今天继续这个话题，事实上这个系列不太好写，写深入了容易将现在正在做的项目技术路径泄露，写浅了又有点隔靴搔痒，但其实现在很多公司都有类似 的问题： 1. AI聊得不像人，最常见案例就是生硬，就算上RAG或知识库也不好使； 2. AI准确率不高，最常见就是AI能覆盖80%的场景，但业务的及格线是95%； 这些问题都与我们探讨的问题相关，其中准确率不高这个是专家系统需要解决的任务；而聊得不像人这就比较麻烦了，策略层面涉及了Cot，技术层面暂 时多与RAG相关。 只不过就RAG这个技术，要用好的公司也不多，为避免泄露当前项目技术机密，今天我就借Douwe Kiela（RAG 技术的最初开创者之一）提出的10个宝贵 经验，来聊聊如何做好RAG这件事。 上下文悖论 The Context Paradox，莫拉维克悖论指出：对计算机而言，执行人类觉得困难的任务（如下棋）比执行人类觉得容易的任务（如行走、感知）更容易。 其实这一观点与RL 之父 Rich Sutton某一观点十分类似：依靠纯粹算力的通用方法，最终总能以压倒性优势胜出。 他特别提出：AlphaGo/GPT-3的成功并非源于复杂规则，而是大规模算力支撑的简单算法 ...

（原标题：估值72亿美元，红杉加持的这家AI搜索创企什么来头？） AI初创公司Glean近日宣布，其已经完成1.5亿美元的融资，估值达72亿美元。这是这家美国企业级AI搜 索初创公司在不到两年内的第三次融资。相比去年9月份的融资估值46亿美元，本次融资的估值大幅提 升。 Glean完成新一轮融资 据了解，本轮融资由威灵顿资产（Wellington Management）领投，新增新投资者包括Khosla Ventures、 Bicycle Capital、Geodesic Capital和Archerman Capital。而老股东红杉资本（Sequoia Capital）、Coatue、 DST Global和光速资本（Lightspeed Venture Partners）也再次参与，表明他们对Glean发展势头的持续信 心。 据了解，公司自2019年成立后完成六轮融资。去年9月，公司完成E轮融资，融资金额2.6亿美元，估值 46亿美元。 Glean表示，这笔资金将用于加速产品开发、发展合作伙伴生态系统以及国际扩张。公司首席执行官 Arvind Jain将此次融资定位为战略性举措，而非短期运营所必需。他表 ...

Core Viewpoint - The article provides a comprehensive comparison of five mainstream LLM application platforms: Dify, Coze, n8n, FastGPT, and RAGFlow, emphasizing the importance of selecting the right platform based on individual needs and use cases [1][2]. Group 1: Overview of LLM Platforms - LLM application platforms significantly lower the development threshold for AI applications, accelerating the transition from concept to product [2]. - These platforms allow users to focus on business logic and user experience innovation rather than repetitive underlying technology construction [3]. Group 2: Platform Characteristics - **n8n**: Known for its powerful general workflow automation capabilities, it allows users to embed LLM nodes into complex automation processes [4]. - **Coze**: Launched by ByteDance, it emphasizes low-code/no-code AI agent development, enabling rapid construction and deployment of conversational AI applications [5]. - **FastGPT**: An open-source AI agent construction platform focused on knowledge base Q&A systems, offering data processing, model invocation, and visual workflow orchestration capabilities [6]. - **Dify**: An open-source LLM application development platform that integrates BaaS and LLMOps concepts, providing a one-stop solution for rapid AI application development and operation [7]. - **RAGFlow**: An open-source RAG engine focused on deep document understanding, specializing in knowledge extraction and high-quality Q&A from complex formatted documents [8][40]. Group 3: Detailed Platform Analysis - **Dify**: Described as a "Swiss Army Knife" of LLM platforms, it offers a comprehensive set of features including RAG pipelines, AI workflows, monitoring tools, and model management [8][10][12]. - **Coze**: Positioned as the "LEGO" of LLM platforms, it allows users to easily create and publish AI agents with a wide range of built-in tools and plugins [21][25]. - **FastGPT**: Recognized for its ability to quickly build high-quality knowledge bases, it supports various document formats and provides a user-friendly interface for creating AI Q&A assistants [33][35]. - **RAGFlow**: Distinguished by its deep document understanding capabilities, it supports extensive data preprocessing and knowledge graph functionalities [40][42]. - **n8n**: A low-code workflow automation tool that connects various applications and services, enhancing business process automation [46][49]. Group 4: User Suitability and Recommendations - For beginners in AI application development, Coze is recommended as the easiest platform to start with [61]. - For businesses requiring automation across multiple systems, n8n's robust workflow capabilities can save significant time [62]. - For building internal knowledge bases or Q&A systems, FastGPT and RAGFlow are suitable options, with FastGPT being lighter and RAGFlow offering higher performance [63]. - For teams with long-term plans to develop scalable enterprise-level AI applications, Dify's comprehensive ecosystem is advantageous [63]. Group 5: Key Considerations for Platform Selection - Budget considerations include the costs of self-hosting open-source platforms versus subscription fees for cloud services [68]. - Technical capabilities of the team should influence the choice of platform, with no-code options like Coze being suitable for those with limited technical skills [68]. - Deployment preferences, such as the need for local data privacy, should also be evaluated [69]. - Core functionality requirements must be clearly defined to select the platform that best meets specific needs [70]. - The sustainability of the platform, including update frequency and community support, is crucial for long-term viability [71]. - Data security and compliance are particularly important for enterprise users, with self-hosted solutions offering greater control over data [72].

在众多应用场景中，因病理图像具有非常大的多样性，病理大模型也被认为是医疗模型"皇冠上的明 珠"。为破解病理诊断准确性与效率难题，透彻未来研发了全球首个临床应用级病理大模型产品——透 彻洞察，基于亿级参数量和海量高精度病理数据训练，为病理医生提供精准稳健、全面快速的病理临床 诊断辅助。 2025年以来，Deepseek通过开放生态加速了算法研发与临床场景的深度融合。医疗大模型摒弃了"技术 至上"的思维，逐渐进入实用主义阶段。作为AI应用最为深入的领域之一，医学影像在大模型时代迎来 了更快速的发展。 如何增强AI模型泛化能力？大模型幻觉问题如何解决？大模型多模态数据整合的难点及解决方案有哪 些？动脉网与数坤科技首席技术官郑超、透彻未来联创兼首席技术官王书浩这两位深耕医疗AI多年的 专家们聊了聊，供行业参考。 本文主要观点如下： 01 大模型已深入医生全工作流程 医学影像人工智能模型在参数规模未达当前水平时便展现出了广阔的应用前景，现已在影像科医生的工 作全流程中实现了常态化应用。而在辅助诊断专用模型之后，数坤科技在4月发布的"数坤坤多模态医疗 健康大模型"，便实现了让AI从辅助工具进化为诊疗生态的核心驱动力。 数 ...