路由

在 路由模式 中，团队领导根据请求内容将用户查询导向最合适的团队成员。

团队领导扮演智能路由器的角色，分析查询并选择最适合处理的代理。然后，成员的响应将直接返回给用户。

路由模式如何工作

在“route”模式下：

1. 团队接收用户查询
2. 团队领导分析查询，确定哪位团队成员具备正确的专业知识
3. 查询被转发给选定的团队成员
4. 团队成员的响应直接返回给用户

当您拥有具有不同专业领域的专业代理并希望自动将查询定向到正确的专家时，此模式特别有用。

1. 创建多语言团队

   创建文件 multi_language_team.py

   multi_language_team.py

   from agno.agent import Agent
   from agno.models.anthropic import Claude
   from agno.models.deepseek import DeepSeek
   from agno.models.mistral.mistral import MistralChat
   from agno.models.openai import OpenAIChat
   from agno.team.team import Team
   
   english_agent = Agent(
       name="English Agent",
       role="You can only answer in English",
       model=OpenAIChat(id="gpt-4.5-preview"),
       instructions=[
           "You must only respond in English",
       ],
   )
   
   japanese_agent = Agent(
       name="Japanese Agent",
       role="You can only answer in Japanese",
       model=DeepSeek(id="deepseek-chat"),
       instructions=[
           "You must only respond in Japanese",
       ],
   )
   chinese_agent = Agent(
       name="Chinese Agent",
       role="You can only answer in Chinese",
       model=DeepSeek(id="deepseek-chat"),
       instructions=[
           "You must only respond in Chinese",
       ],
   )
   spanish_agent = Agent(
       name="Spanish Agent",
       role="You can only answer in Spanish",
       model=OpenAIChat(id="gpt-4.5-preview"),
       instructions=[
           "You must only respond in Spanish",
       ],
   )
   
   french_agent = Agent(
       name="French Agent",
       role="You can only answer in French",
       model=MistralChat(id="mistral-large-latest"),
       instructions=[
           "You must only respond in French",
       ],
   )
   
   german_agent = Agent(
       name="German Agent",
       role="You can only answer in German",
       model=Claude("claude-3-5-sonnet-20241022"),
       instructions=[
           "You must only respond in German",
       ],
   )
   multi_language_team = Team(
       name="Multi Language Team",
       mode="route",
       model=OpenAIChat("gpt-4.5-preview"),
       members=[
           english_agent,
           spanish_agent,
           japanese_agent,
           french_agent,
           german_agent,
           chinese_agent,
       ],
       show_tool_calls=True,
       markdown=True,
       instructions=[
           "You are a language router that directs questions to the appropriate language agent.",
           "If the user asks in a language whose agent is not a team member, respond in English with:",
           "'I can only answer in the following languages: English, Spanish, Japanese, French and German. Please ask your question in one of these languages.'",
           "Always check the language of the user's input before routing to an agent.",
           "For unsupported languages like Italian, respond in English with the above message.",
       ],
       show_members_responses=True,
   )
   
   
   # Ask "How are you?" in all supported languages
   multi_language_team.print_response(
       "How are you?", stream=True  # English
   )
   
   multi_language_team.print_response(
       "你好吗？", stream=True  # Chinese
   )
   
   multi_language_team.print_response(
       "お元気ですか?", stream=True  # Japanese
   )
   
   multi_language_team.print_response(
       "Comment allez-vous?",
       stream=True,  # French
   )
   
2. 运行团队

   安装库

   pip install openai mistral agno
   

   运行团队

   python multi_language_team.py
   

使用路由模式进行结构化输出

路由模式的一项强大功能是能够维护成员代理的结构化输出。 当使用 Pydantic 模型作为响应时，选定团队成员的响应将自动解析为指定的结构。

定义结构化输出模型

from pydantic import BaseModel
from typing import List, Optional
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.team import Team


class StockAnalysis(BaseModel):
    symbol: str
    company_name: str
    analysis: str

class CompanyAnalysis(BaseModel):
    company_name: str
    analysis: str

stock_searcher = Agent(
    name="Stock Searcher",
    model=OpenAIChat("gpt-4o"),
    response_model=StockAnalysis,
    role="Searches for information on stocks and provides price analysis.",
    tools=[
        YFinanceTools(
            stock_price=True,
            analyst_recommendations=True,
        )
    ],
)

company_info_agent = Agent(
    name="Company Info Searcher",
    model=OpenAIChat("gpt-4o"),
    role="Searches for information about companies and recent news.",
    response_model=CompanyAnalysis,
    tools=[
        YFinanceTools(
            stock_price=False,
            company_info=True,
            company_news=True,
        )
    ],
)

team = Team(
    name="Stock Research Team",
    mode="route",
    model=OpenAIChat("gpt-4o"),
    members=[stock_searcher, company_info_agent],
    markdown=True,
)

# This should route to the stock_searcher
response = team.run("What is the current stock price of NVDA?")
assert isinstance(response.content, StockAnalysis)