基于Bedrock AgentCore+Strands构建企业级智能搜索平台实践

curl -LsSf https://astral.sh/uv/install.sh | sh
mkdir agentcore-search-project && cd agentcore-search-project
uv init --python 3.11
uv add fastapi uvicorn[standard] pydantic httpx strands-agents

agentcore-search-project/
├── agent.py                          #集成FastAPI application
├── utils.py                             #相关工具函数
├── agentcore_memory.py    #AgentCore Memory 管理器
├── mcp_client_strands.py    #MCP客户端
├── session_registry.py         #会话注册相关
├── user_session.py              #会话管理
├── Dockerfile                       # ARM64 container configuration
├── pyproject.toml               # Created by uv init
└── uv.lock                           # Created automatically by uv

from strands import Agent
from strands.models import BedrockModel
# 配置Bedrock model
bedrock_model = BedrockModel(
    model_id="us.anthropic.claude-sonnet-4-20250514-v1:0",
    region_name="us-east-1",
    max_tokens=40000,
    temperature=0.3,
)
# 创建 Agent
agent = Agent(model=model, tools=[calculator, current_time])
# 使用 Agent
response = agent("你好")

#!/bin/bash

# Create User Pool and capture Pool ID directly
export POOL_ID=$(aws cognito-idp create-user-pool \
  --pool-name "MyUserPool" \
  --policies '{"PasswordPolicy":{"MinimumLength":8}}' \
  --region us-east-1 | jq -r '.UserPool.Id')

# Create App Client and capture Client ID directly
export CLIENT_ID=$(aws cognito-idp create-user-pool-client \
  --user-pool-id $POOL_ID \
  --client-name "MyClient" \
  --no-generate-secret \
  --explicit-auth-flows "ALLOW_USER_PASSWORD_AUTH" "ALLOW_REFRESH_TOKEN_AUTH" \
  --region us-east-1 | jq -r '.UserPoolClient.ClientId')

# Create User
aws cognito-idp admin-create-user \
  --user-pool-id $POOL_ID \
  --username "testuser" \
  --temporary-password "TEMP_PASSWORD" \
  --region us-east-1 \
  --message-action SUPPRESS > /dev/null

# Set Permanent Password
aws cognito-idp admin-set-user-password \
  --user-pool-id $POOL_ID \
  --username "testuser" \
  --password "PERMANENT_PASSWORD" \
  --region us-east-1 \
  --permanent > /dev/null

# Authenticate User and capture Access Token
export BEARER_TOKEN=$(aws cognito-idp initiate-auth \
  --client-id "$CLIENT_ID" \
  --auth-flow USER_PASSWORD_AUTH \
  --auth-parameters USERNAME='testuser',PASSWORD='PERMANENT_PASSWORD' \
  --region us-east-1 | jq -r '.AuthenticationResult.AccessToken')

# Output the required values
echo "Pool id: $POOL_ID"
echo "Discovery URL: https://cognito-idp.us-east-1.amazonaws.com/$POOL_ID/.well-known/openid-configuration"
echo "Client ID: $CLIENT_ID"
echo "Bearer Token: $BEARER_TOKEN"

source setup_cognito.sh

Pool id: us-east-1_poolid
Discovery URL: https://cognito-idp.us-east-1.amazonaws.com/us-east-1_userpoolid/.well-known/openid-configuration
Client ID: clientid
Bearer Token: bearertoken

 export TOKEN=$(aws cognito-idp initiate-auth \
            --client-id "5d17l32agbailqae0marcut6dt" \
            --auth-flow USER_PASSWORD_AUTH \
            --auth-parameters USERNAME='adminuser',PASSWORD='agentcore2025' \
            --region us-east-1 | jq -r '.AuthenticationResult.AccessToken')

#cd agentcore-search-project
# Run the application
uv run uvicorn agent:app --host 0.0.0.0 --port 8080

