LangGraph full-stack project adds RAG and multimodal search
AI summary
The Juejin AI report describes the third installment of a LangGraph full-stack project, adding a lightweight local RAG knowledge base built with ChromaDB and an MCP project that generates webpages dynamically. It also consolidates online search, webpage generation, and knowledge-base retrieval in a search_node, requires human approval before web searches, and uses a multimodal model to recognize uploaded images and find similar images.
In-depth insight
This update documents a concrete LangGraph application combining local RAG, MCP tools, human-in-the-loop review, and multimodal image search within one project architecture.
- 上传图片并识别
- 搜索前需要人工审核 (HITL)
- 本地知识库 使用 chromadb 实现轻量级RAG知识库
- 动态生成 网页的 mcp 项目接入
- 搜索,生成网页,知识库检索 都集中在 search_node 节点
本地知识库存的事本项目架构文档
联网搜索前用户确认
多模态模型识别图片并搜索类似图片