PROMPT CHAINING SYSTEM FOR GENERATIVE ARTIFICIAL INTELLIGENCE SYSTEMS
A method for text prompt refinement includes analyzing, by a detection module, a text prompt to identify one or more characteristics. The method also includes generating, by a recommendation engine, one or more recommended modifications to the text prompt based on the one or more characteristics. The method further includes receiving, by a text prompt variation module, a user selection of at least one of the recommended modifications. The method also includes generating, by the text prompt variation module, a refined text prompt based on the user selection, the refined text prompt comprising one or more prompt variations. The method further includes receiving a user selection of one of the one or more prompt variations. The method also includes generating, via a generative model, a generative output based on the user-selected prompt variation.
1 . A method for text prompt refinement, the method comprising:
analyzing, by a detection module, a text prompt to identify one or more characteristics;
generating, by a recommendation engine, one or more recommended modifications to the text prompt based on the one or more characteristics;
receiving, by a text prompt variation module, a user selection of at least one of the recommended modifications;
generating, by the text prompt variation module, a refined text prompt based on the user selection, the refined text prompt comprising one or more prompt variations;
receiving a user selection of one of the one or more prompt variations; and
generating, via a generative model, a generative output based on the user-selected prompt variation.
2 . The method of claim 1 , wherein the generative output comprises a visualization.
3 . The method of claim 1 , wherein analyzing the text prompt comprises using semantics to identify an ambiguous word or phrase in the text prompt.
4 . The method of claim 3 , wherein identifying the ambiguous word or phrase is based on historical data associated with a user.
5 . The method of claim 1 , wherein analyzing the text prompt comprises identifying an understated element in the text prompt that lacks detail.
6 . The method of claim 1 , wherein analyzing the text prompt comprises identifying a pattern in the text prompt that deviates from an expected norm.
7 . The method of claim 1 , wherein generating the one or more recommended modifications comprises generating a prioritized list of keywords or phrases.
8 . An apparatus, comprising:
one or more processors; and
one or more memories coupled with the one or more processors and storing processor-executable code that, when executed by the one or more processors, is configured to cause the apparatus to:
analyze a text prompt to identify one or more characteristics;
generate one or more recommended modifications to the text prompt based on the one or more characteristics;
receive a user selection of at least one of the recommended modifications;
generate a refined text prompt based on the user selection, the refined text prompt comprising one or more prompt variations;
receive a user selection of one of the one or more prompt variations; and
generate, via a generative model, a generative output based on the user-selected prompt variation.
9 . The apparatus of claim 8 , wherein the generative output comprises a visualization.
10 . The apparatus of claim 8 , wherein execution of the processor-executable code further causes the apparatus to analyze the text prompt by using semantics to identify an ambiguous word or phrase in the text prompt.
11 . The system of claim 10 , wherein execution of the processor-executable code further causes the apparatus to identify the ambiguous word or phrase based on historical data associated with a user.
12 . The system of claim 8 , wherein execution of the processor-executable code further causes the apparatus to analyze the text prompt by identifying an understated element in the text prompt that lacks detail.
13 . The system of claim 8 , wherein execution of the processor-executable code further causes the apparatus to analyze the text prompt by identifying a pattern in the text prompt that deviates from an expected norm.
14 . The system of claim 8 , wherein execution of the processor-executable code further causes the apparatus to generate the one or more recommended modifications by generating a prioritized list of keywords or phrases.
15 . A non-transitory computer-readable medium having program code recorded thereon, the program code executed by one or more processors and comprising:
program code to analyze a text prompt to identify one or more characteristics;
program code to generate one or more recommended modifications to the text prompt based on the one or more characteristics;
program code to receive a user selection of at least one of the recommended modifications;
program code to generate a refined text prompt based on the user selection, the refined text prompt comprising one or more prompt variations;
program code to receive a user selection of one of the one or more prompt variations; and
program code to generate, via a generative model, a generative output based on the user-selected prompt variation.
16 . The non-transitory computer-readable medium of claim 15 , wherein the generative output comprises a visualization.
17 . The non-transitory computer-readable medium of claim 15 , wherein the program code further comprises program code to analyze the text prompt by using semantics to identify an ambiguous word or phrase in the text prompt.
18 . The non-transitory computer-readable medium of claim 17 , wherein the program code further comprises program code to identify the ambiguous word or phrase based on historical data associated with a user.
19 . The non-transitory computer-readable medium of claim 15 , wherein the program code further comprises program code to analyze the text prompt by identifying an understated element in the text prompt that lacks detail.
20 . The non-transitory computer-readable medium of claim 15 , wherein the program code further comprises program code to analyze the text prompt by identifying a pattern in the text prompt that deviates from an expected norm.