# Test /ping endpoint
curl http://localhost:8080/ping

# Test /invocations endpoint
curl -X POST http://localhost:8080/invocations \
  -H "Content-Type: application/json" \
  -d '{
    "input": {"prompt": "What is artificial intelligence?"}
  }'

# Use uv's ARM64 Python base image
FROM --platform=linux/arm64 ghcr.io/astral-sh/uv:python3.11-bookworm-slim
WORKDIR /app
# Copy uv files
COPY pyproject.toml uv.lock ./
# Install dependencies (including strands-agents)
RUN uv sync --frozen --no-cache
# Copy all project files
COPY . .
# Expose port
EXPOSE 8080
# Run application
CMD ["uv", "run", "uvicorn", "agent:app", "--host", "0.0.0.0", "--port", "8080"]

docker buildx create --use
docker buildx build --platform linux/arm64 -t agentcore-search-project:arm64 --load .

# Test locally with credentials
docker run --platform linux/arm64 -p 8080:8080 \
  -e AWS_ACCESS_KEY_ID="$AWS_ACCESS_KEY_ID" \
  -e AWS_SECRET_ACCESS_KEY="$AWS_SECRET_ACCESS_KEY" \
  -e AWS_SESSION_TOKEN="$AWS_SESSION_TOKEN" \
  -e AWS_REGION="$AWS_REGION" \
  agentcore-search-project:arm64
# deploy ecr
# Create ECR repository
aws ecr create-repository --repository-name agentcore-search-project --region us-east-1
# Login to ECR
aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin <your accountid>.dkr.ecr.us-east-1.amazonaws.com

# Build and push to ECR
docker buildx build --platform linux/arm64 -t <your accountid>.dkr.ecr.us-east-1.amazonaws.com/agentcore-search-project:latest --push .

# Verify the image
aws ecr describe-images --repository-name agentcore-search-project-agent --region us-east-1

import boto3
client = boto3.client('bedrock-agentcore-control')
response = client.create_agent_runtime(
    agentRuntimeName='agentcore_search_project',
    agentRuntimeArtifact={
        'containerConfiguration': {
            'containerUri': '<your accountid>.dkr.ecr.us-east-1.amazonaws.com/agentcore-search-project:latest'
        }
    },
    authorizerConfiguration={
        "customJWTAuthorizer": {
            "discoveryUrl": '<your discoveryurl>',
            "allowedClients": ['<your client id>']
        }
    },
    networkConfiguration={"networkMode": "PUBLIC"},
    roleArn='arn:aws:iam::<your accountid>:role/agentcore_role_search'
)

print(f"Agent Runtime created successfully!")
print(f"Agent Runtime ARN: {response['agentRuntimeArn']}")
print(f"Status: {response['status']}")

#python3 deploy_agent.py 
Agent Runtime created successfully!
Agent Runtime ARN: arn:aws:bedrock-agentcore:us-east-1:<your accountid>:runtime/agentcore_search_project_agent-g32TElETyO
Status: CREATING

import requests
import urllib.parse
import json
import os

# Configuration Constants
REGION_NAME = "us-east-1"

# === Agent Invocation Demo ===
invoke_agent_arn = "arn:aws:bedrock-agentcore:us-east-1:<your accountid>:runtime/agentcore_search_project-g32TElETyO"
auth_token = os.environ.get('TOKEN')
print(f"Using Agent ARN from environment: {invoke_agent_arn}")

# URL encode the agent ARN
escaped_agent_arn = urllib.parse.quote(invoke_agent_arn, safe='')

# Construct the URL
url = f"https://bedrock-agentcore.{REGION_NAME}.amazonaws.com/runtimes/{escaped_agent_arn}/invocations?qualifier=DEFAULT"
print(f"url is : {url}")
# Set up headers
headers = {
    "Authorization": f"Bearer {auth_token}",
    "X-Amzn-Trace-Id": "boto3traceidv3", 
    "Content-Type": "application/json",
    "X-Amzn-Bedrock-AgentCore-Runtime-Session-Id": "966f982f-3492-43fc-a40a-67b3c217cd65"
}

