From 6d3a017609c5970cd56a8ff60dc6a27098209b6e Mon Sep 17 00:00:00 2001 From: Artem Astafev Date: Fri, 15 Nov 2024 16:24:06 +0700 Subject: [PATCH] Add compose example for ChatQnA AMD ROCm deployment (#1122) Signed-off-by: Artem Astafev Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> --- ChatQnA/docker_compose/amd/gpu/rocm/README.md | 432 ++++++++++++++++++ .../docker_compose/amd/gpu/rocm/compose.yaml | 183 ++++++++ .../docker_compose/amd/gpu/rocm/set_env.sh | 34 ++ ChatQnA/tests/test_compose_on_rocm.sh | 265 +++++++++++ 4 files changed, 914 insertions(+) create mode 100644 ChatQnA/docker_compose/amd/gpu/rocm/README.md create mode 100644 ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml create mode 100644 ChatQnA/docker_compose/amd/gpu/rocm/set_env.sh create mode 100644 ChatQnA/tests/test_compose_on_rocm.sh diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/README.md b/ChatQnA/docker_compose/amd/gpu/rocm/README.md new file mode 100644 index 000000000..9e18d0f61 --- /dev/null +++ b/ChatQnA/docker_compose/amd/gpu/rocm/README.md @@ -0,0 +1,432 @@ +# Build and deploy CodeGen Application on AMD GPU (ROCm) + +## Build MegaService of ChatQnA on AMD ROCm GPU + +This document outlines the deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on AMD ROCm GPU platform. The steps include Docker image creation, container deployment via Docker Compose, and service execution to integrate microservices such as embedding, retriever, rerank, and llm. We will publish the Docker images to Docker Hub, it will simplify the deployment process for this service. + +Quick Start Deployment Steps: + +1. Set up the environment variables. +2. Run Docker Compose. +3. Consume the ChatQnA Service. + +## Quick Start: 1.Setup Environment Variable + +To set up environment variables for deploying ChatQnA services, follow these steps: + +1. Set the required environment variables: + + ```bash + # Example: host_ip="192.168.1.1" + export HOST_IP=${host_ip} + # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1" + export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token} + ``` + +2. If you are in a proxy environment, also set the proxy-related environment variables: + + ```bash + export http_proxy="Your_HTTP_Proxy" + export https_proxy="Your_HTTPs_Proxy" + ``` + +3. Set up other environment variables: + + ```bash + source ./set_env.sh + ``` + +## Quick Start: 2.Run Docker Compose + +```bash +docker compose up -d +``` + +It will automatically download the docker image on `docker hub`: + +```bash +docker pull opea/chatqna:latest +docker pull opea/chatqna-ui:latest +``` + +In following cases, you could build docker image from source by yourself. + +- Failed to download the docker image. + +- If you want to use a specific version of Docker image. + +Please refer to 'Build Docker Images' in below. + +## QuickStart: 3.Consume the ChatQnA Service + +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 +# upload pdf file with dataprep +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F "files=@./nke-10k-2023.pdf" +``` + +Get MegaSerice(backend) response: + +```bash +curl http://${host_ip}:8888/v1/chatqna \ + -H "Content-Type: application/json" \ + -d '{ + "messages": "What is the revenue of Nike in 2023?" + }' +``` + +## 🚀 Build Docker Images + +First of all, you need to build Docker Images locally. This step can be ignored after the Docker images published to Docker hub. + +### 1. Source Code install GenAIComps + +```bash +git clone https://github.com/opea-project/GenAIComps.git +cd GenAIComps +``` + +### 2. Build Retriever Image + +```bash +docker build --no-cache -t opea/retriever-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/redis/langchain/Dockerfile . +``` + +### 3. Build Dataprep Image + +```bash +docker build --no-cache -t opea/dataprep-redis:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/redis/langchain/Dockerfile . +``` + +### 4. Build MegaService Docker Image + +To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the `chatqna.py` Python script. Build the MegaService Docker image using the command below: + +```bash +git clone https://github.com/opea-project/GenAIExamples.git +cd GenAIExamples/ChatQnA/docker +docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile . +cd ../../.. +``` + +### 5. Build UI Docker Image + +Construct the frontend Docker image using the command below: + +```bash +cd GenAIExamples/ChatQnA/ui +docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile . +cd ../../../.. +``` + +### 6. Build React UI Docker Image (Optional) + +Construct the frontend Docker image using the command below: + +```bash +cd GenAIExamples/ChatQnA/ui +docker build --no-cache -t opea/chatqna-react-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile.react . +cd ../../../.. +``` + +### 7. Build Nginx Docker Image + +```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 . +``` + +Then run the command `docker images`, you will have the following 5 Docker Images: + +1. `opea/retriever-redis:latest` +2. `opea/dataprep-redis:latest` +3. `opea/chatqna:latest` +4. `opea/chatqna-ui:latest` or `opea/chatqna-react-ui:latest` +5. `opea/nginx:latest` + +## 🚀 Start MicroServices and MegaService + +### Required Models + +By default, the embedding, reranking and LLM models are set to a default value as listed below: + +| Service | Model | +| --------- | ------------------------- | +| Embedding | BAAI/bge-base-en-v1.5 | +| Reranking | BAAI/bge-reranker-base | +| LLM | Intel/neural-chat-7b-v3-3 | + +Change the `xxx_MODEL_ID` below for your needs. + +### Setup Environment Variables + +1. Set the required environment variables: + + ```bash + # Example: host_ip="192.168.1.1" + export host_ip="External_Public_IP" + # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1" + export no_proxy="Your_No_Proxy" + export CHATQNA_HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token" + # Example: NGINX_PORT=80 + export HOST_IP=${host_ip} + export NGINX_PORT=${your_nginx_port} + export CHATQNA_TGI_SERVICE_IMAGE="ghcr.io/huggingface/text-generation-inference:2.3.1-rocm" + export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" + export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base" + export CHATQNA_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" + export CHATQNA_TGI_SERVICE_PORT=8008 + export CHATQNA_TEI_EMBEDDING_PORT=8090 + export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}" + export CHATQNA_TEI_RERANKING_PORT=8808 + export CHATQNA_REDIS_VECTOR_PORT=16379 + export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001 + export CHATQNA_REDIS_DATAPREP_PORT=6007 + export CHATQNA_REDIS_RETRIEVER_PORT=7000 + export CHATQNA_INDEX_NAME="rag-redis" + export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP} + export CHATQNA_RETRIEVER_SERVICE_HOST_IP=${HOST_IP} + export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://127.0.0.1:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna" + export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep" + export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get_file" + export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete_file" + export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP} + export CHATQNA_FRONTEND_SERVICE_PORT=5173 + export CHATQNA_BACKEND_SERVICE_NAME=chatqna + export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP} + export CHATQNA_BACKEND_SERVICE_PORT=8888 + export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}" + export CHATQNA_EMBEDDING_SERVICE_HOST_IP=${HOST_IP} + export CHATQNA_RERANK_SERVICE_HOST_IP=${HOST_IP} + export CHATQNA_LLM_SERVICE_HOST_IP=${HOST_IP} + export CHATQNA_NGINX_PORT=5176 + ``` + +2. If you are in a proxy environment, also set the proxy-related environment variables: + + ```bash + export http_proxy="Your_HTTP_Proxy" + export https_proxy="Your_HTTPs_Proxy" + ``` + +3. Note: In order to limit access to a subset of GPUs, please pass each device individually using one or more -device /dev/dri/rendered, where is the card index, starting from 128. (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus) into tgi-service in compose.yaml file + +Example for set isolation for 1 GPU + +``` + - /dev/dri/card0:/dev/dri/card0 + - /dev/dri/renderD128:/dev/dri/renderD128 +``` + +Example for set isolation for 2 GPUs + +``` + - /dev/dri/card0:/dev/dri/card0 + - /dev/dri/renderD128:/dev/dri/renderD128 + - /dev/dri/card1:/dev/dri/card1 + - /dev/dri/renderD129:/dev/dri/renderD129 +``` + +Please find more information about accessing and restricting AMD GPUs in the link (https://rocm.docs.amd.com/projects/install-on-linux/en/latest/how-to/docker.html#docker-restrict-gpus) + +4. Set up other environment variables: + + ```bash + source ./set_env.sh + ``` + +### Start all the services Docker Containers + +```bash +cd GenAIExamples/ChatQnA/docker_compose/amd/gpu/rocm +docker compose up -d +``` + +### Validate MicroServices and MegaService + +1. TEI Embedding Service + + ```bash + curl ${host_ip}:8090/embed \ + -X POST \ + -d '{"inputs":"What is Deep Learning?"}' \ + -H 'Content-Type: application/json' + ``` + +2. Retriever Microservice + + To consume the retriever microservice, you need to generate a mock embedding vector by Python script. The length of embedding vector + is determined by the embedding model. + Here we use the model `EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"`, which vector size is 768. + + Check the vecotor dimension of your embedding model, set `your_embedding` dimension equals to it. + + ```bash + export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)") + curl http://${host_ip}:7000/v1/retrieval \ + -X POST \ + -d "{\"text\":\"test\",\"embedding\":${your_embedding}}" \ + -H 'Content-Type: application/json' + ``` + +3. TEI Reranking Service + + ```bash + curl http://${host_ip}:8808/rerank \ + -X POST \ + -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \ + -H 'Content-Type: application/json' + ``` + +4. TGI Service + + In first startup, this service will take more time to download the model files. After it's finished, the service will be ready. + + Try the command below to check whether the TGI service is ready. + + ```bash + docker logs ${CONTAINER_ID} | grep Connected + ``` + + If the service is ready, you will get the response like below. + + ``` + 2024-09-03T02:47:53.402023Z INFO text_generation_router::server: router/src/server.rs:2311: Connected + ``` + + Then try the `cURL` command below to validate TGI. + + ```bash + curl http://${host_ip}:8008/generate \ + -X POST \ + -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":64, "do_sample": true}}' \ + -H 'Content-Type: application/json' + ``` + +5. MegaService + + ```bash + curl http://${host_ip}:8888/v1/chatqna -H "Content-Type: application/json" -d '{ + "messages": "What is the revenue of Nike in 2023?" + }' + ``` + +6. Nginx Service + + ```bash + curl http://${host_ip}:${NGINX_PORT}/v1/chatqna \ + -H "Content-Type: application/json" \ + -d '{"messages": "What is the revenue of Nike in 2023?"}' + ``` + +7. Dataprep Microservice（Optional） + +If you want to update the default knowledge base, you can use the following commands: + +Update Knowledge Base via Local File Upload: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F "files=@./nke-10k-2023.pdf" +``` + +This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment. + +Add Knowledge Base via HTTP Links: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep" \ + -H "Content-Type: multipart/form-data" \ + -F 'link_list=["https://opea.dev"]' +``` + +This command updates a knowledge base by submitting a list of HTTP links for processing. + +Also, you are able to get the file list that you uploaded: + +```bash +curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \ + -H "Content-Type: application/json" +``` + +To delete the file/link you uploaded: + +```bash +# delete link +curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \ + -d '{"file_path": "https://opea.dev"}' \ + -H "Content-Type: application/json" + +# delete file +curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \ + -d '{"file_path": "nke-10k-2023.pdf"}' \ + -H "Content-Type: application/json" + +# delete all uploaded files and links +curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \ + -d '{"file_path": "all"}' \ + -H "Content-Type: application/json" +``` + +## 🚀 Launch the UI + +### Launch with origin port + +To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below: + +```yaml + chaqna-ui-server: + image: opea/chatqna-ui:latest + ... + ports: + - "80:5173" +``` + +### Launch with Nginx + +If you want to launch the UI using Nginx, open this URL: `http://${host_ip}:${NGINX_PORT}` in your browser to access the frontend. + +## 🚀 Launch the Conversational UI (Optional) + +To access the Conversational UI (react based) frontend, modify the UI service in the `compose.yaml` file. Replace `chaqna-ui-server` service with the `chatqna-react-ui-server` service as per the config below: + +```yaml +chatqna-react-ui-server: + image: opea/chatqna-react-ui:latest + container_name: chatqna-react-ui-server + environment: + - APP_BACKEND_SERVICE_ENDPOINT=${BACKEND_SERVICE_ENDPOINT} + - APP_DATA_PREP_SERVICE_URL=${DATAPREP_SERVICE_ENDPOINT} + ports: + - "5174:80" + depends_on: + - chaqna-backend-server + ipc: host + restart: always +``` + +Once the services are up, open the following URL in your browser: http://{host_ip}:5174. By default, the UI runs on port 80 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below: + +```yaml + chaqna-react-ui-server: + image: opea/chatqna-react-ui:latest + ... + ports: + - "80:80" +``` + +![project-screenshot](../../../../assets/img/chat_ui_init.png) + +Here is an example of running ChatQnA: + +![project-screenshot](../../../../assets/img/chat_ui_response.png) + +Here is an example of running ChatQnA with Conversational UI (React): + +![project-screenshot](../../../../assets/img/conversation_ui_response.png) diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml b/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml new file mode 100644 index 000000000..dd0c4ddc7 --- /dev/null +++ b/ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml @@ -0,0 +1,183 @@ +# Copyright (C) 2024 Advanced Micro Devices, Inc. +# SPDX-License-Identifier: Apache-2.0 + +services: + chatqna-redis-vector-db: + image: redis/redis-stack:7.2.0-v9 + container_name: redis-vector-db + ports: + - "${CHATQNA_REDIS_VECTOR_PORT}:6379" + - "${CHATQNA_REDIS_VECTOR_INSIGHT_PORT}:8001" + chatqna-dataprep-redis-service: + image: ${REGISTRY:-opea}/dataprep-redis:${TAG:-latest} + container_name: dataprep-redis-server + depends_on: + - chatqna-redis-vector-db + - chatqna-tei-embedding-service + ports: + - "${CHATQNA_REDIS_DATAPREP_PORT}:6007" + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + REDIS_URL: ${CHATQNA_REDIS_URL} + INDEX_NAME: ${CHATQNA_INDEX_NAME} + TEI_ENDPOINT: ${CHATQNA_TEI_EMBEDDING_ENDPOINT} + HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + chatqna-tei-embedding-service: + image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 + container_name: chatqna-tei-embedding-server + ports: + - "${CHATQNA_TEI_EMBEDDING_PORT}:80" + volumes: + - "/var/opea/chatqna-service/data:/data" + shm_size: 1g + ipc: host + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + command: --model-id ${CHATQNA_EMBEDDING_MODEL_ID} --auto-truncate + devices: + - /dev/kfd:/dev/kfd + - /dev/dri/card1:/dev/dri/card1 + - /dev/dri/renderD136:/dev/dri/renderD136 + cap_add: + - SYS_PTRACE + group_add: + - video + security_opt: + - seccomp:unconfined + chatqna-retriever: + image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest} + container_name: chatqna-retriever-redis-server + depends_on: + - chatqna-redis-vector-db + ports: + - "${CHATQNA_REDIS_RETRIEVER_PORT}:7000" + ipc: host + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + REDIS_URL: ${CHATQNA_REDIS_URL} + INDEX_NAME: ${CHATQNA_INDEX_NAME} + TEI_EMBEDDING_ENDPOINT: ${CHATQNA_TEI_EMBEDDING_ENDPOINT} + restart: unless-stopped + chatqna-tei-reranking-service: + image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 + container_name: chatqna-tei-reranking-server + ports: + - "${CHATQNA_TEI_RERANKING_PORT}:80" + volumes: + - "/var/opea/chatqna-service/data:/data" + shm_size: 1g + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + HF_HUB_DISABLE_PROGRESS_BARS: 1 + HF_HUB_ENABLE_HF_TRANSFER: 0 + devices: + - /dev/kfd:/dev/kfd + - /dev/dri/:/dev/dri/ + cap_add: + - SYS_PTRACE + group_add: + - video + security_opt: + - seccomp:unconfined + command: --model-id ${CHATQNA_RERANK_MODEL_ID} --auto-truncate + chatqna-tgi-service: + image: ${CHATQNA_TGI_SERVICE_IMAGE} + container_name: chatqna-tgi-server + ports: + - "${CHATQNA_TGI_SERVICE_PORT}:80" + environment: + no_proxy: ${no_proxy} + http_proxy: ${http_proxy} + https_proxy: ${https_proxy} + HUGGINGFACEHUB_API_TOKEN: ${CHATQNA_HUGGINGFACEHUB_API_TOKEN} + HF_HUB_DISABLE_PROGRESS_BARS: 1 + HF_HUB_ENABLE_HF_TRANSFER: 0 + volumes: + - "/var/opea/chatqna-service/data:/data" + shm_size: 1g + devices: + - /dev/kfd:/dev/kfd + - /dev/dri/:/dev/dri/ + cap_add: + - SYS_PTRACE + group_add: + - video + security_opt: + - seccomp:unconfined + command: --model-id ${CHATQNA_LLM_MODEL_ID} + ipc: host + chatqna-backend-server: + image: ${REGISTRY:-opea}/chatqna:${TAG:-latest} + container_name: chatqna-backend-server + depends_on: + - chatqna-redis-vector-db + - chatqna-tei-embedding-service + - chatqna-retriever + - chatqna-tei-reranking-service + - chatqna-tgi-service + ports: + - "${CHATQNA_BACKEND_SERVICE_PORT}:8888" + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + - MEGA_SERVICE_HOST_IP=${CHATQNA_MEGA_SERVICE_HOST_IP} + - EMBEDDING_SERVER_HOST_IP=${HOST_IP} + - EMBEDDING_SERVER_PORT=${CHATQNA_TEI_EMBEDDING_PORT:-80} + - RETRIEVER_SERVICE_HOST_IP=${HOST_IP} + - RERANK_SERVER_HOST_IP=${HOST_IP} + - RERANK_SERVER_PORT=${CHATQNA_TEI_RERANKING_PORT:-80} + - LLM_SERVER_HOST_IP=${HOST_IP} + - LLM_SERVER_PORT=${CHATQNA_TGI_SERVICE_PORT:-80} + - LLM_MODEL=${CHATQNA_LLM_MODEL_ID} + ipc: host + restart: always + chatqna-ui-server: + image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest} + container_name: chatqna-ui-server + depends_on: + - chatqna-backend-server + ports: + - "${CHATQNA_FRONTEND_SERVICE_PORT}:5173" + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + - CHAT_BASE_URL=${CHATQNA_BACKEND_SERVICE_ENDPOINT} + - UPLOAD_FILE_BASE_URL=${CHATQNA_DATAPREP_SERVICE_ENDPOINT} + - GET_FILE=${CHATQNA_DATAPREP_GET_FILE_ENDPOINT} + - DELETE_FILE=${CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT} + ipc: host + restart: always + chatqna-nginx-server: + image: ${REGISTRY:-opea}/nginx:${TAG:-latest} + container_name: chaqna-nginx-server + depends_on: + - chatqna-backend-server + - chatqna-ui-server + ports: + - "${CHATQNA_NGINX_PORT}:80" + environment: + - no_proxy=${no_proxy} + - https_proxy=${https_proxy} + - http_proxy=${http_proxy} + - FRONTEND_SERVICE_IP=${CHATQNA_FRONTEND_SERVICE_IP} + - FRONTEND_SERVICE_PORT=${CHATQNA_FRONTEND_SERVICE_PORT} + - BACKEND_SERVICE_NAME=${CHATQNA_BACKEND_SERVICE_NAME} + - BACKEND_SERVICE_IP=${CHATQNA_BACKEND_SERVICE_IP} + - BACKEND_SERVICE_PORT=${CHATQNA_BACKEND_SERVICE_PORT} + ipc: host + restart: always + +networks: + default: + driver: bridge diff --git a/ChatQnA/docker_compose/amd/gpu/rocm/set_env.sh b/ChatQnA/docker_compose/amd/gpu/rocm/set_env.sh new file mode 100644 index 000000000..0a581dc86 --- /dev/null +++ b/ChatQnA/docker_compose/amd/gpu/rocm/set_env.sh @@ -0,0 +1,34 @@ +#!/usr/bin/env bash + +# Copyright (C) 2024 Advanced Micro Devices, Inc. +# SPDX-License-Identifier: Apache-2.0 + +export CHATQNA_TGI_SERVICE_IMAGE="ghcr.io/huggingface/text-generation-inference:2.3.1-rocm" +export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" +export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base" +export CHATQNA_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" +export CHATQNA_TGI_SERVICE_PORT=18008 +export CHATQNA_TEI_EMBEDDING_PORT=18090 +export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}" +export CHATQNA_TEI_RERANKING_PORT=18808 +export CHATQNA_REDIS_VECTOR_PORT=16379 +export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001 +export CHATQNA_REDIS_DATAPREP_PORT=6007 +export CHATQNA_REDIS_RETRIEVER_PORT=7000 +export CHATQNA_INDEX_NAME="rag-redis" +export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_RETRIEVER_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://127.0.0.1:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna" +export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep" +export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get_file" +export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete_file" +export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP} +export CHATQNA_FRONTEND_SERVICE_PORT=15173 +export CHATQNA_BACKEND_SERVICE_NAME=chatqna +export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP} +export CHATQNA_BACKEND_SERVICE_PORT=18888 +export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}" +export CHATQNA_EMBEDDING_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_RERANK_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_LLM_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_NGINX_PORT=15176 diff --git a/ChatQnA/tests/test_compose_on_rocm.sh b/ChatQnA/tests/test_compose_on_rocm.sh new file mode 100644 index 000000000..6518578e6 --- /dev/null +++ b/ChatQnA/tests/test_compose_on_rocm.sh @@ -0,0 +1,265 @@ +#!