Build Mega Service of ChatQnA on Xeon

This document outlines the deployment process for a ChatQnA application utilizing the GenAIComps microservice pipeline on Intel Xeon server. 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 soon, it will simplify the deployment process for this service.

Quick Start:

Set up the environment variables.
Run Docker Compose.
Consume the ChatQnA Service.

Quick Start: 1.Setup Environment Variable

To set up environment variables for deploying ChatQnA services, follow these steps:

Set the required environment variables:

# Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"

If you are in a proxy environment, also set the proxy-related environment variables:

export http_proxy="Your_HTTP_Proxy"
export https_proxy="Your_HTTPs_Proxy"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy",chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service

Set up other environment variables:
```
source ./set_env.sh
```

Quick Start: 2.Run Docker Compose

docker compose up -d

It will automatically download the docker image on docker hub:

docker pull opea/chatqna:latest
docker pull opea/chatqna-ui:latest

NB: You should build docker image from source by yourself if:

You are developing off the git main branch (as the container's ports in the repo may be different from the published docker image).
You can't download the docker image.
You want to use a specific version of Docker image.

Please refer to 'Build Docker Images' in below.

QuickStart: 3.Consume the ChatQnA Service

curl http://${host_ip}:8888/v1/chatqna \
    -H "Content-Type: application/json" \
    -d '{
        "messages": "What is the revenue of Nike in 2023?"
    }'

🚀 Apply Xeon Server on AWS

To apply a Xeon server on AWS, start by creating an AWS account if you don't have one already. Then, head to the EC2 Console to begin the process. Within the EC2 service, select the Amazon EC2 M7i or M7i-flex instance type to leverage 4th Generation Intel Xeon Scalable processors that are optimized for 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.

Network Port & Security

Access the ChatQnA UI by web browser

It supports to access by 80 port. Please confirm the 80 port is opened in the firewall of EC2 instance.
Access the microservice by tool or API
1. Login to the EC2 instance and access by local IP address and port.
  
  It's recommended and do nothing of the network port setting.
2. Login to a remote client and access by public IP address and port.
  
  You need to open the port of the microservice in the security group setting of firewall of EC2 instance setting.
  
  For detailed guide, please refer to Validate Microservices.
  
  Note, it will increase the risk of security, so please confirm before do it.

🚀 Build Docker Images

First of all, you need to build Docker Images locally and install the python package of it.

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

1. Build Retriever Image

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 .

2. Build Dataprep Image

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 .
cd ..

3. Build MegaService Docker Image

MegaService with Rerank

To construct the Mega Service with Rerank, we utilize the GenAIComps microservice pipeline within the chatqna.py Python script. Build MegaService Docker image via below command:

git clone https://github.com/opea-project/GenAIExamples.git
cd GenAIExamples/ChatQnA
docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .

MegaService without Rerank

To construct the Mega Service without Rerank, we utilize the GenAIComps microservice pipeline within the chatqna_without_rerank.py Python script. Build MegaService Docker image via below command:

git clone https://github.com/opea-project/GenAIExamples.git
cd GenAIExamples/ChatQnA
docker build --no-cache -t opea/chatqna-without-rerank:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile.without_rerank .

4. Build UI Docker Image

Build frontend Docker image via below command:

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 .

5. Build Conversational React UI Docker Image (Optional)

Build frontend Docker image that enables Conversational experience with ChatQnA megaservice via below command:

Export the value of the public IP address of your Xeon server to the host_ip environment variable

cd GenAIExamples/ChatQnA/ui
docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile.react .

6. Build Nginx Docker Image

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:

opea/dataprep-redis:latest
opea/retriever-redis:latest
opea/chatqna:latest or opea/chatqna-without-rerank:latest
opea/chatqna-ui:latest
opea/nginx:latest

🚀 Start Microservices

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.

