Admin > AI Configurations
Intended audience: DEVELOPERS ADMINISTRATORS
AO Platform: 4.3
Overview
The AI Configurations pages allow the user to configure options for AI Models, Groups and Services as well as NLP configurations.
Most of the pages in this section offer the following general actions:
Search/Filter - use a search term to find an entry from existing configurations.
Delete - batch deletion of any/all selected items.
Add New - create a new entry on the page.
Refresh - refreshes the page.
Import from Excel - allows provision to import configuration of one or more entries of the selected configuration page.
Export as CSV - exports the content of page to a CSV file.
Settings - allows configuration of which columns can be seen on the page.
Go to (or select by page number) - allows moving to another page in case of too many entries for one page.
Additionally, these are the actions on individual entries:
View - views the properties of an entry in read-only mode.
Edit - allows the properties of an entry to be edited.
Delete - deletes an entry.
Add to Transport - adds the configuration record to Transport.
View Annotations - this option is specific to the AI Models page.
View Models - this option is specific to the AI Model Services page.
AI Models
The AI Models page includes a list of all AI Models included with the AO Platform. Generally, an AI model is a software program that has been trained on a set of data to perform specific tasks like recognizing certain patterns. Artificial intelligence models use decision-making algorithms to learn from the training and data and apply that learning to achieve specific pre-defined objectives.
Configuration details include only General and AI Model properties.
AI Model Groups
The AI Model Groups page includes a list of the Groups containing AI Models, such as NLP_GENERIC, QA, CV, COMMON, and NLP_SPACY.
Configuration details include only General properties.
AI Model Services
The AI Model Services page includes a list of all AI Model Services included with the AO Platform. An AI Model Service is the programmable end-point required to execute an AI Model. To view which AI Models belong to a given AI Model Service, select View Models from the Options menu for a specific AI Model Service.
Configuration details include only General and AI Model Service properties.
AI Model Service Groups
The AI Model Services Groups page includes a list of the Groups containing AI Model Services, such as NLP, QA, CV, and COMMON.
Configuration details include only General properties.
NLP > Model Annotations
The Model Annotations page includes Annotations that relate to the AI Models. To view the relationships between the AI Models and the Model Annotations, open the AI Models and select View Annotations from the Options menu for a specific AI Model.
Configuration details include only General and AI Model properties.
NLP > Entity Extraction Preprocessors
This page allows user to add any number of preprocessors as a central repository. These preprocessors can then be used when configuring MSOs in areas such as the Entity Extractor. An individual processor can be configured/used by multiple MSOs. See NLP > Entity Extraction Preprocessors.
NLP > Entity Extraction Postprocessors
This page allows user to add any number of postprocessors as a central repository. These postprocessors can then be used when configuring MSOs in areas such as the Entity Extractor. An individual processor can be configured/used by multiple MSOs. See NLP > Entity Extraction Postprocessors.
NLP > Normalizers
This page allows users to add any number of normalizers as a central repository. This normalizers can then be used when configuring MSOs in the Entity Extractor configuration. An individual normalizer can be configured/used by multiple MSOs. See NLP > Entity Extraction Normalizers.
Model Field Transformation
The Model Field Transformation page includes a list of the Transformation and Feature Engineering Functions used by the Model Composer when transforming data source fields.
Configuration details include Depends On, Field Name, Custom Function Name, Model, ML Function and Parameters.