Application arrangement method and device of intelligent agent and medium

Abstract

The invention discloses an intelligent agent application arrangement method and device and a medium, and the method comprises the steps: obtaining a request of a user, determining a plurality of components according to the request, and arranging the plurality of components to obtain an intelligent agent; exporting the intelligent agent to obtain an API (Application Program Interface) service, and packaging the API service; and deploying the packaged API service according to a preset software cluster, and determining an instance corresponding to the API service so as to run through the instance. According to the application, a plurality of components can be quickly determined and arranged according to the user request, the required agent is constructed, and the agent is easily exported to package the API service. And the method also supports deployment of the packaged API service to a preset software cluster, and automatically determines and runs a corresponding instance. The arrangement and deployment mode not only improves the working efficiency, but also ensures the stability and expandability of the agent service, and provides a more convenient and efficient agent application solution for users.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to an application orchestration method, device, and medium for an agent. Background Art

[0002] An agent is an entity that can perceive the environment and take actions to achieve specific goals. An agent can be software, hardware, or a system, and it has autonomy, adaptability, and interaction capabilities. By perceiving changes in the environment, such as through sensors or data input, the agent makes judgments and decisions based on the knowledge and algorithms it has learned, and then executes actions to affect the environment or achieve a predetermined goal. Its core lies in the ability to learn autonomously and evolve continuously to better complete tasks and adapt to complex environments.

[0003] Agent application orchestration development refers to integrating multiple agents with different functions into an application system through specific methods and technologies, and orchestrating and scheduling these agents so that they can work together to complete specific tasks or goals. Traditional agent application orchestration and deployment usually adopt a single model or rule engine to execute specific tasks, lacking flexibility and scalability. Summary of the Invention

[0004] To solve the above problems, this application proposes an application orchestration method for an agent, including: obtaining a user's request, determining multiple components according to the request, and orchestrating the multiple components to obtain an agent; exporting the agent to obtain an API service, and packaging the API service; deploying the packaged API service according to a pre-set software cluster, and determining an instance corresponding to the API service to run through the instance.

[0005] In one example, the method further includes: encapsulating the agent according to a pre-set microservices architecture, and modularizing the agent according to the software cluster, where the modularization process includes automated deployment, expansion, and fault recovery; managing the communication of the agent according to a pre-set service mesh to monitor the communication information and traffic information of the agent.

[0006] In one example, the method further includes: obtaining the user's request through a pre-set large language model, disassembling the request to obtain the multiple components; determining the environmental state corresponding to the agent, and allocating the multiple components according to the environmental state to determine the scheduling of the agent; obtaining the scheduling through a pre-set driver architecture so that the agent executes tasks according to the scheduling.

[0007] In one example, the method further includes: recording data of the agent through a pre-set vector database to store the historical task data corresponding to the agent in the vector database; performing context management on the agent according to the historical task data to continuously process the tasks corresponding to the agent, and determining a corresponding retrieval engine according to the continuously processed agent; and retrieving the task data of the agent according to the retrieval engine.

[0008] In one example, determining a plurality of components according to the request specifically includes: running the plurality of components through pre-set module codes, and enabling the plurality of components to be independent containers after being orchestrated into an agent and running in the form of the independent containers.

[0009] In one example, exporting the agent to obtain an API service specifically includes: exporting the agent in the form of the module code so that the agent provides services for users as an independent API.

[0010] In one example, deploying the packaged API service according to a pre-set software cluster specifically includes: determining a configuration file corresponding to the software cluster, submitting the configuration file to a scheduler corresponding to the software cluster, and determining a corresponding instance according to the configuration file through the scheduler.

[0011] In one example, the method further includes: performing access deployment on the agent according to pre-set authentication and access mechanisms, and establishing an API interface for the agent after access deployment to obtain the access log of the agent through the API interface.

[0012] On the other hand, the present application also provides an application orchestration device for an agent, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the application orchestration device for an agent can execute: the method according to any one of the above examples.

[0013] On the other hand, the present application also provides a non-volatile computer storage medium storing computer-executable instructions, and the computer-executable instructions are set to: the method according to any one of the above examples.