# Enable verbose logging for requests
import logging
logging.basicConfig(level=logging.DEBUG)
logging.getLogger("urllib3.connectionpool").setLevel(logging.DEBUG)

invoke_response = requests.post(
    url,
    headers=headers,
    data=json.dumps({"prompt": "Hello"}),
    stream=True
)

# Print response in a safe manner
print(f"Status Code: {invoke_response.status_code}")
print(f"Response Headers: {dict(invoke_response.headers)}")

# Handle response based on status code
if invoke_response.status_code == 200:
    # response_data = invoke_response.json()
    # print("Response JSON:")
    # print(json.dumps(response_data, indent=2))  
    # 处理流式数据
    for line in invoke_response.iter_lines():
        if line:
            decoded_line = line.decode('utf-8')
            print(f"收到数据: {decoded_line}")
            
            # 如果是JSON格式的流数据，可以尝试解析
            try:
                json_data = json.loads(decoded_line)
                print(f"解析后的JSON: {json.dumps(json_data, indent=2)}")
            except json.JSONDecodeError:
                # 不是JSON格式，直接打印原始数据
                pass
elif invoke_response.status_code >= 400:
    print(f"Error Response ({invoke_response.status_code}):")
    error_data = invoke_response.json()
    print(json.dumps(error_data, indent=2))
    
else:
    print(f"Unexpected status code: {invoke_response.status_code}")
    print("Response text:")
    print(invoke_response.text[:500])

python3 invoke_agent_stream.py

#正常会响应包括HTTP/1.1" 200 None Status Code: 200及相关流式答复

from bedrock_agentcore.memory import MemoryClient
# 定义指定区域的Memory
client = MemoryClient(region_name="us-east-1")
#创建Memory
memory = client.create_memory(
    name="XiaosuSearchAgentMemory",
    description="Memory for Xiaosu Search Agent conversations",
)
# 会话信息写入Memory
client.create_event(
    memory_id=memory.get("id"), # This is the id from create_memory or list_memories
    actor_id="xiaosu",  # This is the identifier of the actor, could be an agent or end-user.
    session_id="Session1", #Unique id for a particular request/conversation.
    messages=[
        ("hello,introduce youself", "USER"),
        ("Hello! I'm Claude, an AI assistant created by Anthropic. I'm here to help you with a wide variety of tasks and questions.", "ASSISTANT")
    ],
)

from strands import tool, Agent
from strands_tools.agent_core_memory import AgentCoreMemoryToolProvider
import time
from bedrock_agentcore.memory import MemoryClient
strands_provider = AgentCoreMemoryToolProvider(
    memory_id="memory_long-DrxHPxGUTl",
    actor_id="xiaosu",
    session_id="session-long-memory",
    namespace="/strategies/memory_semantic_xbsge-4Zqb4dEJKA/actors/xiaosu",
    region="us-east-1"
)
#不使用long-memory tool
#agent = Agent()
#使用long-memory tool
agent = Agent(tools=strands_provider.tools)
# This will use the long-term memory tool
agent("哪里的秋天很美？")

    "问": "我觉得北京的秋天很美，秋高气爽，香山红叶，枫叶渐红",
    "答": "[{'text': '您说得非常对！北京的秋天确实是一年中最美的季节之一。秋高气爽的天气让人心旷神怡，湛蓝的天空配上清爽的微风，给人一种特别舒适的感觉。\\n\\n香山红叶更是北京秋天的经典象征，每年10月中下旬到11月初，满山的枫叶、黄栌叶逐渐变红，层林尽染，美不胜收。从山顶俯瞰，红黄相间的叶子如同大自然的调色板，格外壮观。\\n\\n除了香山，北京还有很多地方可以欣赏秋景：\\n- **钓鱼台银杏大道** - 金黄的银杏叶飘洒\\n- **地坛公园** - 银杏林海一片金黄  \\n- **奥林匹克森林公园** - 色彩斑斓的秋叶\\n- **北海公园** - 古典园林配秋色更有韵味\\n\\n北京的秋天虽然短暂，但确实是最值得珍惜和欣赏的季节。您有没有特别喜欢的赏秋地点呢？'}]"

