Adding files to deploy CodeGen application on AMD GPU (#1130)

Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

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

@@ -0,0 +1,126 @@
+# Build and deploy CodeGen Application on AMD GPU (ROCm)
+
+## Build images
+
+### Build the LLM Docker Image
+
+```bash
+### Cloning repo
+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 .
+```
+
+### Build the MegaService Docker Image
+
+```bash
+### Cloning repo
+git clone https://github.com/opea-project/GenAIExamples
+cd GenAIExamples/CodeGen
+
+### Build Docker image
+docker build -t opea/codegen:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+```
+
+### Build the UI Docker Image
+
+```bash
+cd GenAIExamples/CodeGen/ui
+### Build UI Docker image
+docker build -t opea/codegen-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
+
+### Build React UI Docker image (React UI allows you to use file uploads)
+docker build --no-cache -t opea/codegen-react-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile.react .
+```
+
+It is recommended to use the React UI as it works for downloading files. The use of React UI is set in the Docker Compose file
+
+## Deploy CodeGen 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/CodeGen/docker_compose/amd/gpu/rocm
+```
+
+### Set environments
+
+In the file "GenAIExamples/CodeGen/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 TGI service
+
+```bash
+curl http://${HOST_IP}:${CODEGEN_TGI_SERVICE_PORT}/generate \
+  -X POST \
+  -d '{"inputs":"Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception.","parameters":{"max_new_tokens":256, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate LLM service
+
+```bash
+curl http://${HOST_IP}:${CODEGEN_LLM_SERVICE_PORT}/v1/chat/completions\
+  -X POST \
+  -d '{"query":"Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception.","max_tokens":256,"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://${HOST_IP}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen -H "Content-Type: application/json" -d '{
+  "messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."
+  }'
+```

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

@@ -0,0 +1,78 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  codegen-tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    container_name: codegen-tgi-service
+    ports:
+      - "${CODEGEN_TGI_SERVICE_PORT:-8028}:80"
+    volumes:
+      - "/var/lib/GenAI/data:/data"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGING_FACE_HUB_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_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 ${CODEGEN_LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
+  codegen-llm-server:
+    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
+    container_name: codegen-llm-server
+    depends_on:
+      - codegen-tgi-service
+    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"
+      HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
+    restart: unless-stopped
+  codegen-backend-server:
+    image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
+    container_name: codegen-backend-server
+    depends_on:
+      - codegen-llm-server
+    ports:
+      - "${CODEGEN_BACKEND_SERVICE_PORT:-7778}:7778"
+    environment:
+      no_proxy: ${no_proxy}
+      https_proxy: ${https_proxy}
+      http_proxy: ${http_proxy}
+      MEGA_SERVICE_HOST_IP: ${CODEGEN_MEGA_SERVICE_HOST_IP}
+      LLM_SERVICE_HOST_IP: "codegen-llm-server"
+    ipc: host
+    restart: always
+  codegen-ui-server:
+    image: ${REGISTRY:-opea}/codegen-ui:${TAG:-latest}
+    container_name: codegen-ui-server
+    depends_on:
+      - codegen-backend-server
+    ports:
+      - "${CODEGEN_UI_SERVICE_PORT:-5173}:5173"
+    environment:
+      no_proxy: ${no_proxy}
+      https_proxy: ${https_proxy}
+      http_proxy: ${http_proxy}
+      BASIC_URL: ${CODEGEN_BACKEND_SERVICE_URL}
+      BACKEND_SERVICE_ENDPOINT: ${CODEGEN_BACKEND_SERVICE_URL}
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge

