BAIA Configuration
Info
The BAIA configuration described here, enables the following AI features in PIM:
For enabling AI Product Placement Suggestions please refer to the developer tutorial.
Configure attribute fields
A new BAIA configuration for an attribute field can be created from the attribute details page, as seen in the screenshot below:
All existing configurations are listed on the BAIA Configuration page, which can be found under the Administration section in PIM. From here, existing configurations can be modified or deleted.
The following input parameters are to be configured per attribute field:
- Attributes to use as input for the AI feature
- Golden products which set the standard of well-enriched products
- Instruction prompt for providing context to the AI feature
These input parameters come together in a BAIA configuration as shown in the following diagram:
Relevant attributes
Attributes that should be used by the AI feature as input for generating a value or suggestion can be selected here. These attributes should be present on the product(s) for which the feature is applied to get the best possible result. Also, the golden products must contain a value for all the attributes selected here.
Note
Any attribute that does not use predefined values can be selected here.
Golden products
The products configured as golden products will act as example products for the AI feature. Golden products are considered well-enriched products that BAIA will use, so the AI engine can derive from these products what the characteristics of the generated value or suggestion should be. It also gets an idea of how the other attributes and master data properties on these golden products should be interpreted.
Instruction prompt
Providing context to the AI feature in the form of an instruction prompt allows users to customize its result. The instruction prompt can contain any type of instruction, from text length restrictions to instructions regarding tone of voice and target audience.
The instruction prompt is segmented for segmented attribute field types. This means that a specific instruction prompt can be set for each segment, in case the data type of the attribute field which the AI feature is configured for is a segmented type.
Example
A custom instruction per segment allows for targeting different audiences, for example, when working with channel segmented product descriptions. A good example of this is creating a specific prompt for the B2B and B2C segments.
This prompt can instruct the text generation for the B2B segment to include specific technical details about a product, which could be interesting for the business customer reading it:
Generate a product description with targeting other businesses as customers. The description should include a summary of the technical specifications of the product.
The B2C text on the other hand, can be generated with specific use cases in mind which are relevant for a regular customer:
Generate a product description with a friendly, approachable tone. The description should explain the product's main uses and benefits, appealing to a broad audience. Keep the language simple and relatable.