For users in China who are unable to download models directly from Huggingface, you can use ModelScope or a Huggingface mirror to download models. TGI can load the models either online or offline as described below:

Online

export HF_TOKEN=${your_hf_token}
export HF_ENDPOINT="https://hf-mirror.com"
model_name="Intel/neural-chat-7b-v3-3"
docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu --model-id $model_name

Offline
- Search your model name in ModelScope. For example, check this page for model neural-chat-7b-v3-1.
- Click on Download this model button, and choose one way to download the model to your local path /path/to/model.
- Run the following command to start TGI service.
```
export HF_TOKEN=${your_hf_token}
export model_path="/path/to/model"
docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu --model-id /data
```

Setup Environment Variables

Set the required environment variables:

# Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}

If you are in a proxy environment, also set the proxy-related environment variables:

export http_proxy="Your_HTTP_Proxy"
export https_proxy="Your_HTTPs_Proxy"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy",chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm_service

Set up other environment variables:
```
source ./set_env.sh
```

Start all the services Docker Containers

Before running the docker compose command, you need to be in the folder that has the docker compose yaml file

cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/

If use TGI backend.

# Start ChatQnA with Rerank Pipeline
docker compose -f compose.yaml up -d
# Start ChatQnA without Rerank Pipeline
docker compose -f compose_without_rerank.yaml up -d

If use vLLM backend.

docker compose -f compose_vllm.yaml up -d

Validate Microservices

Note, when verify the microservices by curl or API from remote client, please make sure the ports of the microservices are opened in the firewall of the cloud node.
Follow the instructions to validate MicroServices. For details on how to verify the correctness of the response, refer to how-to-validate_service.

TEI Embedding Service

curl ${host_ip}:6006/embed \
    -X POST \
    -d '{"inputs":"What is Deep Learning?"}' \
    -H 'Content-Type: application/json'

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 vector dimension of your embedding model, set your_embedding dimension equals to it.
```
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'
```

TEI Reranking Service

Skip for ChatQnA without Rerank pipeline

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'

LLM backend 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 LLM serving is ready.

docker logs tgi-service | 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 services.

# TGI service
curl http://${host_ip}:9009/v1/chat/completions \
  -X POST \
  -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
  -H 'Content-Type: application/json'

# vLLM Service
curl http://${host_ip}:9009/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "Intel/neural-chat-7b-v3-3", "messages": [{"role": "user", "content": "What is Deep Learning?"}]}'

MegaService

 curl http://${host_ip}:8888/v1/chatqna -H "Content-Type: application/json" -d '{
       "messages": "What is the revenue of Nike in 2023?"
       }'

Nginx Service

curl http://${host_ip}:${NGINX_PORT}/v1/chatqna \
    -H "Content-Type: application/json" \
    -d '{"messages": "What is the revenue of Nike in 2023?"}'

Dataprep Microservice（Optional）

If you want to update the default knowledge base, you can use the following commands:

Update Knowledge Base via Local File nke-10k-2023.pdf. Or click here to download the file via any web browser. Or run this command to get the file on a terminal.

wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf

Upload:

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:

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:

curl -X POST "http://${host_ip}:6007/v1/dataprep/get_file" \
     -H "Content-Type: application/json"

Then you will get the response JSON like this. Notice that the returned name/id of the uploaded link is https://xxx.txt.

[
  {
    "name": "nke-10k-2023.pdf",
    "id": "nke-10k-2023.pdf",
    "type": "File",
    "parent": ""
  },
  {
    "name": "https://opea.dev.txt",
    "id": "https://opea.dev.txt",
    "type": "File",
    "parent": ""
  }
]

To delete the file/link you uploaded:

The file_path here should be the id get from /v1/dataprep/get_file API.

# delete link
curl -X POST "http://${host_ip}:6007/v1/dataprep/delete_file" \
     -d '{"file_path": "https://opea.dev.txt"}' \
     -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"

Profile Microservices

To further analyze MicroService Performance, users could follow the instructions to profile MicroServices.

1. vLLM backend Service

Users could follow previous section to testing vLLM microservice or ChatQnA MegaService.
By default, vLLM profiling is not enabled. Users could start and stop profiling by following commands.

Start vLLM profiling

curl http://${host_ip}:9009/start_profile \
  -H "Content-Type: application/json" \
  -d '{"model": "Intel/neural-chat-7b-v3-3"}'

Users would see below docker logs from vllm-service if profiling is started correctly.