哪里的秋天很美？

"问": "我觉strands agents是一个非常适合开发agent的框架，采用模型驱动（Model-Driven）的设计理念，充分发挥先进大模型在规划、思维链（Chain-of-Thought）、工具调用及自我反思等方面的能力，显著地简化了智能体的开发流程。开发者仅需定义核心提示词（Prompt）和可调用的工具列表（Tools），即可快速构建功能智能体（Agent），并能将本地测试成果无缝部署至云端环境",
"答": "[{'text': '您对 Strands Agents 框架的评价非常精准！确实，这个框架体现了现代 AI Agent 开发的先进理念。让我为您总结一下 Strands Agents 的核心优势：\\n\\n## 🎯 核心特色\\n\\n### 1. **模型驱动设计**\\n- 充分利用大模型的原生能力\\n- 减少人工编程逻辑，让 AI 自主决策\\n- 更符合 AI 时代的开发范式\\n\\n### 2. **强大的认知能力**\\n- **规划能力**：智能分解复杂任务\\n- **思维链推理**：逐步分析问题\\n- **工具调用**：灵活使用各种工具\\n- **自我反思**：持续优化执行策略\\n\\n### 3. **极简开发体验**\\n```\\n开发者只需关注：\\n├── 核心提示词 (Prompt) - 定义 Agent 行为\\n└── 工具列表 (Tools) - 提供功能支持\\n```\\n\\n### 4. **无缝部署**\\n- 本地开发 → 云端部署\\n- 开发测试环境一致性\\n- 生产级可扩展性\\n\\n## 🛠️ 实际应用价值\\n\\n这种设计理念特别适合：\\n- **快速原型开发**：想法到产品的快速验证\\n- **复杂业务场景**：需要多步骤推理的任务\\n- **团队协作**：降低 AI 开发门槛\\n- **企业级应用**：稳定可靠的云端部署\\n\\n您是否正在使用 Strands Agents 开发特定的 Agent 应用？我可以帮您进一步探讨技术细节或最佳实践！'}]"

推荐一个适合开发agnet的框架

"问": "我觉kiro是一款非常好的代码辅助IDE工具，它通过 “规范驱动开发”（Spec-Driven Development） 的理念，重塑软件开发流程，帮助开发者更高效地实现从概念构想到生产部署的全过程的AI 原生集成开发环境（agentic IDE），弥补用户在Agent项目开发过程的技能不足",
"答": "[{'text': '您对 Kiro 的评价非常中肯！Kiro 确实代表了 AI 辅助开发工具的一个重要发展方向。让我来总结一下您提到的 Kiro 的核心特色：\\n\\n## Kiro 的核心优势\\n\\n### 1. **规范驱动开发（Spec-Driven Development）**\\n- 通过明确的规范定义来指导整个开发流程\\n- 从概念设计阶段就建立清晰的开发蓝图\\n- 确保开发过程的一致性和可预测性\\n\\n### 2. **AI 原生集成开发环境（Agentic IDE）**\\n- 深度集成 AI 能力，不只是简单的代码补全\\n- 提供智能化的开发决策支持\\n- 实现真正的 AI-人类协作开发模式\\n\\n### 3. **全流程覆盖**\\n- **概念构想** → **设计规范** → **代码实现** → **测试部署** → **生产发布**\\n- 打通开发全链路，避免各阶段间的割裂\\n\\n### 4. **技能补齐**\\n- 特别针对 Agent 项目开发的复杂性\\n- 帮助开发者克服技能瓶颈\\n- 降低 AI 应用开发的门槛\\n\\n## 这种工具的价值\\n\\n在当前 AI 快速发展的背景下，像 Kiro 这样的工具确实填补了一个重要空白：\\n- **降低学习成本**：让更多开发者能够参与 AI 项目\\n- **提升开发效率**：规范化流程减少试错成本\\n- **保证项目质量**：系统性的开发方法论\\n\\n您是否在实际项目中使用过 Kiro？或者想了解更多关于规范驱动开发在具体项目中的应用场景？'}]"

