与「RAG」相关的搜索结果

🚀发现一个很适合搭配 Pi、Claude Code、Cursor 使用的开源知识库项目：pi-llm-wiki。 它采用 Karpathy 提出的 LLM Wiki 思路，把 URL、PDF、Markdown、JSON、XML 等原始资料，转化为可持续维护、相互链接的本地 Wiki，而不是每次提问都重新进行一次性 RAG。 核心亮点： ▪️ 自动采集、整理和关联不同来源 ▪️ 区分原始资料、来源摘要、概念页和综合分析 ▪️ 兼容 Obsidian，可直接查看和编辑 ▪️ 原生支持 OKF v0.2，知识库不被特定应用锁定 ▪️ 同时搜索个人知识库与项目知识库 ▪️ 自动检查断链、孤立页面、内容冲突和知识缺口 ▪️ 通过 MCP 接入 Claude Code、Cursor、Windsurf ▪️ 可选记录 Agent 的任务轨迹，并沉淀为可复用 Skills 这不是简单的“让 AI 搜索笔记”，而是让 AI 帮你长期维护一套会不断积累、更新和复利的知识系统。

给中小企业搭内部AI知识库，一单八千到三万 公司资料散在微信群、飞书文档和一堆 PDF 里，新人问个流程要问三个人。你要做的是把资料收上来，用 Dify 或 FastGPT 搭一个 RAG 知识库，接上 DeepSeek 的 API，再挂到企业微信或飞书机器人上，员工在聊天框直接问。 技术门槛没想象中高，Dify 有云端版，会配置就能交付。按资料量和部门数报价，基础版八千到一万五，含流程梳理和权限分级的三万起，后续维护再收年费。 最耗时的不是搭系统而是清洗资料，报价前一定要先看文档数量和格式。涉及财务和人事的库要单独做权限，出一次泄露就没有下次合作。

RAG system that skips HTML parsing entirely! PixelRAG is an open-source visual RAG framework that renders documents as screenshots instead of parsing them into text. Most RAG pipelines start by converting HTML to text. Tables flatten into unstructured rows. Charts disappear. Layout context is gone before the LLM ever sees it. The paper measured this directly: HTML-to-text conversion accounts for 36.6% of retrieval failures on SimpleQA. PixelRAG skips that step entirely. It renders pages as screenshot tiles using Playwright, embeds those tiles with a fine-tuned Qwen3-VL-Embedding model, builds a FAISS index, and passes retrieved images directly to a VLM reader. No text abstraction in between. Benchmarked across six datasets against the strongest text-based baselines: - SimpleQA: 78.8% vs 71.6% (+7.1 points) - NQ-Tables: 48.8% vs 42.5% (+6.3 points) - EVQA: +15.5 points - LiveVQA: +11.3 points One honest caveat from the authors: this requires Qwen3-VL-4B class models or larger to see the benefit. Smaller models trail text retrieval. The authors also recommend using PixelRAG as an enhancement layer alongside existing text systems rather than a full replacement. Ships with a pre-built Wikipedia index covering 8.28M articles across 28.1M screenshot tiles. A Claude Code plugin lets Claude take screenshots of any URL and reason over the visual content directly. Key capabilities: • Renders web pages, PDFs, and images as screenshot tiles via Playwright • Fine-tuned Qwen3-VL-Embedding model for visual retrieval • FAISS index for fast vector search • Pre-built Wikipedia index: 8.28M articles, 28.1M tiles • 3x token cost reduction via image compression • Claude Code plugin for direct URL screenshot and visual reasoning • LoRA fine-tuning support via pixelrag-train 100% open source. I've shared the link in the replies!

"Voice gets interesting the moment developers find interaction patterns that only voice makes possible." - @scottcjohnston We built a @DeepLearningAI course on exactly that. Voice for AI Agents and Applications, with @_ashwyn , @AndrewYNg , and @scottcjohnston. Most voice infrastructure out there was built for one job: replace humans in contact centers. Answer the phone, follow the script, close the ticket. Building voice into a real product is a different problem. This free short course is about that, giving your apps and agents an actual voice. You'll walk away having built: 🎮 a voice-interactive game where voice and mouse clicks run over one channel 🤖 a chat agent that gains a voice in ~10 lines, no touching your prompts, RAG, or tools 📞 an agent that makes real outbound phone calls and streams the transcript back live Enroll for free: We'd love to see what you build. Let's go 🚀

