OpenViking launches 3D STEP content-understanding model
OpenViking launched a native 3D content-understanding model that imports and parses STEP files, generating orthogonal six-view and eight-axis side-view images, summaries, model details, and indexed PMI information for downstream agent reasoning. 掘金 · 人工智能 reports that OpenViking can support agent workflows including component retrieval, BOM preparation, and supply-change analysis through integrations such as Codex and Claude. OpenViking claims 100% information recovery, but no independent testing or reproduction was provided.
The release extends agent context databases beyond documents and media into structured engineering data, potentially making 3D models and manufacturing specifications directly retrievable in existing agent workflows.
10 月 20 日,OpenViking 发布原生支持 3D 数据导入与解析的内容理解模型。 现在你可以把零件模型、工程图纸和项目资料都交给 OpenViking,在豆包工作/Workbuddy/Codex/Claude 等 Agent 中描述你要找的结构,让 AI 帮你找候选零件、整理 BOM,核对供应变更带来的影响。
OpenViking ✖️ 3D 内容理解模型
OpenViking 是火山引擎推出的 Agent 上下文数据库,支持文档、图片、音视频等多模态数据理解。
今天迎来重磅升级,上线首个 3D 内容理解模型,支持三维 STEP 文件的导入与解析,信息还原率做到 100%。
导入一个三维 STEP 文件,解析产物会包含其正交六视图、八轴侧视图、信息摘要及模型明细,涵盖几何、PMI、装配、工艺等全部原始信息。
#OpenViking#Volcano Engine#Codex#Claude#Doubao Work#Workbuddy