Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Excerpt

Connects directly to the Python Bridge, to send text or sections of the interpretation graph to be process processed by ML algorithms in Python.

Info

Uses Python Model Recognizer Stage

Image Removed

If authentication is needed to connect to the Python Bridge, enable the "Authenticate" checkbox and enter the Service username and password as below:

Image Added

If authentication is not required or authentication is successful, select Model Name, Version and/or Method then click on the Save button:

Image Added

  • Parameter
    summaryURL for the host where Python Bridge is running.
    defaultlocalhost
    nameService Hostname
    requiredtrue
  • Parameter
    summaryPort where Python Bridge is running.
    default5000
    nameService Port
    requiredtrue
  • Parameter
    summaryWhether or not to use authentication for the python bridge
    defaultfalse
    nameAuthentication
    typeboolean
    requiredtrue
  • Parameter
    summaryUsername to connect to the Python Bridge
    nameService Username
  • Parameter
    summaryPassword to connect to the Python Bridge
    nameService Password
  • Parameter
    summaryModel name registered in the python bridge.
    nameSelect Model
    requiredtrue
  • Parameter
    summaryModel version registered in the python wrapper to query.
    nameSelect Version
  • parameter
    Parameter
    summaryModel method to call for the model.
    nameSelect Model Method
    requiredtrue
    summaryMaximum number of connection retries to the Python Bridge.
    default3
    nameNumber of retries
    requiredtrue


Configuration

Image RemovedImage Added

  • Parameter
    summaryList of tags to be dependent for the model. Execute after these tags.
    nameDependency tags
    typestring array
  • Parameter
    summaryTags (flagged as SEMANTIC_TAG) are normalized.
    defaultfalse
    nameNormalize Tags
    typeboolean
  • Parameter
    summaryIncludes up to two fields in the metadata of the new tag, the values are "before" and "after".
    defaultfalse
    nameInclude Context
    typeboolean
  • Parameter
    summaryVertex text such as colon and comma will be included as a token in the response
    defaultfalse
    nameInclude vertex text as token
    typeboolean
  • Parameter
    summaryVertices are ignored when processing the lexical items
    nameSkip vertex flags
  • Parameter
    summaryMatching intents need to have a higher confidence value than this threshold to be selected
    default0.6
    nameMatch Threshold
    typedouble
    requiredtrue

General Settings

Include Page
Generic Recognizer Config
Generic Recognizer Config