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
Add Rasa NLU parser/matcher #336
Merged
Merged
Conversation
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
Codecov Report
@@ Coverage Diff @@
## master #336 +/- ##
======================================
Coverage 100% 100%
======================================
Files 17 18 +1
Lines 877 1023 +146
======================================
+ Hits 877 1023 +146
Continue to review full report at Codecov.
|
jacobtomlinson
changed the title
[WIP] Add Rasa NLU parser/matcher
Add Rasa NLU parser/matcher
Jan 13, 2018
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This is my first attempt at #335.
This change adds a new parser/matcher pair for Rasa NLU. This is pretty standard and follows the same format as Dialogflow/LUIS/Wit.
However Rasa can also be trained directly through the API so this PR adds the ability to include intents in your skills in the Rasa markdown format (see the rasa branch of the hello skill for an example). Then when opsdroid starts it runs an extra
train_parsers
method which sends the intents to Rasa NLU to be trained into a model which will be used when parsing messages. This simplifies the portability of NLU skills as the intents don't have to be recreated and retrained by each user. This has also been added as a standard section of startup in the hope that something similar could be added for the other NLU engines. I have a feeling that LUIS can also be trained via API, not sure about the others.Fixes #335
Status
UNDER DEVELOPMENT
Type of change
How Has This Been Tested?
docker run --rm -p 5000:5000 rasa/rasa_nlu:0.10.5-full
.hello
skill but using therasa
branch.Checklist: