Skip to content

Latest commit

 

History

History
executable file
·
121 lines (84 loc) · 5.24 KB

README.md

File metadata and controls

executable file
·
121 lines (84 loc) · 5.24 KB
Raw

Build Mega Service of CodeTrans on Xeon

This document outlines the deployment process for a CodeTrans application utilizing the GenAIComps microservice pipeline on Intel Xeon server. The steps include Docker image creation, container deployment via Docker Compose, and service execution using microservices llm. We will publish the Docker images to Docker Hub soon, it will simplify the deployment process for this service.

🚀 Create an AWS Xeon Instance

To run the example on a AWS Xeon instance, start by creating an AWS account if you don't have one already. Then, get started with the EC2 Console. AWS EC2 M7i, C7i, C7i-flex and M7i-flex instances are next-generation compute optimized instances powered by custom 4th Generation Intel Xeon Scalable processors (code named Sapphire Rapids). These instances are optimized for high-performance computing and demanding workloads.

For detailed information about these instance types, you can refer to this link. Once you've chosen the appropriate instance type, proceed with configuring your instance settings, including network configurations, security groups, and storage options.

After launching your instance, you can connect to it using SSH (for Linux instances) or Remote Desktop Protocol (RDP) (for Windows instances). From there, you'll have full access to your Xeon server, allowing you to install, configure, and manage your applications as needed.

🚀 Build Docker Images

First of all, you need to build Docker Images locally and install the python package of it. This step can be ignored after the Docker images published to Docker hub.

1. Install GenAIComps from Source Code

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

2. Build the LLM 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 .

3. Build MegaService Docker Image

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

4. Build UI Docker Image

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

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

  • opea/llm-tgi:latest
  • opea/codetrans:latest
  • opea/codetrans-ui:latest

🚀 Start Microservices

Setup Environment Variables

Since the compose.yaml will consume some environment variables, you need to setup them in advance as below. Notice that the LLM_MODEL_ID indicates the LLM model used for TGI service.

export no_proxy=${your_no_proxy}
export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export LLM_MODEL_ID="HuggingFaceH4/mistral-7b-grok"
export TGI_LLM_ENDPOINT="http://${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}:7777/v1/codetrans"

Start Microservice Docker Containers

cd GenAIExamples/CodeTrans/docker/xeon
docker compose up -d

Validate Microservices

  1. TGI Service
curl http://${host_ip}:8008/generate \
  -X POST \
  -d '{"inputs":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:","parameters":{"max_new_tokens":17, "do_sample": true}}' \
  -H 'Content-Type: application/json'
  1. LLM Microservice
curl http://${host_ip}:9000/v1/chat/completions\
  -X POST \
  -d '{"query":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:"}' \
  -H 'Content-Type: application/json'
  1. MegaService
curl http://${host_ip}:7777/v1/codetrans \
    -H "Content-Type: application/json" \
    -d '{"language_from": "Golang","language_to": "Python","source_code": "package main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n}"}'

Enable LangSmith to Monitor an Application (Optional)

LangSmith offers tools to debug, evaluate, and monitor language models and intelligent agents. It can be used to assess benchmark data for each microservice. Before launching your services with docker compose -f compose.yaml up -d, you need to enable LangSmith tracing by setting the LANGCHAIN_TRACING_V2 environment variable to true and configuring your LangChain API key.

Here's how you can do it:

  1. Install the latest version of LangSmith:
pip install -U langsmith
  1. Set the necessary environment variables:
export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=ls_...