Method and system for automatic workflow generation by large language models
A method for using a large language model to generate executable code for workflow execution in a manner that integrates user feedback and adjusts the workflow as needed while preserving data privacy is provided. The method includes: receiving first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request; using the received information to generate a lecture, and transmitting the lecture to a language model; receiving a user query that relates to performing a task, and transmitting the query to the language model; receiving a workflow that is automatically generated by the language model based on the lecture and the query; and executing the workflow in order to generate an output that is responsive to the query.
1. A method for generating a workflow, the method being implemented by at least one processor, the method comprising:
receiving, by the at least one processor, first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request;
transmitting a lecture, generated by the at least one processor based on the first information, the second information, and the third information, to a language model;
receiving, by the at least one processor from a user, a query that relates to performing a task, and transmitting the query to the language model;
receiving, by the at least one processor from the language model, a workflow that is automatically generated by the language model based on the lecture and the query; and
generating, by the at least one processor from the language model, executable code for workflow execution.
2. The method of claim 1 , further comprising executing the workflow in order to generate an output that is responsive to the query.
3. The method of claim 1 , further comprising:
receiving, from the user, feedback that relates to the workflow;
transmitting the feedback to the language model; and
receiving, from the language model, a modified workflow that is automatically generated based on the feedback.
4. The method of claim 1 , wherein the first information includes a textual description of a domain of a task to be performed based on an expected type of the query.
5. The method of claim 1 , wherein the second information includes a name, an input argument type, and a description of an output type for at least one API from among a predetermined set of APIs that corresponds to a predetermined library of functions.
6. The method of claim 1 , wherein the query includes a request for a specific type of information.
7. The method of claim 6 , wherein the query relates to fourth information included in a set of annual filings for registered investment companies that are submitted pursuant to a governmental regulation and are publicly available.
8. The method of claim 7 , wherein the fourth information relates to a single fund that is administered by a single investment company.
9. The method of claim 7 , wherein the fourth information relates to a plurality of funds that are administered by a single investment company.
10. The method of claim 1 , further comprising displaying an output on a display via a graphical user interface (GUI).
11. A computing apparatus for generating a workflow, the computing apparatus comprising:
a processor;
a memory;
a display; and
a communication interface coupled to each of the processor, the memory, and the display,
wherein the processor is configured to:
receive, via the communication interface, first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request;
transmit a lecture, generated by the at least one processor based on the first information, the second information, and the third information, to a language model;
receive, via the communication interface from a user, a query that relates to performing a task, and transmit the query to the language model;
receive, from the language model, a workflow that is automatically generated by the language model based on the lecture and the query; and
generate, from the language model, executable code for workflow execution.
12. The computing apparatus of claim 11 , wherein the processor is further configured to execute the workflow in order to generate an output that is responsive to the query.
13. The computing apparatus of claim 11 , wherein the processor is further configured to:
receive, from the user via the communication interface, feedback that relates to the workflow;
transmit the feedback to the language model; and
receive, from the language model, a modified workflow that is automatically generated based on the feedback.
14. The computing apparatus of claim 11 , wherein the first information includes a textual description of a domain of a task to be performed based on an expected type of the query.
15. The computing apparatus of claim 11 , wherein the second information includes a name, an input argument type, and a description of an output type for at least one API from among a predetermined set of APIs that corresponds to a predetermined library of functions.
16. The computing apparatus of claim 11 , wherein the query includes a request for a specific type of information.
17. The computing apparatus of claim 16 , wherein the query relates to fourth information included in a set of annual filings for registered investment companies that are submitted pursuant to a governmental regulation and are publicly available.
18. The computing apparatus of claim 11 , wherein the processor is further configured to cause the display to display an output via a graphical user interface (GUI).
19. A non-transitory computer readable storage medium storing instructions for generating a workflow, the storage medium comprising first executable code which, when executed by a processor, causes the processor to:
receive first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request;
transmit a lecture, generated by the at least one processor based on the first information, the second information, and the third information, to a language model;
receive, from a user, a query that relates to performing a task, and transmit the query to the language model;
receive, from the language model, a workflow that is automatically generated by the language model based on the lecture and the query; and
generate, from the language model, second executable code for workflow execution.
20. The storage medium of claim 19 , wherein when executed, the first executable code further causes the processor to execute the workflow in order to generate an output that is responsive to the query.