INFO api_server.py:361] Starting profiler...
INFO api_server.py:363] Profiler started.
INFO:     x.x.x.x:35940 - "POST /start_profile HTTP/1.1" 200 OK

After vLLM profiling is started, users could start asking questions and get responses from vLLM MicroService
or ChatQnA MicroService.

Stop vLLM profiling

By following command, users could stop vLLM profliing and generate a *.pt.trace.json.gz file as profiling result
under /mnt folder in vllm-service docker instance.

# vLLM Service
curl http://${host_ip}:9009/stop_profile \
  -H "Content-Type: application/json" \
  -d '{"model": "Intel/neural-chat-7b-v3-3"}'

Users would see below docker logs from vllm-service if profiling is stopped correctly.

INFO api_server.py:368] Stopping profiler...
INFO api_server.py:370] Profiler stopped.
INFO:     x.x.x.x:41614 - "POST /stop_profile HTTP/1.1" 200 OK

After vllm profiling is stopped, users could use below command to get the *.pt.trace.json.gz file under /mnt folder.

docker cp  vllm-service:/mnt/ .

Check profiling result

Open a web browser and type "chrome://tracing" or "ui.perfetto.dev", and then load the json.gz file, you should be able
to see the vLLM profiling result as below diagram.

🚀 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:

  chaqna-gaudi-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-xeon-ui-server service with the chatqna-xeon-conversation-ui-server service as per the config below:

chaqna-xeon-conversation-ui-server:
  image: opea/chatqna-conversation-ui:latest
  container_name: chatqna-xeon-conversation-ui-server
  environment:
    - APP_BACKEND_SERVICE_ENDPOINT=${BACKEND_SERVICE_ENDPOINT}
    - APP_DATA_PREP_SERVICE_URL=${DATAPREP_SERVICE_ENDPOINT}
  ports:
    - "5174:80"
  depends_on:
    - chaqna-xeon-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:

  chaqna-gaudi-conversation-ui-server:
    image: opea/chatqna-conversation-ui:latest
    ...
    ports:
      - "80:80"

Here is an example of running ChatQnA:

Here is an example of running ChatQnA with Conversational UI (React):

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

README.md

README.md

Build Mega Service of ChatQnA on Xeon

Quick Start: 1.Setup Environment Variable

Quick Start: 2.Run Docker Compose

QuickStart: 3.Consume the ChatQnA Service

🚀 Apply Xeon Server on AWS

Network Port & Security

🚀 Build Docker Images

1. Build Retriever Image

2. Build Dataprep Image

3. Build MegaService Docker Image

4. Build UI Docker Image

5. Build Conversational React UI Docker Image (Optional)

6. Build Nginx Docker Image

🚀 Start Microservices

Required Models

Setup Environment Variables

Start all the services Docker Containers

Validate Microservices

Profile Microservices

1. vLLM backend Service

Start vLLM profiling

Stop vLLM profiling

Check profiling result

🚀 Launch the UI

Launch with origin port

Launch with Nginx

🚀 Launch the Conversational UI (Optional)

Files

README.md

Latest commit

History

README.md

File metadata and controls

Build Mega Service of ChatQnA on Xeon

Quick Start: 1.Setup Environment Variable

Quick Start: 2.Run Docker Compose

QuickStart: 3.Consume the ChatQnA Service

🚀 Apply Xeon Server on AWS

Network Port & Security

🚀 Build Docker Images

1. Build Retriever Image

2. Build Dataprep Image

3. Build MegaService Docker Image

4. Build UI Docker Image

5. Build Conversational React UI Docker Image (Optional)

6. Build Nginx Docker Image

🚀 Start Microservices

Required Models

Setup Environment Variables

Start all the services Docker Containers

Validate Microservices

Profile Microservices

1. vLLM backend Service

Start vLLM profiling

Stop vLLM profiling

Check profiling result

🚀 Launch the UI

Launch with origin port

Launch with Nginx

🚀 Launch the Conversational UI (Optional)