/bin/bash +# Copyright (C) 2024 Advanced Micro Devices, Inc. +# 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 $1}') + +export HOST_IP=${ip_address} +export CHATQNA_TGI_SERVICE_IMAGE="ghcr.io/huggingface/text-generation-inference:2.3.1-rocm" +export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" +export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base" +export CHATQNA_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" +export CHATQNA_TGI_SERVICE_PORT=9009 +export CHATQNA_TEI_EMBEDDING_PORT=8090 +export CHATQNA_TEI_EMBEDDING_ENDPOINT="http://${HOST_IP}:${CHATQNA_TEI_EMBEDDING_PORT}" +export CHATQNA_TEI_RERANKING_PORT=8808 +export CHATQNA_REDIS_VECTOR_PORT=6379 +export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001 +export CHATQNA_REDIS_DATAPREP_PORT=6007 +export CHATQNA_REDIS_RETRIEVER_PORT=7000 +export CHATQNA_INDEX_NAME="rag-redis" +export CHATQNA_MEGA_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_RETRIEVER_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_BACKEND_SERVICE_ENDPOINT="http://127.0.0.1:${CHATQNA_BACKEND_SERVICE_PORT}/v1/chatqna" +export CHATQNA_DATAPREP_SERVICE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep" +export CHATQNA_DATAPREP_GET_FILE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/get_file" +export CHATQNA_DATAPREP_DELETE_FILE_ENDPOINT="http://127.0.0.1:${CHATQNA_REDIS_DATAPREP_PORT}/v1/dataprep/delete_file" +export CHATQNA_FRONTEND_SERVICE_IP=${HOST_IP} +export CHATQNA_FRONTEND_SERVICE_PORT=15173 +export CHATQNA_BACKEND_SERVICE_NAME=chatqna +export CHATQNA_BACKEND_SERVICE_IP=${HOST_IP} +export CHATQNA_BACKEND_SERVICE_PORT=8888 +export CHATQNA_REDIS_URL="redis://${HOST_IP}:${CHATQNA_REDIS_VECTOR_PORT}" +export CHATQNA_EMBEDDING_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_RERANK_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_LLM_SERVICE_HOST_IP=${HOST_IP} +export CHATQNA_NGINX_PORT=80 +export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} +export PATH="/home/huggingface/miniconda3/bin:$PATH" + +function build_docker_images() { + cd "$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="chatqna chatqna-ui chatqna-conversation-ui dataprep-redis retriever-redis nginx" + 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 images && sleep 1s +} + +function start_services() { + cd "$WORKPATH"/docker_compose/amd/gpu/rocm + + # Start Docker Containers + docker compose -f compose.yaml up -d > "${LOG_PATH}"/start_services_with_compose.log + + n=0 + until [[ "$n" -ge 500 ]]; do + docker logs chatqna-tgi-server > "${LOG_PATH}"/tgi_service_start.log + if grep -q Connected "${LOG_PATH}"/tgi_service_start.log; then + break + fi + sleep 1s + n=$((n+1)) + done +} + +function validate_service() { + local URL="$1" + local EXPECTED_RESULT="$2" + local SERVICE_NAME="$3" + local DOCKER_NAME="$4" + local INPUT_DATA="$5" + + if [[ $SERVICE_NAME == *"dataprep_upload_file"* ]]; then + cd "$LOG_PATH" + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'files=@./dataprep_file.txt' -H 'Content-Type: multipart/form-data' "$URL") + elif [[ $SERVICE_NAME == *"dataprep_upload_link"* ]]; then + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -F 'link_list=["https://www.ces.tech/"]' "$URL") + elif [[ $SERVICE_NAME == *"dataprep_get"* ]]; then + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -H 'Content-Type: application/json' "$URL") + elif [[ $SERVICE_NAME == *"dataprep_del"* ]]; then + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d '{"file_path": "all"}' -H 'Content-Type: application/json' "$URL") + else + HTTP_RESPONSE=$(curl --silent --write-out "HTTPSTATUS:%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL") + fi + HTTP_STATUS=$(echo "$HTTP_RESPONSE" | tr -d '\n' | sed -e 's/.