-
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
22 additions
and
9 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,14 +1,14 @@ | ||
Coming next | ||
=== | ||
|
||
- [x] Support markdown in the answer and ask `text` property and automatically add a `raw_text` property containing the text without formatting (same goes for cards properties) | ||
- [ ] Add a meta() for skills to define skill metadata, this will be pretty useful to query available skills and their needed configurations (need some more keys such as configs) | ||
- [ ] Add support for **contexts** with sub intents | ||
- [ ] Remote training of the interpreter for when you have large training data and you are deploying pytlas on a small device | ||
- [ ] Introduce a `pytlas.settings` namespace which will handle all global settings used by skills. It will read settings from a configuration file and environment variables (should replace `pytlas.cli.conf`) | ||
- [x] Defer all loadings (training and localization) by storing only a function handler and calling it at runtime. It will make easy to add dynamic trainings at runtime (such as available rooms or devices needed in training entities) | ||
- [x] Support markdown in the answer and ask `text` property and automatically add a `raw_text` property containing the text without formatting (same goes for cards properties) | ||
- [x] Add a meta() for skills to define skill metadata, this will be pretty useful to query available skills and their needed settings | ||
- [x] Add `require_input` in the `agent.done` method to indicates that a skill has done its work but the client should listen to user inputs right now (it will be useful when working with contexts) | ||
- [x] Updated snips-nlu dependency | ||
- [x] Add `skills` args to `fit_from_skill_data` to restrict which training data should be loaded | ||
- [x] You can now use a `pytlas.conf` file and it will be read by the cli in the current working directory | ||
- [ ] Introduce a `pytlas.settings` namespace which will handle all global settings used by skills. It will read settings from a configuration file and environment variables (should replace `pytlas.cli.conf`) | ||
- [x] Defer all loadings (training and localization) by storing only a function handler and calling it at runtime. It will make easy to add dynamic trainings at runtime (such as available rooms or devices needed in training entities) | ||
- [x] Skills manager | ||
- [ ] Remote training of the interpreter for when you have large training data and you are deploying pytlas on a small device |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters