【LLM】Agents-北京尧图网络

Agents智能体是一个独立的执行单元旨在自主行动以实现特定目标。智能体可以执行任务、与用户互动、使用外部工具以及与其他智能体协调。基于BaseAgent扩展成LlmAgent、WorkflowAgent、CustomAgentLLM agentsLearn more about LLM Agents…code_writer_agent LlmAgent( nameCodeWriterAgent, modelGEMINI_MODEL, # Change 3: Improved instruction instructionYou are a Python Code Generator. Based *only* on the users request, write Python code that fulfills the requirement. Output *only* the complete Python code block, enclosed in triple backticks (python ... ). Do not add any other text before or after the code block. , descriptionWrites initial Python code based on a specification., output_keygenerated_code # Stores output in state[generated_code] )Workflow agentsLearn more about Workflow Agents…Sequential agentscode_pipeline_agent SequentialAgent( nameCodePipelineAgent, sub_agents[code_writer_agent, code_reviewer_agent, code_refactorer_agent], descriptionExecutes a sequence of code writing, reviewing, and refactoring., # The agents will run in the order provided: Writer - Reviewer - Refactorer )Loop agents# Part of agent.py -- Follow https://google.github.io/adk-docs/get-started/quickstart/ to learn the setup import asyncio import os from google.adk.agents import LoopAgent, LlmAgent, BaseAgent, SequentialAgent from google.genai import types from google.adk.runners import InMemoryRunner from google.adk.agents.invocation_context import InvocationContext from google.adk.tools.tool_context import ToolContext from typing import AsyncGenerator, Optional from google.adk.events import Event, EventActions # --- Constants --- APP_NAME doc_writing_app_v3 # New App Name USER_ID dev_user_01 SESSION_ID_BASE loop_exit_tool_session # New Base Session ID GEMINI_MODEL gemini-2.0-flash STATE_INITIAL_TOPIC initial_topic # --- State Keys --- STATE_CURRENT_DOC current_document STATE_CRITICISM criticism # Define the exact phrase the Critic should use to signal completion COMPLETION_PHRASE No major issues found. # --- Tool Definition --- def exit_loop(tool_context: ToolContext): Call this function ONLY when the critique indicates no further changes are needed, signaling the iterative process should end. print(f [Tool Call] exit_loop triggered by {tool_context.agent_name}) tool_context.actions.escalate True # Return empty dict as tools should typically return JSON-serializable output return {} # --- Agent Definitions --- # STEP 1: Initial Writer Agent (Runs ONCE at the beginning) initial_writer_agent LlmAgent( nameInitialWriterAgent, modelGEMINI_MODEL, include_contentsnone, # MODIFIED Instruction: Ask for a slightly more developed start instructionfYou are a Creative Writing Assistant tasked with starting a story. Write the *first draft* of a short story (aim for 2-4 sentences). Base the content *only* on the topic provided below. Try to introduce a specific element (like a character, a setting detail, or a starting action) to make it engaging. Topic: {{initial_topic}} Output *only* the story/document text. Do not add introductions or explanations. , descriptionWrites the initial document draft based on the topic, aiming for some initial substance., output_keySTATE_CURRENT_DOC ) # STEP 2a: Critic Agent (Inside the Refinement Loop) critic_agent_in_loop LlmAgent( nameCriticAgent, modelGEMINI_MODEL, include_contentsnone, # MODIFIED Instruction: More nuanced completion criteria, look for clear improvement paths. instructionfYou are a Constructive Critic AI reviewing a short document draft (typically 2-6 sentences). Your goal is balanced feedback. **Document to Review:** {{current_document}} **Task:** Review the document for clarity, engagement, and basic coherence according to the initial topic (if known). IF you identify 1-2 *clear and actionable* ways the document could be improved to better capture the topic or enhance reader engagement (e.g., Needs a stronger opening sentence, Clarify the characters goal): Provide these specific suggestions concisely. Output *only* the critique text. ELSE IF the document is coherent, addresses the topic adequately for its length, and has no glaring errors or obvious omissions: Respond *exactly* with the phrase {COMPLETION_PHRASE} and nothing else. It doesnt need to be perfect, just functionally complete for this stage. Avoid suggesting purely subjective stylistic preferences if the core is sound. Do not add explanations. Output only the critique OR the exact completion phrase. , descriptionReviews the current draft, providing critique if clear improvements are needed, otherwise signals completion., output_keySTATE_CRITICISM ) # STEP 2b: Refiner/Exiter Agent (Inside the Refinement Loop) refiner_agent_in_loop LlmAgent( nameRefinerAgent, modelGEMINI_MODEL, # Relies solely on state via placeholders include_contentsnone, instructionfYou are a Creative Writing Assistant refining a document based on feedback OR exiting the process. **Current Document:** {{current_document}} **Critique/Suggestions:** {{criticism}} **Task:** Analyze the Critique/Suggestions. IF the critique is *exactly* {COMPLETION_PHRASE}: You MUST call the exit_loop function. Do not output any text. ELSE (the critique contains actionable feedback): Carefully apply the suggestions to improve the Current Document. Output *only* the refined document text. Do not add explanations. Either output the refined document OR call the exit_loop function. , descriptionRefines the document based on critique, or calls exit_loop if critique indicates completion., tools[exit_loop], # Provide the exit_loop tool output_keySTATE_CURRENT_DOC # Overwrites state[current_document] with the refined version ) # STEP 2: Refinement Loop Agent refinement_loop LoopAgent( nameRefinementLoop, # Agent order is crucial: Critique first, then Refine/Exit sub_agents[ critic_agent_in_loop, refiner_agent_in_loop, ], max_iterations5 # Limit loops ) # STEP 3: Overall Sequential Pipeline # For ADK tools compatibility, the root agent must be named root_agent root_agent SequentialAgent( nameIterativeWritingPipeline, sub_agents[ initial_writer_agent, # Run first to create initial doc refinement_loop # Then run the critique/refine loop ], descriptionWrites an initial document and then iteratively refines it with critique using an exit tool. )Parallel agentsCustom agentsMulti-agent systems

【LLM】Agents

相关推荐

Jellium Desktop睡眠模式控制：如何防止播放时电脑休眠

TDDD命令行详解：掌握tddd:watch与tddd:test提升开发效率

-嵌入式高手都在偷偷用的“第35条”：用 objcopy 把版本号、校验码甚至文件系统“烙”进固件里

更多资讯

Cursor Skill 实战：用 SKILL.md 打造 10 分钟可评审测试用例生成器

svgwordpress图解步骤：备案避坑与流量实战

【ModelArts】用VSCode远程连接Notebook：SSH配置与TaoToken接入实践

Cursor + Claude Opus 4.6 完整使用指南｜AI编程神器安装与实操教程（TaoToken 配置篇）

从写作到编程，2026 全场景 AI 工具实测：33 款里先配好 TaoToken 的 5 个配置文件骨架

OpenClaw教程补充内容——飞书Bot配置中TaoToken统一Key接入与WebSocket长连接排错

今日更新

如何彻底离线使用 Laya-CoreML：Hugging Face 下载、缓存机制与 local_files_only 详解

基于1Panel 部署MySQL MCP 服务：TaoToken 统一 Key 接入与 config.toml 配置实战

崇州园区营销网站建设避坑指南：5大注意事项保备案安全

本周精选

如何彻底离线使用 Laya-CoreML：Hugging Face 下载、缓存机制与 local_files_only 详解

基于1Panel 部署MySQL MCP 服务：TaoToken 统一 Key 接入与 config.toml 配置实战

崇州园区营销网站建设避坑指南：5大注意事项保备案安全

本月热门

基于YOLO的焊缝缺陷检测：从数据标注到工业部署全流程实践

分布式服务的决策记录

创业产品的首版范围

读完文章，想聊聊您的网站？