Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 18:20:30 GMT

Current Revision posted to Wiki by Brian John on 5/14/2024 6:20:30 PM

Language Weaver Edge could easily be deployed in Docker & the deployment architecture is similar to an on-prem Windows/Linux deployment. Docker image and sample “docker-compose.yml” files are provided by RWS for easy deployment. A docker host with a GPU is preferred for Training Engines.

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & docker-compose installed on the host.
Sudo access for user mtedge.
Local storage as recommended for the image & language pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as external ports in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefined number of containers as manifested in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic and .env files provided by RWS to current user's home folder.
3. Download & install required language pairs on docker host. (can be removed after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up. This will also create docker volumes mtedge-controller-pvc & mtedge-lp-pvc
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied and then restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete locally installed language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Language Weaver Edge instance in a docker host could be reconfigured/resized by modifying the docker-compose.yml and Edge admin user details by modifying the .env file. All modifications require a restart of docker containers by running docker-compose up -d.

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines or PUs for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 18:19:56 GMT

Revision 14 posted to Wiki by Brian John on 5/14/2024 6:19:56 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & docker-compose installed on the host.
Sudo access for user mtedge.
Local storage as recommended for the image & language pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as external ports in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefined number of containers as manifested in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic and .env files provided by RWS to current user's home folder.
3. Download & install required language pairs on docker host. (can be removed after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up. This will also create docker volumes mtedge-controller-pvc & mtedge-lp-pvc
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied and then restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete locally installed language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines or PUs for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 18:13:17 GMT

Revision 13 posted to Wiki by Brian John on 5/14/2024 6:13:17 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & docker-compose installed on the host.
Sudo access for user mtedge.
Local storage as recommended for the image & language pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as external ports in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefined number of containers as manifested in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/mtedge/sdl-mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic and .env files provided by RWS to current user's home folder.
3. Download & install required language pairs on docker host. (can be removed after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up. This will also create docker volumes mtedge-controller-pvc & mtedge-lp-pvc
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied and then restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete locally installed language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines or PUs for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 17:17:51 GMT

Revision 12 posted to Wiki by Brian John on 5/14/2024 5:17:51 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & docker-compose installed on the host.
Sudo access for user mtedge.
Local storage as recommended for the image & language pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as external ports in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefined number of containers as manifested in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic and .env files provided by RWS to current user's home folder.
3. Download & install required language pairs on docker host. (can be removed after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up. This will also create docker volumes mtedge-controller-pvc & mtedge-lp-pvc
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied and then restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete locally installed language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines or PUs for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 17:07:55 GMT

Revision 11 posted to Wiki by Brian John on 5/14/2024 5:07:55 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & docker-compose installed on the host.
Sudo access for user mtedge.
Local storage as recommended for the image & language pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as external ports in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic & .env files provided by RWS to current users home folder.
3. Download & install required language pairs. (can be uninstalled after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up.
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied & restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Language Weaver Edge instance in a docker host could be reconfigured/resized by modifying the docker-compose.yml and Edge admin user details could be reconfigured by modifying the .env file. All modifications require a restart of docker containers by running docker-compose up -d.

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 17:06:38 GMT

Revision 10 posted to Wiki by Brian John on 5/14/2024 5:06:38 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & docker-compose installed on the host.
Sudo access for user mtedge.
Local storage as recommended for the image & language pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic & .env files provided by RWS to current users home folder.
3. Download & install required language pairs. (can be uninstalled after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up.
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied & restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 17:02:29 GMT

Revision 9 posted to Wiki by Brian John on 5/14/2024 5:02:29 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & Docker-Compose installed on the host.
Sudo access granted to user mtedge.
Recommended size of the local storage for the image & Language Pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic & .env files provided by RWS to current users home folder.
3. Download & install required language pairs. (can be uninstalled after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up.
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied & restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 16:57:21 GMT

