Google Knowledge

This recognizer uses the Google Knowledge API (closed alpha) for FAQ matching. FAQ could be loaded directly from an HTML page via a URL or created manually in Saga and then uploaded to the Google Knowledge service to construct the model.

Saga uses a keys.json file from the service account configured to interact with this API to authenticate all GCP REST calls. More information here.

Configuration

• Project Id ( type=string | required ) - Project Id from GCP where the service is available
• API Version ( type=string | required ) - Version of the Knowledge API to use. I.e. v1alpha
• Minimum Probability ( type=double | default=0.5 | required ) - Minimum threshold of a match to be tagged
• Knowledge Base Source ( type=string | required )
  
  • Options
    • HTML URL: Specify a URL to an FAQ page. The service parse the page and train the model on these question/answer pairs.
    • FAQ Editor: Add question/answer pairs to Saga and then upload to the Google Knowledge Service to train the model for matching.

HTML FAQ

When selecting the HTML URL on the Knowledge Base Source parameter, an option to specify a FAQ URL is displayed.

• Url ( type=string | required ) - URL to an HTML page containing a list of FAQ.

When clicking on , Saga will send the URL to be processed by the Google Knowledge API to produce the model. 

Replace image with pattern in row 

FAQ Editor

When selecting the FAQ Editor on the Knowledge Base Source parameter, a table to add question/answer pairs is displayed.

Adding a Question/Answer pair

Click on the  button which will popup the "Add new Google FAQ" dialog

• Write question here ( type=string | required ) - Question to add to the FAQ
• Write answer here ( type=string | required ) - Answer to the question

Load FAQ for training

Clicking on the  will upload all question/answer pairs for training.

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.