Semarchy GenAI Azure enricher
The Semarchy GenAI Azure enricher generates a single text response based on a user prompt.
Description
The GenAI Azure enricher is designed to enhance text data using OpenAI’s language models hosted on the Microsoft Azure platform. Users can leverage this enricher to improve the quality, relevance, and depth of their text data using advanced AI capabilities.
Plugin parameters
The following table lists the plugin parameters.
| Parameter name | Mandatory | Type | Description | ||||
|---|---|---|---|---|---|---|---|
Base URL |
Yes |
String |
Base URL for the client’s Azure OpenAI Service resource, available through the Azure portal. |
||||
API Key |
Yes |
String |
Client-side API key for establishing connectivity with Azure OpenAI Service. |
||||
Deployment Name |
Yes |
String |
Unique identifier for the deployed model, used to call the model through client libraries and REST APIs. |
||||
Model |
Yes |
String |
Language model to be used. Possible values are:
|
||||
Temperature |
No |
Number |
Value ranging from 0 to 1 for balancing between conservative and coherent outputs (0) and creative variations (1) during text generation. |
||||
Frequency Penalty |
No |
Number |
Value between -2.0 and 2.0 used to discourage the model from repeatedly sampling the same sequences of tokens during text generation. Reasonable values typically range from 0.1 to 1. |
||||
Max Tokens |
No |
Integer |
Maximum number of tokens allowed in the generated output during text generation.
|
||||
Presence Penalty |
No |
Number |
Value between -2.0 and 2.0 used to reduce the likelihood of the model generating repetitive sequences of tokens during text generation. Reasonable values typically range from 0.1 to 1. |
||||
Top P |
No |
Number |
Value ranging from 0 to 1 for defining the cumulative probability threshold for nucleus sampling (i.e., token selection).
|
||||
Max Retries |
No |
Integer |
Maximum number of attempts allowed for API requests before considering them unsuccessful. |
Language models
Language models are AI systems trained on vast amounts of text data to understand and generate human-like language, enabling tasks like text completion, translation, summarization, and sentiment analysis.
The OpenAI API offers a range of models with distinct capabilities. The models supported by the GenAI Azure enricher include:
-
gpt-3.5-turbo: the latest iteration of GPT-3.5 Turbo. -
gpt-4: this model builds upon the advancements of GPT-3.5, with continuous upgrades. -
gpt-4o: stands for GPT-4 Omni, an advanced, multimodal model with improved efficiency and accuracy, and superior performance in non-English language tasks.
All options theoretically point to the latest version of their respective model.
For more information on Azure OpenAI Service models, see the official Azure OpenAI Service documentation.
Tokens
Tokens are units of text that language models use to process and generate language. They can range from individual characters to entire words, depending on the language and the specific model being used.
For more information about tokens, see the official Azure OpenAI Service documentation.
Plugin inputs
The following table lists the plugin inputs.
| Input name | Mandatory | Type | Description |
|---|---|---|---|
User Prompt |
Yes |
String |
Input query specifying the user’s particular needs, intentions, or requests for the generated text. |
System Prompt |
No |
String |
Initial instruction designed to guide the model towards specific topics, styles, tones, or formats of generated text. |
Plugin outputs
The following table lists the plugin outputs.
| Output name | Type | Description |
|---|---|---|
Response |
String |
Generated response applied to a designated attribute. |
Examples and use cases
Imagine a scenario where a user needs a condensed version of a detailed product description for social media, where character or space limits apply. In practice, during record creation or editing, the user wants a brief social media blurb to be generated based on the Description field’s content.
For instance, consider the Velocity Pro Carbon Bike product record with the following description:
"Introducing the Velocity Pro Carbon Bike from Italy, a high-performance masterpiece meticulously crafted for speed enthusiasts. This aerodynamic marvel boasts cutting-edge design and lightweight materials, providing an unparalleled riding experience. Elevate your cycling adventures with the pinnacle of Italian engineering. Price: 134."
Suppose the enricher is configured as follows:
-
In the plugin input properties:
-
User Prompt:
'Summarize the following description in less than 150 characters: ' || Description
-
-
In the plugin output properties:
-
Attribute Name: SocialMediaBlurb
-
In this setup, the response provided by the enricher may populate the Social Media Blurb field of the Velocity Pro Carbon Bike record with the following:
"Introducing the Velocity Pro Carbon Bike from Italy: a high-performance marvel, aerodynamic design, lightweight materials, ultimate riding experience. Price: $134."
Below are just a few examples of the diverse range of use cases that the GenAI Azure enricher can support:
-
Content generation: create detailed descriptions of products or customer personas; generate captions for social media posts, ads, or campaigns.
-
Content synthesis: capture the essence of a text to create titles or names for products, services, or features.
-
Content quality: enhance clarity, refine structure, and adjust tone to meet specific communication goals; correct spelling and grammar errors to adhere to standard language conventions.
-
Custom tone of voice: adapt the tone of the text to align with specific communication objectives, conveying neutrality, professionalism, empathy, education, or casualness.
-
Language translation: translate text into one or several other languages.
-
Price conversion: convert product prices from one currency to another.