Revision 8 posted to Wiki by Brian John on 5/14/2024 4:57:21 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & Docker-Compose installed on the host.
Sudo access granted to user mtedge.
Recommended size of the local storage for the image & Language Pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic & .env files provided by RWS to current users home folder.
3. Download & install required language pairs. (can be uninstalled after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up.
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied & restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 16:48:40 GMT

Revision 7 posted to Wiki by Brian John on 5/14/2024 4:48:40 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the recommended minimum requirement.
e.g. Azure, EC2, VMWare
Docker & Docker-Compose installed on the host.
Sudo access granted to user mtedge.
Recommended size of the local storage for the image & Language Pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic & .env files provided by RWS to current users home folder.
3. Download & install required language pairs. (can be uninstalled after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up.
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied & restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Typical values that could be changed are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/decrease number of Job Engines, Training Engines or add/modify Translation Engines for a given Language Pair.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 16:42:02 GMT

Revision 6 posted to Wiki by Brian John on 5/14/2024 4:42:02 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the minimum requirement.
e.g. Azure, EC2, VMWare
Docker & Docker-Compose installed on the host.
Sudo access granted to user mtedge.
Recommended size of the local storage for the image & Language Pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add a new line as below.
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install unzip, docker & docker-compose on the host.
  eg. on a Ubuntu EC2 host, run.
  
  $ sudo apt update
  $ sudo apt install -y docker.io docker-compose unzip
  $ sudo usermod -a -G docker mtedge
Installation
1. Login to docker repo and pull LW Edge docker image.
  
  $ docker login docker.edge.languageweaver.com
  
  $ docker pull docker.edge.languageweaver.com/sdl/mtedge:8.6.4
2. Copy docker-compose.yml, sdl-ets.lic & .env files provided by RWS to current users home folder.
3. Download & install required language pairs. (can be uninstalled after a successful docker deployment).
  
  $ sftp user@files.edge.languageweaver.com
  
  $ get Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ unzip Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer.zip
  
  $ sudo ./Language_Weaver_Edge_XxxXxx_Generic_SRV_TNM_X_X_x_1_installer/setup-linux-x64.run --mode unattended
4. Start containers by running docker-compose up.
  
  $ docker-compose up -d
5. Copy license file sdl-ets.lic to mtedge-controller-pvc.
  
  $ docker cp sdl-ets.lic mtedge-controller:/mnt/controller/conf/sdl-ets.lic
6. Copy language pair models to mtedge-lp-pvc.
  
  $ sudo docker cp /opt/sdl/ets/lps/. mtedge-controller:/opt/sdl/ets/lps
7. Wait until all language pair models are copied & restart translation engines from UI or run a docker-compose down & up
Cleanup
1. Delete language pair models, installation zip files & folders from the host.
  
  $ sudo rm -rf /opt/sdl
  
  $ sudo rm -rf /etc/opt/sdl
  
  $ sudo rm -rf Language_Weaver_Edge_*

Reconfigure

Language Weaver Edge instance in a docker host could be reconfigured/resized while the Language Weaver Edge service is running. Reconfiguration can be performed using a helm upgrade or directly modifying relevant Kubernetes objects. The simplest way is to modify the “values.yaml” and run a helm upgrade.

Typical values that could be changed while the system is running are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/Decrease the size of the pool of Job Engines, Training Engines or add/modify the pool of Translation Engines for a given Language Pair.
Auto scale the number of Translation Engines, depending on the system load.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 15:26:03 GMT

Revision 5 posted to Wiki by Brian John on 5/14/2024 3:26:03 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the minimum requirement.
e.g. Azure, EC2, VMWare
Docker & Docker-Compose installed on the host.
Sudo access granted to user mtedge.
Recommended size of the local storage for the image & Language Pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add new line as below
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install docker & docker-compose on the host.
Helm charts & example “values.yaml” files are provided by RWS for easy deployment.
Upgrades & rescaling of Edge configuration is possible with helm upgrades.
Training Engines require GPU nodes in the Kubernetes cluster for better performance.
LW Edge license & default admin accounts are saved as Kubernetes secrets.
Persistent volume of the Controller pod could be a standard RWO storage class.
Persistent volume of Language Pairs requires a high performance, case sensitive RWX storage class.
Language Pairs are deployed to the persistent volume using Kubernetes Jobs.

