如需使用 Vertex AI Agent Engine,您必须先开发一个可部署在 Vertex AI Agent Engine 上的代理。开发代理的最简单方法是使用我们提供的特定于框架的模板之一。特定于框架的模板会自动处理开发代理的一些常见方面,例如序列化对象,以及将初始化代理的代码与响应提示的代码分开。我们提供以下特定于框架的模板:
[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-09-10。"],[],[],null,["Overview\n\nTo use Vertex AI Agent Engine, you must first develop an agent that can be deployed on Vertex AI Agent Engine. The easiest way to develop an agent is to use one of the framework-specific templates that we provide. Framework-specific templates automatically handle some of the common aspects of developing an agent such as serializing objects and separating the code that initializes an agent from the code that responds to prompts. We provide the following framework-specific templates:\n\n| Framework | Description |\n|-------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Agent Development Kit](/vertex-ai/generative-ai/docs/agent-engine/develop/adk) | Designed based on Google's internal best practices for developers building AI applications or teams needing to rapidly prototype and deploy robust agent-based solutions. |\n| [Agent2Agent](/vertex-ai/generative-ai/docs/agent-engine/develop/a2a) (preview) | The [Agent2Agent (A2A) protocol](https://a2a-protocol.org/) is an open standard designed to enable seamless communication and collaboration between AI agents. |\n| [LangChain](/vertex-ai/generative-ai/docs/agent-engine/develop/langchain) | Easier to implement for basic use cases because of its predefined configurations and abstractions. |\n| [LangGraph](/vertex-ai/generative-ai/docs/agent-engine/develop/langgraph) | Graph-based approach to defining workflows, with advanced human-in-the-loop and rewind/replay capabilities. |\n| [AG2 (formerly AutoGen)](/vertex-ai/generative-ai/docs/agent-engine/develop/ag2) | AG2 provides multi-agent conversation framework as a high-level abstraction for building LLM workflows. |\n| [LlamaIndex](/vertex-ai/generative-ai/docs/agent-engine/develop/llama-index/query-pipeline) (preview) | LlamaIndex's query pipeline offers a high-level interface for creating Retrieval-Augmented Generation (RAG) workflows. |\n\nIf your use case doesn't align with one of the framework-specific templates, you can [develop your own custom agent](/vertex-ai/generative-ai/docs/agent-engine/develop/custom).\n\nAgent2Agent (A2A) protocol\n\nIf you are building a multi-agent system, we highly recommend reviewing the [A2A Protocol](https://a2a-protocol.org/). A2A Protocol is an open standard that enables seamless communication and collaboration between AI agents, regardless of their underlying frameworks. It was [donated by Google Cloud to the Linux Foundation in June 2025](https://developers.googleblog.com/en/google-cloud-donates-a2a-to-linux-foundation/). To use the A2A SDKs, or try out the samples, check out the [GitHub repository](https://github.com/a2aproject/A2A).\n\nWhat's next\n\n- [Develop a custom agent](/vertex-ai/generative-ai/docs/agent-engine/develop/custom).\n- [Evaluate an agent](/vertex-ai/generative-ai/docs/agent-engine/evaluate).\n- [Deploy an agent](/vertex-ai/generative-ai/docs/agent-engine/deploy).\n- [Get support](/vertex-ai/generative-ai/docs/agent-engine/support)."]]