Methods, systems, and computer readable media for network test configuration and execution using brokered communications with a large language model (LLM)
One example method for network test configuration and execution using brokered communications with a large language model (LLM) comprises receiving, at an LLM communication broker and from a user, input regarding a network test objective for a network test; generating, by the LLM communication broker, based on the input regarding the network test objective, and using an application programming interface (API) of the LLM, input for invoking the LLM to produce configuration instructions for the network test; providing, by the LLM communication broker and to the LLM, the input for invoking the LLM to produce the configuration instructions; receiving, by a network test system, the configuration instructions for the network test; using, by the network test system, the configuration instructions to configure a network test system to conduct the network test; and conducting, by the network test system, the network test.
1 . A method for network test configuration and execution using brokered communications with a large language model (LLM), the method comprising:
receiving, at a large language model (LLM) communication broker and from a user, input regarding a network test objective for a network test;
generating, by the LLM communication broker, based on the input regarding the network test objective, and using an application programming interface (API) of the LLM, input for invoking the LLM to produce configuration instructions for the network test;
providing, by the LLM communication broker and to the LLM, the input for invoking the LLM to produce the configuration instructions, wherein providing the input for invoking the LLM includes supplementing, by the LLM communication broker, the input from the user regarding the test objective for the network test with at least one of input regarding network test system resources and input regarding system under test (SUT) topology;
receiving, by a network test system, the configuration instructions for the network test;
using, by the network test system, the configuration instructions to configure a network test system to conduct the network test; and
conducting, by the network test system, the network test.
2 . The method of claim 1 receiving the input includes receiving natural language input from the user regarding the network test objective.
3 . The method of claim 1 wherein generating the input for invoking the LLM includes engineering a prompt to the LLM for invoking the LLM to produce the configuration instructions.
4 . The method of claim 1 wherein using the configuration instructions to configure the network test includes configuring one or more network traffic generators to generate and send network traffic to a device under test.
5 . The method of claim 1 wherein providing the input to the LLM includes selecting a domain specific LLM based on the input from the user.
6 . The method of claim 1 wherein providing the input to the LLM includes providing the input to an artificial intelligence chatbot, wherein the artificial intelligence chatbot comprises a chat generative pretrained transformer chatbot.
7 . The method of claim 1 comprising, iteratively communicating, by the LLM communication broker and with the LLM, to refine the configuration instructions.
8 . The method of claim 1 comprising receiving, by the LLM communication broker, the configuration instructions, determining that the configuration instructions are inconsistent with available resources of the network test system, and updating the configuration instructions based on the available resources of the network test system and wherein receiving the test configuration instructions includes receiving the updated test configuration instructions from the LLM communication broker.
9 . A system for network test configuration and execution using brokered communications with a large language model (LLM), the system comprising:
a memory;
at least one processor; and
a network test system implemented using the memory and the at least one processor, the network test system configured for:
receiving, at a large language model (LLM) communication broker and from a user, input regarding a network test objective for a network test;
generating, by the LLM communication broker, based on the input regarding the network test objective, and using an application programming interface (API) of the LLM, input for invoking the LLM to produce configuration instructions for the network test;
providing, by the LLM communication broker and to the LLM, the input for invoking the LLM to produce the configuration instructions, wherein providing the input for invoking the LLM includes supplementing, by the LLM communication broker, the input from the user regarding the test objective for the network test with at least one of input regarding network test system resources and input regarding system under test (SUT) topology;
receiving, by a network test system, the configuration instructions for the network test;
using, by the network test system, the configuration instructions to configure a network test system to conduct the network test; and
conducting, by the network test system, the network test.
10 . The system of claim 9 wherein receiving the input includes receiving natural language input from the user regarding the network test objective.
11 . The system of claim 9 wherein generating the input for invoking the LLM includes engineering a prompt to the LLM for invoking the LLM to produce the configuration instructions.
12 . The system of claim 9 wherein using the configuration instructions to configure the network test includes configuring one or more network traffic generators to generate and send network traffic to a device under test.
13 . The system of claim 9 wherein providing the input to the LLM includes selecting a domain specific LLM based on the input from the user.
14 . The system of claim 9 wherein providing the input to the LLM includes providing the input to an artificial intelligence chatbot.
15 . The system of claim 14 wherein the artificial intelligence chatbot comprises a chat generative pretrained transformer chatbot.
16 . The system of claim 9 wherein the network test system is further configured for iteratively communicating, by the LLM communication broker and with the LLM, to refine the configuration instructions.
17 . The system of claim 9 wherein the network test system is further configured for receiving, by the LLM communication broker, the configuration instructions, determining that the configuration instructions are inconsistent with available resources of the network test system, and updating the configuration instructions based on the available resources of the network test system and wherein receiving the test configuration instructions includes receiving the updated test configuration instructions from the LLM communication broker.
18 . A non-transitory computer readable medium having stored thereon executable instructions that when executed by a processor of a computer control the computer to perform steps comprising:
receiving, at a large language model (LLM) communication broker and from a user, input regarding a network test objective for a network test;
generating, by the LLM communication broker, based on the input regarding the network test objective, and using an application programming interface (API) of the LLM, input for invoking the LLM to produce configuration instructions for the network test;
providing, by the LLM communication broker and to the LLM, the input for invoking the LLM to produce the configuration instructions, wherein providing the input for invoking the LLM includes supplementing, by the LLM communication broker, the input from the user regarding the test objective for the network test with at least one of input regarding network test system resources and input regarding system under test (SUT) topology;
receiving, by a network test system, the configuration instructions for the network test;
using, by the network test system, the configuration instructions to configure a network test system to conduct the network test; and
conducting, by the network test system, the network test.