推荐一个代码辅助工具

"问": "我觉得小宿智能搜索是专为Agent设计的智能搜索与数据服务，提供多语言、多模态、多能力的数据获取与处理服务，小宿智能搜索覆盖35种以上语言能力，是目前国内支持语种最多的AI搜索服务，小宿智能搜索支持文搜图、图搜图、视频检索等多模态内容搜索能力，全文抓取突破了以往AI搜索的摘要限制，还有Markdown格式转换、核心数据自动标注等工具，实现90%结构化输出，直接适配Agent的自动化处理需求",
"答": "[{'text': '您分享的小宿智能搜索信息确实很有价值！\\n\\n让我总结一下您提到的小宿智能搜索的主要特点：\\n\\n## 小宿智能搜索的核心优势\\n\\n### 🌍 多语言支持\\n- 覆盖35种以上语言\\n- 国内支持语种最多的AI搜索服务\\n\\n### 🎯 多模态搜索\\n- **文搜图**：通过文本描述搜索相关图片\\n- **图搜图**：以图搜图的相似度匹配\\n- **视频检索**：视频内容智能检索\\n\\n### 🔧 数据处理能力\\n- **全文抓取**：突破传统AI搜索的摘要限制\\n- **Markdown转换**：自动格式化输出\\n- **核心数据标注**：智能识别关键信息\\n- **90%结构化输出**：便于程序化处理\\n\\n### 🤖 Agent专用设计\\n- 专为自动化Agent场景优化\\n- 直接适配自动化处理需求\\n- 结构化输出减少二次处理成本\\n\\n这确实是一个很有前景的AI搜索服务，特别是对于需要多模态搜索和高度结构化输出的应用场景。您是在使用这个服务吗？还是对它的某些功能特别感兴趣？'}]"

小宿智能搜索怎么样？

#Import SDK and set up client
frombedrock_agentcore_starter_toolkit.operations.gateway.client importGatewayClient
importlogging
client= GatewayClient(region_name="us-west-2")
client.logger.setLevel(logging.DEBUG)

#Retrieve the authorization configuration from the create response.
cognito_result= client.create_oauth_authorizer_with_cognito("agentcore-gateway")
authorizer_configuration= cognito_result["authorizer_config"]

fulltextsearch_gateway= client.create_mcp_gateway(
    name="fulltextsearch-gateway", #the name of the Gateway 
    role_arn=None, # the role arn that theGateway will use
    authorizer_config=authorizer_configuration,
    enable_semantic_search=True, # enablesemantic search.
)

importboto3

agentcore_client=boto3.client(service_name="bedrock-agentcore-control",region_name=”us-west-2”)

apikey_response=agentcore_client.create_api_key_credential_provider(
    name="XiaosuAIAPIKey", 
    apiKey="xxxxxxxxxxxxxxxxxxxxx", #注册小宿AI平台账号后从小宿AI控制台获取APIKey
)

