Sign inSign up

accusoft/ai-hub

By accusoft

•Updated over 1 year ago

Docker image for the AI Hub.

Image
0

2.7K

accusoft/ai-hub repository overview

⁠AI Hub

AI Hub is a service that provides a RESTful API for performing tasks using IBM watsonx.ai.

Running this image will start an AI Hub process with all required services so that you can begin using it for local development of your application. Besides the AI Hub image you will need to run MySQL Server⁠, Process Manager⁠ and PrizmDoc Server⁠ containers as described below.

NOTE: This Docker image is suitable for a production deployment. But since this is a new product we may make some changes to the API in the future.

⁠Licensing

At this time, we only offer a paid, self-hosted option. We do offer a paid "Developer All Access" license that gives you full access to all new AI functionality in PrizmDoc. Due to the costs of running AI, we are not able to offer this as a "free" trial at this time. We are working to provide a cloud-hosted "trial" option that we hope to offer at a much lower cost for trial purposes.

You will need to configure PrizmDoc Server with a license that includes any of the AI features that you would like to use. To purchase a license, contact [email protected]⁠.

You will also need credentials for IBM watsonx.ai, which you will need to obtain from IBM.

To run AI Hub as a Docker container, you simply need a Docker host (a machine with Docker installed). See the Docker documentation⁠ for more information.

⁠Getting Started

⁠1. Create a Docker network so the containers can communicate.
docker network create prizmdoc
⁠2. Run MySQL Server⁠.
docker run --name=mysql --detach --rm --network prizmdoc --publish 3306:3306 --env MYSQL_LOG_CONSOLE="TRUE" --env MYSQL_DATABASE=ProcessManager --env MYSQL_ROOT_PASSWORD=root mysql:5.7 --max_allowed_packet=100M --general_log=1 --general_log_file=/var/lib/mysql/mysql.log --innodb_use_native_aio=0
⁠3. Initialize a default config file for PrizmDoc Server

Before you can run PrizmDoc Server, you'll need a config file. You can create a default config file using the docker image's init-config command. This section explains how to do that.

⁠Windows (PowerShell)

First, make sure you've created a config directory on your host file system:

mkdir config

Then, use the init-config command to create a new prizm-services-config.yml file in your config directory:

docker run --rm -e ACCEPT_EULA=YES --volume $pwd/config:/config accusoft/prizmdoc-server init-config

This will create a new PrizmDoc Server config file on your Windows host filesystem at .\config\prizm-services-config.yml.

⁠Mac or Linux (bash)

Use the init-config command to create a new prizm-services-config.yml file:

docker run --rm -e ACCEPT_EULA=YES --volume $(pwd)/config:/config accusoft/prizmdoc-server init-config

This will create a new PrizmDoc Server config file on your host filesystem at ./config/prizm-services-config.yml.

⁠4. Customize your PrizmDoc Server config file

See the product documentation⁠ for information about configuring PrizmDoc Server. You will need to configure your license and the central database connection string. You will need to specify a license that includes any of the AI features that you would like to use.

⁠5. Run PrizmDoc Server⁠.
docker run --rm --env ACCEPT_EULA=YES --network prizmdoc --publish 18681:18681 --name prizmdoc-server accusoft/prizmdoc-server

Wait until you see the following output in the console:

[info] Starting Product Runner...
[info] product-runner has been started correctly.
[info] Starting PCCIS Watchdog process...
[info] PCCIS Watchdog has been started correctly.
⁠6. Run Process Manager.
docker run --name=process-manager --detach --rm --network prizmdoc --publish 3000:3000 --publish 3001:3001 --env LOG_LEVEL=info --env "DATABASE_CONNECTION_STRING=mysql://root:root@mysql:3306/ProcessManager" --env "PRIZMDOC_SERVER_URL=http://prizmdoc-server:18681" --env ACCEPT_EULA=YES accusoft/process-manager
⁠7. Run AI Hub.

When using IBM watsonx.ai SaaS, you must provide your watsonx.ai API endpoint, API key, IAM token service endpoint and project ID via the environment variables shown below:

docker run --rm --network prizmdoc -p 4100:4100 -e ACCEPT_EULA=YES -e "PROCESS_MANAGER_INTERNAL_URL=http://process-manager:3001" -e "WORKFILE_SERVICE_URL=http://prizmdoc-server:18681/PCCIS/V1/WorkFile" -e WATSONX_API_ENDPOINT="your watsonx API endpoint" -e WATSONX_API_KEY="your watsonx API key" -e WATSONX_IAM_TOKEN_SERVICE="your watsonx token service endpoint" -e WATSONX_PROJECT_ID="your watsonx project ID" --name ai-hub accusoft/ai-hub

When using a local watsonx.ai cluster, you must provide your watsonx.ai API endpoint, API key and user ID via the environment variables shown below:

docker run --rm --network prizmdoc -p 4100:4100 -e ACCEPT_EULA=YES -e "PROCESS_MANAGER_INTERNAL_URL=http://process-manager:3001" -e "WORKFILE_SERVICE_URL=http://prizmdoc-server:18681/PCCIS/V1/WorkFile" -e WATSONX_API_ENDPOINT="your watsonx API endpoint" -e WATSONX_API_KEY="your watsonx API key" -e WATSONX_USER_ID="your watsonx user ID" --name ai-hub accusoft/ai-hub

Tag summary

Content type

Image

Digest

sha256:c5f008142…

Size

250.5 MB

Last updated

over 1 year ago

docker pull accusoft/ai-hub