CodeGen/docker_compose/amd/gpu/rocm/set_env.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+### The IP address or domain name of the server on which the application is running
+export HOST_IP=direct-supercomputer1.powerml.co
+
+### The port of the TGI service. On this port, the TGI service will accept connections
+export CODEGEN_TGI_SERVICE_PORT=8028
+
+### A token for accessing repositories with models
+export CODEGEN_HUGGINGFACEHUB_API_TOKEN=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
+
+### Model ID
+export CODEGEN_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
+
+### The port of the LLM service. On this port, the LLM service will accept connections
+export CODEGEN_LLM_SERVICE_PORT=9000
+
+### The endpoint of the TGI service to which requests to this service will be sent (formed from previously set variables)
+export CODEGEN_TGI_LLM_ENDPOINT="http://${HOST_IP}:${CODEGEN_TGI_SERVICE_PORT}"
+
+### The IP address or domain name of the server for CodeGen MegaService
+export CODEGEN_MEGA_SERVICE_HOST_IP=${HOST_IP}
+
+### The port for CodeGen backend service
+export CODEGEN_BACKEND_SERVICE_PORT=18150
+
+### The URL of CodeGen backend service, used by the frontend service
+export CODEGEN_BACKEND_SERVICE_URL="http://${HOST_IP}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codegen"
+
+### The endpoint of the LLM service to which requests to this service will be sent
+export CODEGEN_LLM_SERVICE_HOST_IP=${HOST_IP}
+
+### The CodeGen service UI port
+export CODEGEN_UI_SERVICE_PORT=18151

CodeGen/tests/test_compose_on_rocm.sh

@@ -0,0 +1,169 @@
+#!/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="codegen codegen-ui llm-tgi"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
+
+    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
+    docker images && sleep 1s
+}
+
+function start_services() {
+    cd $WORKPATH/docker_compose/amd/gpu/rocm/
+
+    export CODEGEN_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
+    export CODEGEN_TGI_SERVICE_PORT=8028
+    export CODEGEN_TGI_LLM_ENDPOINT="http://${ip_address}:${CODEGEN_TGI_SERVICE_PORT}"
+    export CODEGEN_LLM_SERVICE_PORT=9000
+    export CODEGEN_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export CODEGEN_MEGA_SERVICE_HOST_IP=${ip_address}
+    export CODEGEN_LLM_SERVICE_HOST_IP=${ip_address}
+    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
+
+    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 codegen-tgi-service > ${LOG_PATH}/codegen_tgi_service_start.log
+        if grep -q Connected ${LOG_PATH}/codegen_tgi_service_start.log; then
+            break
+        fi
+        sleep 5s
+        n=$((n+1))
+    done
+}
+
+function validate_services() {
+    local URL="$1"
+    local EXPECTED_RESULT="$2"
+    local SERVICE_NAME="$3"
+    local DOCKER_NAME="$4"
+    local INPUT_DATA="$5"
+
+    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
+    if [ "$HTTP_STATUS" -eq 200 ]; then
+        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+
+        local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
+
+        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
+            echo "[ $SERVICE_NAME ] Content is as expected."
+        else
+            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
+            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+            exit 1
+        fi
+    else
+        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
+        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+        exit 1
+    fi
+    sleep 5s
+}
+
+function validate_microservices() {
+    # tgi for llm service
+    validate_services \
+        "${ip_address}:8028/generate" \
+        "generated_text" \
+        "codegen-tgi-service" \
+        "codegen-tgi-service" \
+        '{"inputs":"def print_hello_world():","parameters":{"max_new_tokens":256, "do_sample": true}}'
+
+    # llm microservice
+    validate_services \
+        "${ip_address}:9000/v1/chat/completions" \
+        "data: " \
+        "codegen-llm-server" \
+        "codegen-llm-server" \
+        '{"query":"def print_hello_world():"}'
+
+}
+
+function validate_megaservice() {
+    # Curl the Mega Service
+    validate_services \
+        "${ip_address}:7778/v1/codegen" \
+        "print" \
+        "codegen-backend-server" \
+        "codegen-backend-server" \
+        '{"messages": "def print_hello_world():"}'
+
+}
+
+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 -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_microservices
+    validate_megaservice
+    validate_frontend
+
+    stop_docker
+    echo y | docker system prune
+    cd $WORKPATH
+
+}
+
+main