Skip to content

Latest commit

 

History

History
156 lines (110 loc) · 5.64 KB

README.md

File metadata and controls

156 lines (110 loc) · 5.64 KB
Raw

Build MegaService of Document Summarization on Gaudi

This document outlines the deployment process for a Document Summarization application utilizing the GenAIComps microservice pipeline on Intel Gaudi server. The steps include Docker image creation, container deployment via Docker Compose, and service execution to integrate microservices such as llm. We will publish the Docker images to Docker Hub, which will simplify the deployment process for this service.

🚀 Build Docker Images

First of all, you need to build Docker Images locally. This step can be ignored once the Docker images are published to Docker hub.

git clone https://github.com/opea-project/GenAIComps.git
cd GenAIComps

1. Pull TGI Gaudi Image

As TGI Gaudi has been officially published as a Docker image, we simply need to pull it:

docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1

2. Build LLM Image

docker build -t opea/llm-docsum-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/summarization/tgi/Dockerfile .

3. Build MegaService Docker Image

To construct the Mega Service, we utilize the GenAIComps microservice pipeline within the docsum.py Python script. Build the MegaService Docker image using the command below:

git clone https://github.com/opea-project/GenAIExamples
cd GenAIExamples/DocSum/docker
docker build -t opea/docsum:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .

4. Build UI Docker Image

Construct the frontend Docker image using the command below:

cd GenAIExamples/DocSum/docker/ui/
docker build -t opea/docsum-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .

5. Build React UI Docker Image

Build the frontend Docker image via below command:

cd GenAIExamples/DocSum/docker/ui/
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/docsum"
docker build -t opea/docsum-react-ui:latest --build-arg BACKEND_SERVICE_ENDPOINT=$BACKEND_SERVICE_ENDPOINT -f ./docker/Dockerfile.react .

Then run the command docker images, you will have the following Docker Images:

  1. ghcr.io/huggingface/tgi-gaudi:2.0.1
  2. opea/llm-docsum-tgi:latest
  3. opea/docsum:latest
  4. opea/docsum-ui:latest
  5. opea/docsum-react-ui:latest

🚀 Start Microservices and MegaService

Required Models

We set default model as "Intel/neural-chat-7b-v3-3", change "LLM_MODEL_ID" in following setting if you want to use other models. If use gated models, you also need to provide huggingface token to "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.

export no_proxy=${your_no_proxy}
export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TGI_LLM_ENDPOINT="http://${host_ip}:8008"
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/docsum"

Note: Please replace with host_ip with your external IP address, do not use localhost.

Start Microservice Docker Containers

cd GenAIExamples/DocSum/docker/gaudi
docker compose up -d

Validate Microservices

  1. TGI Service
curl http://${your_ip}:8008/generate \
  -X POST \
  -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":64, "do_sample": true}}' \
  -H 'Content-Type: application/json'
  1. LLM Microservice
curl http://${your_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'
  1. MegaService
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."
     }'

🚀 Launch the Svelte UI

Open this URL http://{host_ip}:5173 in your browser to access the frontend.

project-screenshot

Here is an example for summarizing a article.

image

🚀 Launch the React UI (Optional)

To access the React-based frontend, modify the UI service in the compose.yaml file. Replace docsum-xeon-ui-server service with the docsum-xeon-react-ui-server service as per the config below:

docsum-gaudi-react-ui-server:
  image: ${REGISTRY:-opea}/docsum-react-ui:${TAG:-latest}
  container_name: docsum-gaudi-react-ui-server
  depends_on:
    - docsum-gaudi-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