Add compose example for DocSum amd rocm deployment

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

@@ -0,0 +1,112 @@
+## 🚀 Start Microservices and MegaService
+
+### Required Models
+
+Default model is "Intel/neural-chat-7b-v3-3". Change "LLM_MODEL_ID" in environment variables below if you want to use another model.
+For gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) in "HUGGINGFACEHUB_API_TOKEN" environment variable.
+
+### Setup Environment Variables
+
+Since the `compose.yaml` will consume some environment variables, you need to setup them in advance as below.
+
+```bash
+export DOCSUM_TGI_IMAGE="ghcr.io/huggingface/text-generation-inference:2.3.1-rocm"
+export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export HOST_IP=${host_ip}
+export DOCSUM_TGI_SERVICE_PORT="18882"
+export DOCSUM_TGI_LLM_ENDPOINT="http://${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}"
+export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export DOCSUM_LLM_SERVER_PORT="8008"
+export DOCSUM_BACKEND_SERVER_PORT="8888"
+export DOCSUM_FRONTEND_PORT="5173"
+```
+
+Note: Please replace with `host_ip` with your external IP address, do not use localhost.
+
+Note: In order to limit access to a subset of GPUs, please pass each device individually using one or more -device /dev/dri/rendered<node>, where <node> 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)
+
+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)
+
+### Start Microservice Docker Containers
+
+```bash
+cd GenAIExamples/DocSum/docker_compose/amd/gpu/rocm
+docker compose up -d
+```
+
+### Validate Microservices
+
+1. TGI Service
+
+   ```bash
+   curl http://${host_ip}:8008/generate \
+     -X POST \
+     -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":64, "do_sample": true}}' \
+     -H 'Content-Type: application/json'
+   ```
+
+2. LLM Microservice
+
+   ```bash
+   curl http://${host_ip}:9000/v1/chat/docsum \
+     -X POST \
+     -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \
+     -H 'Content-Type: application/json'
+   ```
+
+3. MegaService
+
+   ```bash
+   curl http://${host_ip}:8888/v1/docsum -H "Content-Type: application/json" -d '{
+        "messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5.","max_tokens":32, "language":"en", "stream":false
+        }'
+   ```
+
+## 🚀 Launch the Svelte UI
+
+Open this URL `http://{host_ip}:5173` in your browser to access the frontend.
+
+![project-screenshot](https://github.com/intel-ai-tce/GenAIExamples/assets/21761437/93b1ed4b-4b76-4875-927e-cc7818b4825b)
+
+Here is an example for summarizing a article.
+
+![image](https://github.com/intel-ai-tce/GenAIExamples/assets/21761437/67ecb2ec-408d-4e81-b124-6ded6b833f55)
+
+## 🚀 Launch the React UI (Optional)
+
+To access the React-based frontend, modify the UI service in the `compose.yaml` file. Replace `docsum-rocm-ui-server` service with the `docsum-rocm-react-ui-server` service as per the config below:
+
+```yaml
+docsum-rocm-react-ui-server:
+  image: ${REGISTRY:-opea}/docsum-react-ui:${TAG:-latest}
+  container_name: docsum-rocm-react-ui-server
+  depends_on:
+    - docsum-rocm-backend-server
+  ports:
+    - "5174:80"
+  environment:
+    - no_proxy=${no_proxy}
+    - https_proxy=${https_proxy}
+    - http_proxy=${http_proxy}
+    - DOC_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
+```
+
+Open this URL `http://{host_ip}:5175` in your browser to access the frontend.
+
+![project-screenshot](../../../../assets/img/docsum-ui-react.png)

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

@@ -0,0 +1,89 @@
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  docsum-tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    container_name: docsum-tgi-service
+    ports:
+      - "${DOCSUM_TGI_SERVICE_PORT}:80"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: "http://${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}"
+      HUGGINGFACEHUB_API_TOKEN: ${DOCSUM_HUGGINGFACEHUB_API_TOKEN}
+    volumes:
+      - "/var/opea/docsum-service/data:/data"
+    shm_size: 1g
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/${DOCSUM_CARD_ID}:/dev/dri/${DOCSUM_CARD_ID}
+      - /dev/dri/${DOCSUM_RENDER_ID}:/dev/dri/${DOCSUM_RENDER_ID}
+    cap_add:
+      - SYS_PTRACE
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+    ipc: host
+    command: --model-id ${DOCSUM_LLM_MODEL_ID}
+  docsum-llm-server:
+    image: ${REGISTRY:-opea}/llm-docsum-tgi:latest
+    container_name: docsum-llm-server
+    depends_on:
+      - docsum-tgi-service
+    ports:
+      - "${DOCSUM_LLM_SERVER_PORT}:9000"
+    ipc: host
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+    cap_add:
+      - SYS_PTRACE
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/${DOCSUM_CARD_ID}:/dev/dri/${DOCSUM_CARD_ID}
+      - /dev/dri/${DOCSUM_RENDER_ID}:/dev/dri/${DOCSUM_RENDER_ID}
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: "http://${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}"
+      HUGGINGFACEHUB_API_TOKEN: ${DOCSUM_HUGGINGFACEHUB_API_TOKEN}
+    restart: unless-stopped
+  docsum-backend-server:
+    image: ${REGISTRY:-opea}/docsum:latest
+    container_name: docsum-backend-server
+    depends_on:
+      - docsum-tgi-service
+      - docsum-llm-server
+    ports:
+      - "${DOCSUM_BACKEND_SERVER_PORT}:8888"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - MEGA_SERVICE_HOST_IP=${HOST_IP}
+      - LLM_SERVICE_HOST_IP=${HOST_IP}
+    ipc: host
+    restart: always
+  docsum-ui-server:
+    image: ${REGISTRY:-opea}/docsum-ui:latest
+    container_name: docsum-ui-server
+    depends_on:
+      - docsum-backend-server
+    ports:
+      - "${DOCSUM_FRONTEND_PORT}:5173"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - DOC_BASE_URL="http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge

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

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+export DOCSUM_TGI_IMAGE="ghcr.io/huggingface/text-generation-inference:2.3.1-rocm"
+export DOCSUM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export HOST_IP=${host_ip}
+export DOCSUM_TGI_SERVICE_PORT="8008"
+export DOCSUM_TGI_LLM_ENDPOINT="http://${HOST_IP}:${DOCSUM_TGI_SERVICE_PORT}"
+export DOCSUM_HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export DOCSUM_LLM_SERVER_PORT="9000"
+export DOCSUM_BACKEND_SERVER_PORT="8888"
+export DOCSUM_FRONTEND_PORT="5173"
+export BACKEND_SERVICE_ENDPOINT="http://${HOST_IP}:${DOCSUM_BACKEND_SERVER_PORT}/v1/docsum"