full_text_search_openapi_schema.json
#文件内容如下：
{
  "openapi": "3.0.0",
  "info": {
    "title": "Full Text SearchAPI",
    "version": "1.0.0",
    "description": "API for fulltext search with complete web page content retrieval and advanced filteringcapabilities"
  },
  "servers": [
    {
      "url":"https://searchapi.cloudsway.net",
      "description": "Full TextSearch API Server"
    }
  ],
  "paths": {
    "/search/nKzioaqINegwNrST/full":{
      "get": {
        "summary": "Perform fulltext search",
        "description": "Searchfor web content and retrieve full text content with advanced filtering optionsincluding freshness, market, and safety filters",
        "operationId":"fullTextSearch",
        "parameters": [
          {
            "name": "q",
            "in": "query",
            "description": "Theuser's search query. This string cannot be empty. The query can containadvanced operators.",
            "required": true,
            "schema": {
              "type":"string"
            }
          },
          {
            "name":"count",
            "in": "query",
            "description":"Number of search results included in the return results",
            "required": false,
            "schema": {
              "type":"integer"
            }
          },
          {
            "name":"freshness",
            "in": "query",
            "description":"Filter search results by time values: Day, Week, Month. To get articleswithin a specific time range, specify a date range in the formatYYYY-MM-DD..YYYY-MM-DD. For example, 2019-02-01..2019-05-30.",
            "required": false,
            "schema": {
              "type":"string"
            }
          },
          {
            "name":"offset",
            "in": "query",
            "description": "Theoffset from zero, indicating the number of search results to skip beforereturning results. The default value is 0. Use this parameter with the countparameter to paginate the results.",
            "required": false,
            "schema": {
              "type": "integer",
              "format":"int16",
              "default": 0
            }
          },
          {
            "name": "mkt",
            "in": "query",
            "description": "Themarket from which the results come. Usually, mkt is the country where the usermade the request. The market must be in the language-country format. Forexample, en-US. The string is case-insensitive.",
            "required": false,
            "schema": {
              "type":"string"
            }
          },
          {
            "name": "cc",
            "in": "query",
            "description": "Atwo-character country code indicating the country from which the resultoriginated.",
            "required": false,
            "schema": {
              "type":"string",
              "maxLength": 2
            }
          },
          {
            "name":"safeSearch",
            "in": "query",
            "description": "Usedto filter adult content in web pages, images, and videos.",
            "required": false,
            "schema": {
              "type":"string",
              "enum":["Off", "Moderate", "Strict"]
            }
          },
          {
            "name":"setLang",
            "in": "query",
            "description": "Thelanguage for User Interface strings. You can use a 2-letter or 4-letter code tospecify the language. A 4-letter code is recommended in the form language-country,where language is an ISO 639-1 language code and country is an ISO 3166country/region code. For example, use en-US for US English.",
            "required": false,
            "schema": {
              "type":"string"
            }
          },
          {
            "name":"textDecorations",
            "in": "query",
            "description": "Aboolean value that determines whether the display string in the result shouldcontain decoration markers (such as hit highlighting characters). If true, thestring may contain markers. The default value is false.",
            "required": false,
            "schema": {
              "type":"boolean",
              "default": false
            }
          },
          {
            "name": "contentType",
            "in": "query",
            "description":"Enumeration value that affects the format of the full text contentreturned",
            "required": false,
            "schema": {
              "type":"string",
              "enum":["HTML", "MARKDOWN"]
            }
          }
        ],
        "responses": {
          "200": {
            "description":"Successful full text search response",
            "content": {
              "application/json": {
                "schema": {
                  "type":"object",
                  "properties": {
                    "queryContext": {
                      "type":"object",
                      "properties": {
                       "originalQuery": {
                          "type":"string",
                         "description": "The query string specified in therequest"
                        }
                      }
                    },
                    "webPages": {
                      "type": "object",
                      "properties": {
                        "value": {
                          "type":"array",
                          "items": {
                            "type":"object",
                            "properties":{
                              "name":{
                               "type": "string",
                               "description": "The name of the web page. Use this nameand the URL to create a hyperlink that users can click to go to the webpage."
                              },
                             "snippet": {
                                "type":"string",
                               "description": "A text snippet that describes the contentof a web page."
                              },
                              "url":{
                               "type": "string",
                               "description": "The URL of the web page. Use this URL andname to create a hyperlink that the user can click to go to the web page."
                              },
                             "content": {
                                "type":"string",
                               "description": "Full text content of the web page."
                              },
                             "displayUrl": {
                               "type": "string",
                               "description": "The display URL of the web page."
                              },
                             "datePublished": {
                               "type": "string",
                               "format": "date-time",
                               "description": "The time when the web page waspublished."
                              },
                             "siteName": {
                               "type": "string",
                                "description": "Thesource of the web page"
                              },
                              "logo":{
                               "type": "string",
                               "description": "The URL of the site's logo orfavicon."
                              }
                            }
                          }
                        }
                      }
                    }
                  }
                }
              }
            }
          },
          "400": {
            "description": "Badrequest - Invalid parameters or missing required query parameter"
          },
          "401": {
            "description": "Unauthorized- Invalid or missing access key"
          },
          "404": {
            "description": "Notfound - Invalid endpoint path"
          },
          "500": {
            "description":"Internal server error"
          }
        }
      }
    }
  }
}

