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

Uses Python Model Recognizer Stage

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

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

  • Service Hostname ( type=string | default=localhost | required ) - URL for the host where Python Bridge is running.
  • Service Port ( type=string | default=5000 | required ) - Port where Python Bridge is running.
  • Authentication ( type=boolean | default=false | required ) - Whether or not to use authentication for the python bridge
  • Service Username ( type=string | optional ) - Username to connect to the Python Bridge
  • Service Password ( type=string | optional ) - Password to connect to the Python Bridge
  • Select Model ( type=string | required ) - Model name registered in the python bridge.
  • Select Version ( type=string | optional ) - Model version registered in the python wrapper to query.
  • Select Model Method ( type=string | required ) - Model method to call for the model.


Configuration

  • Dependency tags ( type=string array | optional ) - List of tags to be dependent for the model. Execute after these tags.
  • Normalize Tags ( type=boolean | default=false | optional ) - Tags (flagged as SEMANTIC_TAG) are normalized.
  • Include Context ( type=boolean | default=false | optional ) - Includes up to two fields in the metadata of the new tag, the values are "before" and "after".
  • Include vertex text as token ( type=boolean | default=false | optional ) - Vertex text such as colon and comma will be included as a token in the response
  • Skip vertex flags ( type=string | optional ) - Vertices are ignored when processing the lexical items
  • Match Threshold ( type=double | default=0.6 | required ) - Matching intents need to have a higher confidence value than this threshold to be selected

General Settings

The general settings can be accessed by clicking on

More settings could be displayed in the same dialog, it varies per recognizer.


  • Enable - Enable the processor to be use in pipelines.
  • Base Pipeline - Indicates the last stage, from a pipeline, needed by the recognizer.
  • Skip Flags ( optional ) - Lexical items flags to be ignored by this processor.
  • Boundary Flags  ( optional ) - List of vertex flags that indicate the beginning and end of a text block.
  • Required Flags ( optional ) - Lexical items flags required by every token to be processed.
  • At Least One Flag ( optional ) - Lexical items flags needed by every token to be processed.
  • Don't Process Flags ( optional ) - List of lexical items flags that are not processed. The difference with "Skip Flags" is that this will drop the path in the Saga graph, skip just skips the token and continues in the same path.
  • Confidence Adjustment - Adjustment factor to apply to the confidence value of 0.0 to 2.0 from (Applies for every match).
    • 0.0 to < 1.0  decreases confidence value
    • 1.0 confidence value remains the same
    • > 1.0 to  2.0 increases confidence value
  • Debug - Enable debug logging.





  • No labels