Depending on the size of the Language Pair and I/O bandwidth, each Language Pair installation job will generally run for about 2-10 minutes.

Whilst it is possible to deploy the Edge software during Language Pair installation process, Translation Engines will not start or be usable until all the above Kubernetes jobs are completed.

Most likely used parameters are described in the sample “google.yaml” & “azure.yaml” files provided. Consult “values.yaml” inside the chart “sdl-mtedge-8.6.2.tgz” for a complete list of parameters.

Reconfigure

Language Weaver Edge instance in a Kubernetes cluster could be reconfigured/resized while the Language Weaver Edge service is running. Reconfiguration can be performed using a helm upgrade or directly modifying relevant Kubernetes objects. The simplest way is to modify the “values.yaml” and run a helm upgrade.

Typical values that could be changed while the system is running are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/Decrease the size of the pool of Job Engines, Training Engines or add/modify the pool of Translation Engines for a given Language Pair.
Auto scale the number of Translation Engines, depending on the system load.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 15:24:09 GMT

Revision 4 posted to Wiki by Brian John on 5/14/2024 3:24:09 PM

Minimum requirement

Docker host with CPU/RAM totalling up to the minimum requirement.
e.g. Azure, EC2, VMWare
Docker & Docker-Compose installed on the host.
Sudo access granted to user mtedge.
Recommended size of the local storage for the image & Language Pair models.

Architecture

Edge Controller host is deployed as a container in docker and Edge UI & API are published as a service in the docker overlay network.
Job Engines, Translation Engines & Training Engines are deployed as containers and could be manually configured to scale up/down based on the predefine number of containers defined in the docker-compose.yml file.
Language Pairs and the Edge configuration is saved in docker volumes.
All containers use the same docker base image.

Deployment

Prerequisites
1. Create mtedge user & group with the id 10001.
  
  $ groupadd mtedge -g 10001
  
  $ useradd mtedge -u 10001 -g 10001 -m -s /sbin/nologin
2. Grant sudo access to user mtedge.
  eg. on a Ubuntu EC2 host, edit /etc/sudoers.d/90-cloud-init-users file and add new line as below
  
  $ vi /etc/sudoers.d/90-cloud-init-users
  
  mtedge ALL=(ALL) NOPASSWD:ALL
3. Install docker & docker-compose on the host.
Helm charts & example “values.yaml” files are provided by RWS for easy deployment.
Upgrades & rescaling of Edge configuration is possible with helm upgrades.
Training Engines require GPU nodes in the Kubernetes cluster for better performance.
LW Edge license & default admin accounts are saved as Kubernetes secrets.
Persistent volume of the Controller pod could be a standard RWO storage class.
Persistent volume of Language Pairs requires a high performance, case sensitive RWX storage class.
Language Pairs are deployed to the persistent volume using Kubernetes Jobs.

Depending on the size of the Language Pair and I/O bandwidth, each Language Pair installation job will generally run for about 2-10 minutes.

Whilst it is possible to deploy the Edge software during Language Pair installation process, Translation Engines will not start or be usable until all the above Kubernetes jobs are completed.

Reconfigure

Typical values that could be changed while the system is running are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/Decrease the size of the pool of Job Engines, Training Engines or add/modify the pool of Translation Engines for a given Language Pair.
Auto scale the number of Translation Engines, depending on the system load.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 14:54:06 GMT

Revision 3 posted to Wiki by Brian John on 5/14/2024 2:54:06 PM

Minimum requirement

Kubernetes cluster with node CPU/RAM totalling up to the minimum requirement.
e.g. AKS, EKS, GKE
Autoscaling is enabled in Kubernetes cluster. (optional)
Ingress controller to access Kubernetes services.
e.g. NGINX
Storage classes in Kubernetes that support both RWO & RWX volume types.

Architecture

Edge Controller host is deployed as a pod in Kubernetes and Edge UI & API are published as a service.
Job Engines, Translation Engines & Training Engines are deployed as Stateful Sets and could be configured to auto scale based on the pod CPU usage or predefine the number of replica pods.
Language Pairs and the Edge configuration is saved in persistent volumes.
All pods use the same docker base image.