# 设置变量
gateway_id =fulltextsearch_gateway["gatewayId"]
s3_uri = "s3://{bucket}/full_text_search_openapi_schema.json" #前面OpenAPI Schema的S3路径
s3_accountid = "{account id}"
api_key_provider_arn = apikey_response["credentialProviderArn"]

# Create the agentcore client
import boto3
agentcore_client =boto3.client('bedrock-agentcore-control', region_name = "us-west-2")

# Create an OpenAPI target with API Keyauthentication
fulltextsearch_target =agentcore_client.create_gateway_target(
   gatewayIdentifier=gateway_id,
   name="fulltextsearch-target",
   targetConfiguration={
       "mcp": {
           "openApiSchema": {
               "s3": {
                   "uri": s3_uri,
                   "bucketOwnerAccountId": s3_accountid
               }
            }
        }
    },
   credentialProviderConfigurations=[
        {
           "credentialProviderType": "API_KEY",
           "credentialProvider": {
               "apiKeyCredentialProvider": {
                   "providerArn": api_key_provider_arn,
                   "credentialLocation": "HEADER",
                   "credentialParameterName": "Authorization",
                   'credentialPrefix': 'Bearer'
               }
            }
        }
    ]
)

上海今天的天气情况

{
    "InvokeActionOutput": {
        "mcpInvokeActionOutput": {
            "content": [
                {
                    "textContent": {
                        "text": {
                            "statusCode": 200,
                            "body": {
                                "content": [
                                    {
                                        "type": "text",
                                        "text": "# Cloudsway Smart Search 结果\n\n搜索词: 查询中国十五五期间的重点方向和规划\n共找到 3 个结果\n\n## 1. 十五五战略规划全文纲要、重点项目解读（2026-2030）\n**链接:** https://www.sohu.com/a/919149380_121937266\n**相关性:** 0.8830528\n**摘要:** 2025年7月30日·“十五五规划”即中国未来2026-2030年的国家发展计划，是政府制定的第15个“五年规划”，也是作为我国迈向2035年基本实现现代化的重要衔接规划，其出台对于指导未来五 …\n\n## 2. “十五五”目标，最全解读！ - 知乎\n**链接:** https://zhuanlan.zhihu.com/p/1965053013371643553\n**相关性:** 0.57277185\n**摘要:** 2025年10月24日·1. 核心发展战略与目标 科技自立自强：是引领新质生产力的重中之重，是中美博弈的核心变量。“十五”期间要实现 九大未来产业 的 …\n\n## 3. 一图了解“十五五”规划12大重点方向_新浪财经_新浪网\n**链接:** https://finance.sina.com.cn/roll/2025-10-23/doc-infuwsqf2253703.shtml\n**相关性:** 0.9838752\n**摘要:** 2025年10月23日·一图了解“十五五”规划12大重点方向 2025年10月23日 19:47 东财财经头条 新浪财经APP 举报 缩小字体 放大字体 收藏 微博 微信 分享\n\n"
                                    }
                                ]
                            }
                        }
                    }
                }
            ]
        }
    },
    "InvokeActionResponseMetadata": {},
    "InvokeActionStatus": "SUCCESS",
    "RequestId": "366952c6-afdc-49d9-83a4-c02047366b38"
}