IF Con Tokyo 2026 演讲上线:Dify 发布 tokener.ai 与知识库 2.0
The IF Con Tokyo 2026 archive is now live. We’re starting with the opening keynote by Luyu Zhang (@...
Dify 把 Tokyo 大会演讲放出来了,30 分钟讲清企业 AI 落地的堵点,还顺手发了模型聚合端点和知识库 2.0,做智能体的可以看看。
Dify 公布了 IF Con Tokyo 2026 大会归档,首支视频是创始人 Luyu Zhang 的 30 分钟主题演讲,主题为企业工作流重构,指出交接与授权是个人效率与组织效率差距的两个落点。
演讲中发布两项新品:tokener.ai 提供单一端点接入所有模型,免去切换账号、密钥与计费;
Dify Knowledge Base 2.0 从零重设计其使用最多的知识库功能,消除文档与智能体之间的转移。
官方同时提供 3 分钟的 Digest 版本供快速了解论证框架。
The IF Con Tokyo 2026 archive is now live. We’re starting with the opening keynote by Luyu Zhang (@...
The IF Con Tokyo 2026 archive is now live. We’re starting with the opening keynote by Luyu Zhang ( @goocarlos ), Founder & CEO of Dify: “Beyond AI Adoption — How to Redesign the Enterprise Workflow.” Individual productivity and organizational productivity are not the same problem. Using the history of railway track gauges as a lens, the talk examines where the gap actually forms and lands on two things: handoffs and authority. ■ Two new announcements - tokener.ai One endpoint for every model, removing the need to switch accounts, keys and billing every time you change models. - Dify Knowledge Base 2.0 The most-used feature in Dify, redesigned from zero — removing the transfer between your documents and your agent. Both are framed by the same question: which transfer does it remove? ■ Available now - Digest (3 min) — the shape of the argument - Full session (30 min) — the full case, including both announcements Sessions from our sponsors and guest speakers will follow. ▶ youtube.com/@dify_japan #IFConTokyo2026 #Dify #GenerativeAI #AIAgents📊 1 ⚡
本条情报归属 AITOP「产品」核心栏目,重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「中美大模型技术代差与商业化对照」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Dify、tokener.ai、知识库、智能体,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「Dify」(@dify_ai),经 AITOP 多维评分管线结构化提炼。