abcced35b8
- Increase RAG retrieval from 5 to 50 docs with relevance threshold (0.15) - LLM inline citations with [来源N] format and reference list - Clickable citation links scroll to source cards with highlight animation - Source previews with full chunk text and answer-matched highlighting - Message-scoped source IDs to fix cross-round citation targeting - Admin panel pages (knowledge, users, forum, course, settings) - Add rehype-raw dependency for HTML-in-markdown rendering Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
国土空间规划课程智能体后端服务
基于FastAPI和LangGraph的智能问答系统后端服务。
技术栈
- 框架: FastAPI + Uvicorn
- AI框架: LangChain + LangGraph
- 大模型: 硅基流动API (Qwen3-30B)
- 向量数据库: Chroma
- 数据库: PostgreSQL
快速开始
使用Docker(推荐)
docker-compose up -d
本地开发
uv sync
uv run main.py
API文档
启动服务后访问:http://localhost:8000/docs