Files
course-agent-od/backend
pengxiao abcced35b8 feat: RAG inline citations, source highlighting, and admin panel
- 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>
2026-05-27 20:51:28 +08:00
..

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