Methods and systems for construction of workflow automation using artificial intelligence
Disclosed herein are methods and systems to generate code for a workflow. A non-limiting example of a method comprises executing, by a processor, a large language model, which receives an input of an intent associated with a workflow and provides a machine-readable description by: identifying, by searching a hierarchical data structure using a vector embedding associated with the intent, an object corresponding to the intent; identifying a set of data paths within the hierarchical data structure to retrieve the identified object; and generating the machine-readable description, the machine-readable description describing the object and at least one data path within the set of data paths; and generating, by the processor, code for the workflow using the machine-readable description.
1 . A method comprising:
executing, by a processor, a large language model, which receives an input of an intent associated with a workflow and provides a machine-readable description by:
identifying, by searching a hierarchical data structure using a vector embedding associated with the intent, an object corresponding to the intent;
identifying a set of data paths within the hierarchical data structure to retrieve the identified object; and
generating the machine-readable description, the machine-readable description describing the object and at least one data path within the set of data paths; and
generating, by the processor, code for the workflow using the machine-readable description.
2 . The method of claim 1 , further comprising:
executing, by the processor, a second large language model to identify the intent using the input.
3 . The method of claim 1 , wherein the at least one data path is selected from the set of data paths using a runtime metric associated with the at least one data path.
4 . The method of claim 1 , wherein the at least one data path is selected from the set of data paths using a number of objects associated with the at least one data path.
5 . The method of claim 1 , further comprising:
generating, by the processor using the large language model, a summary for each path within the set of data paths; and
selecting, by the processor, the at least one data path in accordance with a corresponding summary.
6 . The method of claim 1 , wherein the object has a description within the hierarchical data structure that is semantically similar to the intent.
7 . The method of claim 1 , further comprising:
rendering, by the processor, a visual representation of the workflow.
8 . The method of claim 1 , wherein the workflow has a conditional step.
9 . A computer system comprising:
a server comprising a processor configured to:
execute a large language model, which receives an input of an intent associated with a workflow and provides a machine-readable description by:
identifying, by searching a hierarchical data structure using a vector embedding associated with the intent, an object corresponding to the intent;
identifying a set of data paths within the hierarchical data structure to retrieve the identified object; and
generating the machine-readable description, the machine-readable description describing the object and at least one data path within the set of data paths; and
generate code for the workflow using the machine-readable description.
10 . The computer system of claim 9 , wherein the server is further configured to execute a second large language model to identify the intent using the input.
11 . The computer system of claim 9 , wherein the at least one data path is selected from the set of data paths using a runtime metric associated with the at least one data path.
12 . The computer system of claim 9 , wherein the at least one data path is selected from the set of data paths using a number of objects associated with the at least one data path.
13 . The computer system of claim 9 , wherein the server is further configured to:
generate, using the large language model, a summary for each path within the set of data paths; and
select the at least one data path in accordance with a corresponding summary.
14 . The computer system of claim 9 , wherein the object has a description within the hierarchical data structure that is semantically similar to the intent.
15 . The computer system of claim 9 , wherein the server is further configured to render a visual representation of the workflow.
16 . The computer system of claim 9 , wherein the workflow has a conditional step.
17 . A non-transitory machine-readable storage medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
execute a large language model, which receives an input of an intent associated with a workflow and provides a machine-readable description by:
identifying, by searching a hierarchical data structure using a vector embedding associated with the intent, an object corresponding to the intent;
identifying a set of data paths within the hierarchical data structure to retrieve the identified object; and
generating the machine-readable description, the machine-readable description describing the object and at least one data path within the set of data paths; and
generate code for the workflow using the machine-readable description.
18 . The non-transitory machine-readable storage medium of claim 17 , wherein the instructions further cause the one or more processors to execute a second large language model to identify the intent using the input.
19 . The non-transitory machine-readable storage medium of claim 17 , wherein the at least one data path is selected from the set of data paths using a runtime metric associated with the at least one data path.
20 . The non-transitory machine-readable storage medium of claim 17 , wherein the at least one data path is selected from the set of data paths using a number of objects associated with the at least one data path.