Missing documentation for Personal Commands

[mavrosxristoforos]

Is your issue related to a problem? Please describe.
When teaching a personal command, select "Execute command(s)".
There is currently no way to know what to write in the "using these sentences ..." field.

Describe the solution you'd like
I would like to have a list of commands that can be executed.

Additional context
Most importantly, I would like to be able to run executables in the server, using a personal command.

[fquirin]

Documentation is still a bit sparse, sorry about that, but I'm working on it ^^.
"using these sentences ..." litterally means any sentence that SEPIA understands when you chat with it. You can combine them like this "How is the weather. Show me tech news." and both commands will be executed after another.
Running executables on the server requires a (mini) custom service. I'm currently working on a new SDK that will make it very easy to implement, but there is one design issue: usually custom services are in kind of a sandbox that restricts system access for security reasons. To overcome this issue I'm thinking about a new micro-service-server for potentially risky tasks/commands to move them into a real sandbox and make it deployable on any other device in the network.

That said there is a certain workaround depending on how much experience you have with building your own microservice. You could setup a server with a REST API that can execute executables and use the "Open link/website" command of SEPIA to call a certain URL of your REST API ;-)

[mavrosxristoforos]

I understand now. Thanks for that.
It could certainly work with an external URL. However, It would be nice to be able to pass parameters to that, from what is spoken. For example: "execute command for pizza". Calls URL with pizza as argument.
That being said, it would be even better if we could write our own sequences of commands, accepting arguments, like with the list creation, or others, that waits for a response.

[fquirin]

That is certainly more within the scope of a custom smart-service (what Amazon and Google call skill or action) than the Teach-UI. The Teach-UI is primarily a tool to create (voice-/button-)shortcuts for certain actions (services with specific parameters, e.g. "show me the way to XY").
Smart-services require a little bit of programming skills with Java but I hope with the SDK I can simplify it to reduce the code to a minimum (maybe even support different programming languages later).

[sepia-assistant]

Just a quick note since this has been open for a long time ^^: the SDK has been released a while ago (currently pending an update for SEPIA server v2.2.2) and the new version of the client (v0.18.0) has help and examples integrated into the Teach-UI :-)