Unverified50% confidenceFactExact time
pplx-embed-v2-late supports unified retrieval across text, images, and pages, sharing a single embedding space to enable cross-modal queries.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/10/2026
First Seen
Valid until: 1/8/2027
Sources
Related Entities
Related Claims
Unverifiedpplx-embed-v2-late can retrieve PDF pages without OCR by processing PDF pages directly as images and mapping them into the same embedding space as text.76% similarUnverifiedOpenCLI通过读取结构化的DOM快照获取页面内容，而非依赖截图67% similarUnverifiedThe PPTX file format is based on an XML structure, where each text box, shape, and image is an independent XML node that can be modified individually.65% similarUnverifiedRendemo records product interactions via a Chrome extension, capturing the page's actual DOM/HTML structure rather than screenshots.64% similarUnverified标注模式背后依赖视觉语言模型（VLM）的跨模态对齐能力，将用户在截图上圈选的空间区域映射回对应的HTML/CSS代码片段64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/993141API
curl https://kongchang.com/api/v1/knowledge/claims/993141MCP
get_claim(id=993141)