Core Components: - PDFStorageService with Dify/OSS adapters - LLM12FieldsService with Nougat-first + dual-model + 3-layer JSON parsing - PromptBuilder for dynamic prompt assembly - MedicalLogicValidator with 5 rules + fault tolerance - EvidenceChainValidator for citation integrity - ConflictDetectionService for dual-model comparison Prompt Engineering: - System Prompt (6601 chars, Section-Aware strategy) - User Prompt template (PICOS context injection) - JSON Schema (12 fields constraints) - Cochrane standards (not loaded in MVP) Key Innovations: - 3-layer JSON parsing (JSON.parse + json-repair + code block extraction) - Promise.allSettled for dual-model fault tolerance - safeGetFieldValue for robust field extraction - Mixed CN/EN token calculation Integration Tests: - integration-test.ts (full test) - quick-test.ts (quick test) - cached-result-test.ts (fault tolerance test) Documentation Updates: - Development record (Day 2-3 summary) - Quality assurance strategy (full-text screening) - Development plan (progress update) - Module status (v1.1 update) - Technical debt (10 new items) Test Results: - JSON parsing success rate: 100% - Medical logic validation: 5/5 passed - Dual-model parallel processing: OK - Cost per PDF: CNY 0.10 Files: 238 changed, 14383 insertions(+), 32 deletions(-) Docs: docs/03-涓氬姟妯″潡/ASL-AI鏅鸿兘鏂囩尞/05-寮€鍙戣褰?2025-11-22_Day2-Day3_LLM鏈嶅姟涓庨獙璇佺郴缁熷紑鍙?md
1.2 KiB
1.2 KiB
AIA - AI智能问答
模块代号: AIA (AI Intelligent Answer)
开发状态: ✅ 已完成
商业价值: ⭐⭐⭐⭐
独立性: ⭐⭐⭐
📋 模块概述
AI智能问答模块提供10+个专业AI智能体,覆盖科研关键节点。
核心价值: 差异化AI能力,覆盖科研全流程
🎯 核心功能
已完成功能
- ✅ 12个智能体 - YAML配置框架
- ✅ 多轮对话 - 上下文管理、历史记录
- ✅ 流式输出 - SSE打字机效果
- ✅ 模型切换 - DeepSeek、Qwen3、Qwen-Long
- ✅ @知识库问答 - RAG增强
主要智能体
- 选题评价智能体(四维度评价)
- PICO梳理智能体
- 样本量计算智能体
- 研究方案制定智能体
- 文章润色与翻译智能体
📂 文档结构
AIA-AI智能问答/
├── [AI对接] AIA快速上下文.md # ⏳ 待创建
├── 00-项目概述/
├── 01-设计文档/
└── README.md # ✅ 当前文档
🔗 依赖的通用能力
- LLM网关 - 模型调用和切换
- RAG引擎 - @知识库问答
最后更新: 2025-11-06
维护人: 技术架构师