Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Enhancement] Module CLI #286

Open
kichanyurd opened this issue Feb 17, 2025 · 0 comments
Open

[Enhancement] Module CLI #286

kichanyurd opened this issue Feb 17, 2025 · 0 comments
Labels
enhancement New feature or request priority-medium

Comments

@kichanyurd
Copy link
Contributor

Motivation

Currently, to work with modules, you need to manually create a module file from scratch and manually pass it to the server every time using the --module parameter. It'd be nice to have some assistance and ergonomics around this.

Solution Proposal

  1. Move parlant.toml to under PARLANT_HOME
  2. Add a CLI groupmodule
  3. Add a command parlant-server module init NAME to initialize a new module. This command should create the file and output its created location at $PARLANT_HOME/NAME.py
    1. Support template parameters. For example, --tool-service should create the module using a tool service template.
    2. In the future, we will have templates life lifecycle hooks, registering custom NLP models, etc..
  4. Add a command parlant-server module enable NAME that adds it to parlant.toml so that it's automatically loaded each time even when not specified in the CLI when starting the server
  5. Add a command parlant-server module disable NAME that removes it from parlant.toml# Discussion
    Add any other context or open questions about the feature request here.
@kichanyurd kichanyurd added the enhancement New feature or request label Feb 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request priority-medium
Projects
None yet
Development

No branches or pull requests

1 participant