*HTTPSTATUS://') + RESPONSE_BODY=$(echo "$HTTP_RESPONSE" | sed -e 's/HTTPSTATUS\:.*//g') + + docker logs "${DOCKER_NAME}" >> "${LOG_PATH}"/"${SERVICE_NAME}".log + + # check response status + if [ "$HTTP_STATUS" -ne "200" ]; then + echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS" + exit 1 + else + echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..." + fi + # check response body + if [[ "$RESPONSE_BODY" != *"$EXPECTED_RESULT"* ]]; then + echo "[ $SERVICE_NAME ] Content does not match the expected result: $RESPONSE_BODY" + exit 1 + else + echo "[ $SERVICE_NAME ] Content is as expected." + fi + + sleep 1s +} + +function validate_microservices() { + # Check if the microservices are running correctly. + + # tei for embedding service + validate_service \ + "${ip_address}:8090/embed" \ + "[[" \ + "tei-embedding" \ + "chatqna-tei-embedding-server" \ + '{"inputs":"What is Deep Learning?"}' + + sleep 1m # retrieval can't curl as expected, try to wait for more time + + # test /v1/dataprep upload file + echo "Deep learning is a subset of machine learning that utilizes neural networks with multiple layers to analyze various levels of abstract data representations. It enables computers to identify patterns and make decisions with minimal human intervention by learning from large amounts of data." > "$LOG_PATH"/dataprep_file.txt + validate_service \ + "http://${ip_address}:6007/v1/dataprep" \ + "Data preparation succeeded" \ + "dataprep_upload_file" \ + "dataprep-redis-server" + + # test /v1/dataprep upload link + validate_service \ + "http://${ip_address}:6007/v1/dataprep" \ + "Data preparation succeeded" \ + "dataprep_upload_link" \ + "dataprep-redis-server" + + # test /v1/dataprep/get_file + validate_service \ + "http://${ip_address}:6007/v1/dataprep/get_file" \ + '{"name":' \ + "dataprep_get" \ + "dataprep-redis-server" + + # test /v1/dataprep/delete_file + validate_service \ + "http://${ip_address}:6007/v1/dataprep/delete_file" \ + '{"status":true}' \ + "dataprep_del" \ + "dataprep-redis-server" + + # retrieval microservice + test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)") + validate_service \ + "${ip_address}:7000/v1/retrieval" \ + "retrieved_docs" \ + "retrieval-microservice" \ + "chatqna-retriever-redis-server" \ + "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}" + + # tei for rerank microservice + validate_service \ + "${ip_address}:8808/rerank" \ + '{"index":1,"score":' \ + "tei-rerank" \ + "chatqna-tei-reranking-server" \ + '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' + + # tgi for llm service + validate_service \ + "${ip_address}:9009/generate" \ + "generated_text" \ + "tgi-llm" \ + "chatqna-tgi-server" \ + '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' + +} + +function validate_megaservice() { + # Curl the Mega Service + validate_service \ + "${ip_address}:8888/v1/chatqna" \ + "data: " \ + "chatqna-megaservice" \ + "chatqna-backend-server" \ + '{"messages": "What is the revenue of Nike in 2023?"}' + +} + +function validate_frontend() { + echo "[ TEST INFO ]: --------- frontend test started ---------" + cd "$WORKPATH"/ui/svelte + local conda_env_name="OPEA_e2e" + export PATH=${HOME}/miniforge3/bin/:$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 ${conda_env_name} + echo "[ TEST INFO ]: --------- conda env activated ---------" + + sed -i "s/localhost/$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 [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi + start_time=$(date +%s) + start_services + end_time=$(date +%s) + duration=$((end_time-start_time)) + echo "Mega service start duration is $duration s" && sleep 1s + + + if [ "${mode}" == "perf" ]; then + python3 "$WORKPATH"/tests/chatqna_benchmark.py + elif [ "${mode}" == "" ]; then + validate_microservices + echo "==== microservices validated ====" + validate_megaservice + echo "==== megaservice validated ====" + validate_frontend + echo "==== frontend validated ====" + fi + + stop_docker + echo y | docker system prune + +} + +main