Files
AIclinicalresearch/docs/02-通用能力层
HaHafeng decff0bb1f docs(deploy): Complete full system deployment to Aliyun SAE
Summary:
- Successfully deployed complete system to Aliyun SAE (2025-12-25)
- All services running: Python microservice + Node.js backend + Frontend Nginx + CLB
- Public access available at http://8.140.53.236/

Major Achievements:
1. Python microservice deployed (v1.0, internal IP: 172.17.173.66:8000)
2. Node.js backend deployed (v1.3, internal IP: 172.17.173.73:3001)
   - Fixed 4 critical issues: bash path, config directory, pino-pretty, ES Module
3. Frontend Nginx deployed (v1.0, internal IP: 172.17.173.72:80)
4. CLB load balancer configured (public IP: 8.140.53.236)

New Documentation (9 docs):
- 11-Node.js backend SAE deployment config checklist (21 env vars)
- 12-Node.js backend SAE deployment operation manual
- 13-Node.js backend image fix record (config directory)
- 14-Node.js backend pino-pretty fix
- 15-Node.js backend deployment success summary
- 16-Frontend Nginx deployment success summary
- 17-Complete deployment practical manual 2025 edition (1800 lines)
- 18-Deployment documentation usage guide
- 19-Daily update quick operation manual (670 lines)

Key Fixes:
- Environment variable name correction: EXTRACTION_SERVICE_URL (not PYTHON_SERVICE_URL)
- Dockerfile fix: added COPY config ./config
- Logger configuration: conditional pino-pretty for dev only
- Health check fix: ES Module compatibility (require -> import)

Updated Files:
- System status document updated with full deployment info
- Deployment progress overview updated with latest IPs
- All 3 Docker services' Dockerfiles and configs refined

Verification:
- All health checks passed
- Tool C 7 features working correctly
- Literature screening module functional
- Response time < 1 second

BREAKING CHANGE: Node.js backend internal IP changed from 172.17.173.71 to 172.17.173.73

Closes #deployment-milestone
2025-12-25 21:24:37 +08:00
..

通用能力层

层级定义: 跨业务模块共享的核心技术能力
核心原则: 可复用、高内聚、独立部署


📋 能力清单

能力 说明 复用率 优先级 状态
01-LLM大模型网关 统一管理LLM调用、成本控制、模型切换 71% (5/7) P0 待实现
02-文档处理引擎 PDF/Docx/Txt提取、OCR、表格提取 86% (6/7) P0 已实现
03-RAG引擎 向量检索、语义搜索、RAG问答 43% (3/7) P1 已实现
04-数据ETL引擎 Excel JOIN、数据清洗、数据转换 29% (2/7) P2 待实现
05-医学NLP引擎 医学实体识别、术语标准化 14% (1/7) P2 待实现

🎯 设计原则

1. 可复用性

  • 多个业务模块共享
  • 避免重复开发

2. 独立部署

  • 可以独立为微服务
  • 支持独立扩展

3. 高内聚

  • 每个能力职责单一
  • 接口清晰

4. 领域知识

  • 包含业务领域知识
  • 不是纯技术组件

📊 复用率分析

LLM网关 - 71%复用率(最高优先级)

  • AIAAI智能问答
  • ASLAI智能文献
  • PKB个人知识库
  • DC数据清洗
  • RVW稿件审查

文档处理引擎 - 86%复用率(已实现)

  • ASL、PKB、DC、SSA、ST、RVW

RAG引擎 - 43%复用率(已实现)

  • AIA、ASL、PKB

📚 快速导航

快速上下文

  • [AI对接] 通用能力快速上下文.md - 2-3分钟了解通用能力层

核心能力

  1. LLM大模型网关 - P0优先级
  2. 文档处理引擎 - 已实现
  3. RAG引擎 - 已实现
  4. 数据ETL引擎
  5. 医学NLP引擎

🔗 相关文档


最后更新: 2025-11-06
维护人: 技术架构师