATH
+    if conda info --envs | grep -q "$conda_env_name"; then
+        echo "$conda_env_name exist!"
+    else
+        conda create -n ${conda_env_name} python=3.12 -y
+    fi
+    source activate ${conda_env_name}
+
+    sed -i "s/localhost/$ip_address/g" playwright.config.ts
+
+    conda install -c conda-forge nodejs=22.6.0 -y
+    npm install && npm ci && npx playwright install --with-deps
+    node -v && npm -v && pip list
+
+    exit_status=0
+    npx playwright test || exit_status=$?
+
+    if [ $exit_status -ne 0 ]; then
+       echo "[TEST INFO]: ---------frontend test failed---------"
+       exit $exit_status
+    else
+       echo "[TEST INFO]: ---------frontend test passed---------"
+    fi
+}
+
+function stop_docker() {
+    cd $WORKPATH/docker_compose/amd/gpu/rocm/
+    docker compose stop && docker compose rm -f
+}
+
+function main() {
+
+    stop_docker
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    start_services
+
+    validate_megaservice
+    validate_frontend
+
+    stop_docker
+    echo y | docker system prune
+
+}
+
+main