UC Berkeley 搞出来的新工具直接改了我对 Web RAG 的认知 核心就一句话：别把网页转 HTML 了，直接截图喂给 AI 表格、图表、公式这些东西在 HTML 里全丢了，但截图里完整保留。RAG 精度能涨 18% 多，有些场景改进更明显 用法简单到不像话——装好包，URL 一丢就行，自动把网页变成截图 接入 Claude 的话，它就真的是在'看'网页而不是'读'网页。Wikipedia 800 多万页的索引现在免费就能用 最绝的是这套索引是像素级存储，模型更新了也不用重新构建 从'让 AI 读网页'进化到'让 AI 看网页'，差别还是挺大的

搞 AI 向量数据库和 RAG 的兄弟们可以少走半年弯路了！ GitHub 上爆火的这个项目，直接把“实时数据 + 向量检索 + LLM 管道”给合体了，写 30 行 Python 代码就能秒搭一个企业级 RAG 系统，完全不用去搞各种复杂的向量数据库配置！ 这是 Pathway 团队开源的 llm-app（GitHub 斩获 5.9 万+ Stars，MIT 协议开源）。它最离谱的地方在于“全自动实时同步”——你的 Google Drive、SharePoint、S3 或数据库里文件一改，AI 知识库瞬间自动刷新，根本不需要手动重新跑嵌入或者手动触发同步！ 🎯 核心杀手锏： 零向量库门槛：内置内存向量索引，不依赖 Pinecone 等第三方服务，几行代码跑通。 实时热更新数据：完美对接 Kafka、PostgreSQL、SharePoint，源头数据变了 AI 马上知道。 开箱即用云模板：预置大量 RAG 与企业搜索模板，直接打成 Docker 镜像就能上线。 商业无忧：采用 MIT 宽松协议，不管是自己玩还是做公司商业项目都能随意搞。 还在等啥，自己去看。 🔗 传送门：

"PUT THE GUN DOWN!" Video captures the tense moment officers confront an armed road rage suspect after he allegedly points a handgun at another driver at a busy Des Moines intersection. Police intervene before anyone is hurt, bringing the dangerous encounter to an end.

WATCH: Security camera footage captures a wildfire racing toward a home near Madrid. Raging wildfires have forced more than 300,000 people to flee their homes across Spain and France as firefighters battle the fast-moving blazes.

I listened to 85 minutes of The Economist’s interview of Elon so you don’t have to. Besides, it’s behind a paywall. Elon’s predictions: In five years, AI compute will exceed the sum of all human intelligence. In ten years, we will have reached the age of abundance. Money won’t matter. Everyone will have what they need or want (at least in economies that embrace AI). Ms. Beddoes tried to pin Elon down on how the economy will transform that way, but he wouldn’t get into specifics beyond noting that widespread AI robotics is a deflationary force. This means governments won’t need to raise taxes for universal basic income schemes, or, as Elon likes to call it, universal high income, since they will simply be able to print money to ward off deflation caused by the robot economy. She noted that Elon appears to have a more sanguine view of AI lately. He replied that he’s concluded superintelligent AI is now inevitable, so there’s no point trying to stop or slow it down, it can’t be done. We might as well enjoy the ride. The interviewer also noted that Mars no longer seems to be Elon’s overall ambition. He answered that his real mission was always to propagate and preserve human consciousness into the far future. Mars was just a vehicle for that. But now AI is a very important part of that goal. AI will necessarily be part of any future plan. And then came the oh-so-typical, increasingly tiresome part of most long journalist interviews: the interviewer constructs a straw-man version of Elon and argues against it. Elon carefully explained that he isn’t a raging far-right extremist, racist Nazi who kills puppies … and the journalist still didn't believe it. It is so effing tiresome. The lack of self-awareness on the part of journalists is off the charts. She complained about Elon’s supposed misperception of how dangerous London is, while remaining oblivious to the role she plays in creating the giant misperception of Elon as a person in her own writing. Elon defended his political views, saying he is for secure borders, locking up criminals, and balanced government spending, something even she had to admit didn’t sound crazy. And… that’s about it for an 85-minute interview. I couldn’t help but think that the next long-form interview Elon does should be conducted by an AI.