AI Assistant Configuration

Vector Library Service

Please contact the after-sales staff to obtain the deployment script.

Start Service

bash deploy.sh -m start
# When you see "start success", it indicates that the service has started normally.

Stop Service

bash deploy.sh -m stop

Stop Service (Clean Containers)

bash deploy.sh -m down

Check Running Status

bash deploy.sh -m status

Change HENGSHI Service Configuration (Requires Restarting HENGSHI Service)

Standalone Deployment
Modify the /opt/hengshi/conf/hengshi-sense-env.sh file
Uncomment the VECTOR_DB_URL and VECTOR_ENDPOINT variables

export VECTOR_DB_URL="jdbc:postgresql://<SERVER_IP>:54321/postgres?user=postgres&password=postgres&useUnicode=true&characterEncoding=utf8"
export VECTOR_ENDPOINT="http://<SERVER_IP>:3000/v1/embeddings"

Docker Deployment
Enter the deployment directory docker-compose-x.x, use vi/vim to open the .env file and add the following parameters.

# VECTOR_DB
VECTOR_DB_URL="jdbc:postgresql://<SERVER_IP>:54321/postgres?user=postgres&password=postgres&useUnicode=true&characterEncoding=utf8"
VECTOR_ENDPOINT="http://<SERVER_IP>:3000/v1/embeddings"

K8s Deployment
Edit the configmap named "hengshi-sense" in the namespace where HENGSHI is deployed, and add the following parameters.

VECTOR_DB_URL: "jdbc:postgresql://<SERVER_IP>:54321/postgres?user=postgres&password=postgres&useUnicode=true&characterEncoding=utf8"
VECTOR_ENDPOINT: "http://<SERVER_IP>:3000/v1/embeddings"

Note:

Please replace <SERVER_IP> with the IP address of the deployment machine. You can view the current machine's IP address using the ifconfig command, or configure it as the Service address for K8s deployment.

Restart Operation

Standalone

# Please replace the path with the current deployment path of HENGSHI SENSE, default is /opt/hengshi
/opt/hengshi/bin/hengshi-sense-bin restart hengshi

Docker

# For Docker deployment, execute docker-compose down followed by docker-compose up -d to reapply new configurations
cd docker-compose-x.x
docker-compose down
docker-compose up -d

Kubernetes

# Please replace [namespace] with the actual deployment namespace, and replicas with the actual number of pods, default is 1
kubectl -n [namespace] scale deployment hengshi --replicas=0
kubectl -n [namespace] scale deployment hengshi --replicas=1