Skip to main content

CoCo(Conversational Components) SDK for using components in Rasa

Project description

A Toolkit to work with components in rasa

Installation (We recommend using a virtualenv):

pip install coco-rasa

Setup:

Setting up CoCo actions

in actions.py

from coco_rasa import GenericCoCoAction

class OneLiners(GenericCoCoAction):
    # component name is the component_id from CoCo marketplace
    component_name = "generic_oneliners_vp3"

class Namer(GenericCoCoAction):
    component_name = "namer_vp3"

in domain.yml

actions:
    - generic_oneliners_vp3
    - namer_vp3

to enable multi-turn capabilities for CoCo actions

in your rasa bot config.yml

policy:
  - name: "coco_rasa.CoCoContextPolicy"

triggering actions (and CoCo actions)

  • MappingPolicy
# config.yml:
policies:
    - name: MappingPolicy
# domain.yml
intents:
    - greet:
        triggers: namer_vp3
    - someotherintent
  • Fallback policy
# config.yaml
policies:
    - name: "FallbackPolicy"
        nlu_threshold: 0.4
        core_threshold: 0.3
        fallback_action_name: "generic_oneliners_vp3"

using context transfer

in domain.yml declare the keys you want the use(from CoCo context transfer protocol). data will be transferred automatically between components.

slots:
  user.firstName:
    type: text
  user.lastName:
    type: text

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

coco-rasa-0.0.2.tar.gz (4.4 kB view hashes)

Uploaded Source

Built Distribution

coco_rasa-0.0.2-py3-none-any.whl (4.8 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page