[0014] Through the pre - set module codes and microservice architecture, the agent can quickly and flexibly perform component orchestration and encapsulation, achieving automated deployment, expansion, and fault recovery, which greatly improves the development and deployment efficiency. By introducing service mesh technology, efficient communication and traffic monitoring between agents are realized, ensuring the stability and reliability of services, and facilitating the timely discovery and handling of problems. Combining large - language models with the driving architecture can accurately understand user requests, intelligently allocate components, achieve efficient scheduling and task execution of agents, and improve the response speed and quality of services. Using a vector database for data recording and context management realizes continuous processing of agent tasks, improves the coherence and accuracy of task processing, and facilitates the retrieval and analysis of historical data. Through the cooperation of software clusters and schedulers, rapid deployment of API services and instance creation are achieved, ensuring the efficient operation and elastic scaling ability of agent services. Establishing API interfaces and access log records, combined with authentication and access mechanisms, ensures secure access and control of agent services, enhancing the overall security of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0016] Figure 1 It is a schematic flow chart of an application orchestration method for an agent in an embodiment of the present application;

[0017] Figure 2 It is a schematic diagram of an application orchestration device for an agent in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments and corresponding drawings of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0019] The following will describe in detail the technical solutions provided by each embodiment of the present application in conjunction with the drawings.

[0020] As Figure 1 shown, to solve the above - mentioned problems, an application orchestration method for an agent provided by an embodiment of the present application includes:

[0021] S101. Obtain the user's request, determine multiple components according to the request, and orchestrate the multiple components to obtain an agent.

[0022] A Large Language Model (LLM) is an artificial intelligence model based on deep learning, designed to process and generate natural language text. Through the intelligent agent application orchestration workflow construction tool of the LLM model, the support for LangChain is integrated, providing users with a powerful graphical operation platform. On this platform, users can easily orchestrate multiple key components, including the LLM model itself, various utility tools, and databases, etc. Through flexible orchestration and combination, users can quickly build intelligent agents (Agents) with rich functions and efficient collaboration, thus meeting the needs of diverse application scenarios.

[0023] Each component module in this tool is carefully written in Python, ensuring clear readability and strong scalability of the code. These modules not only achieve a high degree of independence, can run independently and complete specific tasks, but also through sophisticated architecture design, achieve seamless docking and efficient collaboration between modules. This design method not only improves the overall stability and reliability of the system, but also brings great convenience to subsequent maintenance and upgrade work.

[0024] In one embodiment, after the user completes the orchestration and combination of components through the graphical interface, the constructed intelligent agent can be directly packaged as an independent container for running. This feature greatly simplifies the deployment and management process of the intelligent agent, enabling users to focus more on the development and optimization of the intelligent agent's functions, without having to spend too much energy in complex system configuration and running environments.

[0025] S102. Export the intelligent agent to obtain an API service, and package the API service.

[0026] After completing the intelligent agent application orchestration of the LLM model, the carefully constructed Agent is exported in the form of Python code, enabling it to run as an independent FastAPI service. This not only endows the Agent with broader application potential, but also ensures its stability and compatibility in different environments.

[0027] In one embodiment, the internal logic of the Agent is carefully sorted out and optimized to ensure that it can seamlessly dock with the FastAPI framework and provide efficient and reliable API interface services. Subsequently, by writing corresponding Python code, the core functions of the Agent are closely combined with the routing, request handling and other mechanisms of FastAPI to build a complete and easy-to-deploy Web service.

[0028] In one embodiment, to further improve the deployment efficiency and flexibility of the Agent, Docker containerization technology is adopted. By configuring a suitable Docker environment, including installing necessary Python dependency libraries, setting environment variables, and mounting necessary volumes, this independent Python application is packaged into a Docker container. This container not only contains all components required by the Agent service but also achieves complete isolation from the host environment, thus ensuring the security and stability of the service.

[0029] In one embodiment, detailed Docker running instructions and configuration file examples are also provided to help users quickly start and manage this containerized Agent service. Whether in the development and testing stage or the production deployment link, users can easily achieve the rapid deployment and efficient operation of the Agent service.

[0030] S103. Deploy the packaged API service according to a pre-set software cluster, and determine an instance corresponding to the API service to run through the instance.

