Build Mega Service of ChatQnA (with Qdrant) 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.
🚀 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 the power of 4th Generation Intel Xeon Scalable processors. 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.
Certain ports in the EC2 instance need to opened up in the security group, for the microservices to work with the curl commands
See one example below. Please open up these ports in the EC2 instance based on the IP addresses you want to allow
qdrant-vector-db
===============
Port 6333 - Open to 0.0.0.0/0
Port 6334 - Open to 0.0.0.0/0
dataprep-qdrant-server
======================
Port 6043 - Open to 0.0.0.0/0
tei_embedding_service
=====================
Port 6040 - Open to 0.0.0.0/0
embedding
=========
Port 6044 - Open to 0.0.0.0/0
retriever
=========
Port 6045 - Open to 0.0.0.0/0
tei_reranking_service
================
Port 6041 - Open to 0.0.0.0/0
reranking
=========
Port 6046 - Open to 0.0.0.0/0
tgi-service
===========
Port 6042 - Open to 0.0.0.0/0
llm
===
Port 6047 - Open to 0.0.0.0/0
chaqna-xeon-backend-server
==========================
Port 8912 - Open to 0.0.0.0/0
chaqna-xeon-ui-server
=====================
Port 5173 - Open to 0.0.0.0/0
🚀 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-qdrant:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/qdrant/haystack/Dockerfile .
2. Build Dataprep Image¶
docker build --no-cache -t opea/dataprep-qdrant:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/qdrant/langchain/Dockerfile .
cd ..
3. Build MegaService Docker Image¶
To construct the Mega Service, 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 .
cd ../../..
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 .
cd ../../../..
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
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8912/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6043/v1/dataprep"
docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg BACKEND_SERVICE_ENDPOINT=$BACKEND_SERVICE_ENDPOINT --build-arg DATAPREP_SERVICE_ENDPOINT=$DATAPREP_SERVICE_ENDPOINT -f ./docker/Dockerfile.react .
cd ../../../..
Then run the command docker images
, you will have the following 4 Docker Images:
opea/dataprep-qdrant:latest
opea/retriever-qdrant:latest
opea/chatqna:latest
opea/chatqna-ui: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.
Setup Environment Variables¶
Since the compose.yaml
will consume some environment variables, you need to setup them in advance as below.
Export the value of the public IP address of your Xeon server to the host_ip
environment variable
Change the External_Public_IP below with the actual IPV4 value
export host_ip="External_Public_IP"
Export the value of your Huggingface API token to the your_hf_api_token
environment variable
Change the Your_Huggingface_API_Token below with tyour actual Huggingface API Token value
export your_hf_api_token="Your_Huggingface_API_Token"
Append the value of the public IP address to the no_proxy list
export your_no_proxy=${your_no_proxy},"External_Public_IP"
export no_proxy=${your_no_proxy}
export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6040"
export QDRANT_HOST=${host_ip}
export QDRANT_PORT=6333
export INDEX_NAME="rag-qdrant"
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_SERVER_HOST_IP=${host_ip}
export MEGA_SERVICE_HOST_IP=${host_ip}
export RETRIEVER_SERVICE_HOST_IP=${host_ip}
export RERANK_SERVER_HOST_IP=${host_ip}
export LLM_SERVER_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8912/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6043/v1/dataprep"
Note: Please replace with host_ip
with you external IP address, do not use localhost.
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/
docker compose -f compose_qdrant.yaml up -d
Validate Microservices¶
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 ${host_ip}:6040/embed \ -X POST \ -d '{"inputs":"What is Deep Learning?"}' \ -H 'Content-Type: application/json'
Retriever Microservice
To consume the retriever microservice, you need to generate a mock embedding vector by Python script. The length of embedding vector is determined by the embedding model. Here we use the model
EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
, which vector size is 768.Check the vecotor dimension of your embedding model, set
your_embedding
dimension equals to it.export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)") curl http://${host_ip}:6045/v1/retrieval \ -X POST \ -d '{"text":"What is the revenue of Nike in 2023?","embedding":"'"${your_embedding}"'"}' \ -H 'Content-Type: application/json'
TEI Reranking Service
curl http://${host_ip}:6041/rerank \ -X POST \ -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \ -H 'Content-Type: application/json'
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.
docker logs ${CONTAINER_ID} | grep Connected
If the service is ready, you will get the response like below.
2024-09-03T02:47:53.402023Z INFO text_generation_router::server: router/src/server.rs:2311: Connected
Then try the
cURL
command below to validate TGI.curl http://${host_ip}:6042/generate \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \ -H 'Content-Type: application/json'
MegaService
curl http://${host_ip}:8912/v1/chatqna -H "Content-Type: application/json" -d '{ "messages": "What is the revenue of Nike in 2023?" }'
Dataprep Microservice(Optional)
If you want to update the default knowledge base, you can use the following commands:
Update Knowledge Base via Local File Upload:
curl -X POST "http://${host_ip}:6043/v1/dataprep" \ -H "Content-Type: multipart/form-data" \ -F "files=@./your_file.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}:6043/v1/dataprep" \ -H "Content-Type: multipart/form-data" \ -F 'link_list=["https://opea.dev"]'
🚀 Launch the UI¶
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 the Conversational UI (react)¶
To access the Conversational UI frontend, 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-xeon-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):