学习
Datawhale 出品的中文 LLM 应用开发教程:从 API 调用到 Prompt 工程、RAG 知识库、Vector 检索、LangChain 应用与部署,全程围绕一个「知识库助手」项目实战。Datawhale's Chinese LLM application course: from API calls to prompt engineering, RAG, vector search and LangChain, built around one knowledge-base assistant project.
RAG
以数据为中心的 LLM 框架:RAG 索引、检索、文档解析能力业界最全,现已扩展出 Agent 工作流(Workflows),是知识库类应用的首选底座。The data-centric LLM framework: the richest RAG indexing/retrieval toolchain, now extended with agent workflows.
低代码
开源 LLM 应用开发平台:可视化编排工作流、内置 RAG 知识库、Agent 与模型管理,国产开源明星项目,企业落地案例多。Open-source LLM app platform with visual workflow, built-in RAG knowledge base, agents and model management.
RAG
国产开源 RAG 引擎:以深度文档解析见长(表格、扫描件、复杂版式),提供可视化知识库与可溯源引用,中英文场景表现好。Open-source RAG engine with deep document parsing (tables, scans, complex layouts) and traceable citations.
低代码
拖拽式 LLM 应用构建器:节点画布编排 Agent、RAG 与 API,可自托管、可导出为 API,适合快速交付内部 AI 工具。Drag-and-drop LLM app builder: node canvas for agents, RAG and APIs, self-hostable and exportable as an API.
RAG
微软的图谱增强 RAG 方案:先抽取实体关系构建知识图谱,再结合社区摘要回答全局性问题,适合大文档集的「总结型」问答。Microsoft's graph-based RAG: build a knowledge graph then answer global, summarization-style questions over large corpora.