[0031] Deploy the agent to a Kubernetes (K8s) cluster. According to the running requirements of the agent container, write a K8sDeployment configuration file. This file defines in detail key parameters such as the image information, number of replicas, and resource limits of the agent container, ensuring the correct deployment and operation of the container in the K8s cluster. Subsequently, submit this configuration file to the K8s scheduler, which automatically creates corresponding Pod instances according to the resource status and scheduling strategy of the cluster.

[0032] On this basis, a multi-instance running strategy is also configured. By increasing the number of replicas in the Deployment, horizontal scaling of the agent service is achieved. This not only improves the availability and fault tolerance of the service but also makes it possible to achieve load balancing. To further optimize the performance and reliability of the agent service, Service Mesh technology is introduced, through which functions such as intelligent routing, traffic management, and service governance among agent instances are realized.

[0033] The introduction of Service Mesh makes the elastic scaling and load balancing of the agent service more flexible and efficient. Whether facing sudden traffic peaks or daily stable operations, Service Mesh can automatically adjust the number and distribution of agent instances according to the real-time service status and load conditions, ensuring the continuous stable and efficient operation of the service.

[0034] Such as Figure 2As shown in the figure, an application orchestration device for an intelligent agent provided by an embodiment of the present application includes:

[0035] At least one processor; and,

[0036] A memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable an application orchestration device for an intelligent agent to execute: the method described in any one of the above embodiments.

[0038] An embodiment of the present application also provides a non-volatile computer storage medium storing computer-executable instructions, and the computer-executable instructions are set to: the method described in any one of the above embodiments.

[0039] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers can program themselves to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL), and there is not just one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing a little logical programming on the method flow using the above-mentioned several hardware description languages and programming it into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0040] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0041] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0042] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0043] Each embodiment in this application is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0044] The devices, media, and methods provided by the embodiments of this application are in one-to-one correspondence. Therefore, the devices and media also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be elaborated here.

[0045] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0046] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0047] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0049] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0050] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0051] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0052] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0053] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for arranging applications of an intelligent agent, characterized in that: include: Obtaining a user's request, determining a plurality of components according to the request, and arranging the plurality of components to obtain an intelligent agent; Exporting the agent to obtain an API service, and packaging the API service; The packaged API service is deployed according to a pre-set software cluster, and an instance corresponding to the API service is determined so as to run the service through the instance.

2. The method according to claim 1, characterized in that The method further comprises: Encapsulating the agent according to a preset microservice architecture, and modularizing the agent according to the software cluster, wherein the modularization includes automated deployment, expansion, and fault recovery; The communication of the intelligent agent is managed according to a preset service grid to monitor the communication information and flow information of the intelligent agent.

3. The method according to claim 1, characterized in that The method further comprises: Acquire the request of the user through a preset large language model, and decompose the request to obtain the multiple components; Determine an environment state corresponding to the agent, and allocate the plurality of components according to the environment state to determine a schedule for the agent; The schedule is obtained through a preset driving architecture so that the agent performs tasks according to the schedule.

4. The method according to claim 1, characterized in that The method further comprises: Recording data of the agent through a preset vector database to store historical task data corresponding to the agent in the vector database; Performing context management on the agent according to the historical task data to continuously process the tasks corresponding to the agent, and determining a corresponding search engine according to the continuously processed agent; The task data of the agent is retrieved according to the retrieval engine.

5. The method according to claim 1, characterized in that Multiple components are determined based on the request, including: The multiple components are run through a preset module code, and after being arranged into an intelligent body, the multiple components are run as independent containers in the form of the independent containers.

6. The method according to claim 5, characterized in that The agent is exported to obtain API services, including: The agent is exported in the form of the module code, so that the agent provides services to users as an independent API.

7. The method according to claim 1, characterized in that Deploy the packaged API service according to the pre-set software cluster, specifically including: A configuration file corresponding to the software cluster is determined, the configuration file is submitted to a scheduler corresponding to the software cluster, and the scheduler determines a corresponding instance according to the configuration file.

8. The method according to claim 1, characterized in that The method further comprises: The agent is access-deployed according to a preset authentication mechanism and access mechanism, and an API interface is established for the agent after access deployment, so as to obtain the access log of the agent through the API interface.

9. An application arrangement device for an intelligent agent, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the application orchestration device of the intelligent agent to execute: the method as claimed in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured as follows: a method as described in any one of claims 1 to 8.

Images