用于大规模搜索、抓取与交互网页的 API。🔥The context API to search, scrape, and interact with the web at scale. 🔥
仓库/Skill 库
14 个 · RAG 检索增强 · 快速增长
RAGFlow 是一款领先的开源 RAG 引擎,融合前沿 RAG 与 Agent 能力,为 LLM 构建更优的上下文层。RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Context7 Platform——为 LLM 与 AI 代码编辑器提供最新的代码文档Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
网页解析的终结,可扩展像素原生搜索的开端。链接:https://pixelrag.ai/The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
漂亮的、AI 原生的 markdown IDE 与 LLM 知识库。Beautiful, AI-native markdown IDE and LLM wiki
按性价比排序的循证生活指南:长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。
grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる
乔木剪藏:剪藏网页到 Obsidian,阅读、编辑,并向 AI 提问 | Clip the web to Obsidian, then read, edit and chat with AI about it.
品牌面向 AI 定义自我的开放社区。An open community where brands define themselves for AI
FactCircuit:具备不可篡改来源、分阶段检查、有界检索与可复现评估的可审计主张-证据验证回路。FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
在单台 DGX Spark 上运行 Qwen3.8-Flash-Next (180B),方法是将 51B 的 n-gram embedding 表存放在 NVMe 上Run Qwen3.8-Flash-Next (180B) on a single DGX Spark by keeping its 51B n-gram embedding table on NVMe