Deployment

Helm charts & example “values.yaml” files are provided by RWS for easy deployment.
Upgrades & rescaling of Edge configuration is possible with helm upgrades.
Training Engines require GPU nodes in the Kubernetes cluster for better performance.
LW Edge license & default admin accounts are saved as Kubernetes secrets.
Persistent volume of the Controller pod could be a standard RWO storage class.
Persistent volume of Language Pairs requires a high performance, case sensitive RWX storage class.
Language Pairs are deployed to the persistent volume using Kubernetes Jobs.

Depending on the size of the Language Pair and I/O bandwidth, each Language Pair installation job will generally run for about 2-10 minutes.

Whilst it is possible to deploy the Edge software during Language Pair installation process, Translation Engines will not start or be usable until all the above Kubernetes jobs are completed.

Reconfigure

Typical values that could be changed while the system is running are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/Decrease the size of the pool of Job Engines, Training Engines or add/modify the pool of Translation Engines for a given Language Pair.
Auto scale the number of Translation Engines, depending on the system load.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 14:41:10 GMT

Revision 2 posted to Wiki by Brian John on 5/14/2024 2:41:10 PM

Language Weaver Edge could easily be deployed in Kubernetes & the deployment architecture is similar to an on-prem Windows/Linux deployment. Helm charts and sample “values.yaml” files are provided by RWS for easy deployment. Kubernetes GPU nodes are preferred for Training Engines.

Minimum requirement

Kubernetes cluster with node CPU/RAM totalling up to the minimum requirement.
e.g. AKS, EKS, GKE
Autoscaling is enabled in Kubernetes cluster. (optional)
Ingress controller to access Kubernetes services.
e.g. NGINX
Storage classes in Kubernetes that support both RWO & RWX volume types.

Architecture

Edge Controller host is deployed as a pod in Kubernetes and Edge UI & API are published as a service.
Job Engines, Translation Engines & Training Engines are deployed as Stateful Sets and could be configured to auto scale based on the pod CPU usage or predefine the number of replica pods.
Language Pairs and the Edge configuration is saved in persistent volumes.
All pods use the same docker base image.

Deployment

Helm charts & example “values.yaml” files are provided by RWS for easy deployment.
Upgrades & rescaling of Edge configuration is possible with helm upgrades.
Training Engines require GPU nodes in the Kubernetes cluster for better performance.
LW Edge license & default admin accounts are saved as Kubernetes secrets.
Persistent volume of the Controller pod could be a standard RWO storage class.
Persistent volume of Language Pairs requires a high performance, case sensitive RWX storage class.
Language Pairs are deployed to the persistent volume using Kubernetes Jobs.

Depending on the size of the Language Pair and I/O bandwidth, each Language Pair installation job will generally run for about 2-10 minutes.

Whilst it is possible to deploy the Edge software during Language Pair installation process, Translation Engines will not start or be usable until all the above Kubernetes jobs are completed.

Reconfigure

Typical values that could be changed while the system is running are:

Bootstrap Language Weaver Edge admin user.
Install new Language Pairs.
Increase/Decrease the size of the pool of Job Engines, Training Engines or add/modify the pool of Translation Engines for a given Language Pair.
Auto scale the number of Translation Engines, depending on the system load.

Environment Variables

Custom environment variables could be set independently for:

Controller pod.
Job Engine pods - all pods share the same environment variables.
Translation Engine pods - each Language Pair has its own environment variables.
Training Engine pods - all pods share the same environment variables.

Edge API

The API key is automatically prefixed with “u_” + username + ”_” when created.

For an example, to make a REST API call for user admin@example.com with API key myapikey1234

$ curl -u u_admin@example.com_myapikey1234: https://myhost.example.com/api/v2/

Running Language Weaver Edge on Docker

Brian John — Tue, 14 May 2024 14:39:19 GMT

Revision 1 posted to Wiki by Brian John on 5/14/2024 2:39:19 PM

Running Language Weaver Edge on Docker