快讯
Perplexity 开源 pplx-embed-v2-late 多向量嵌入模型，支持文本与图像共享嵌入空间检索
Aravind Srinivas 宣布开源 pplx-embed-v2-late，一对用于文本和图像的多向量（late-interaction）嵌入模型，提供 9B 和 0.6B 两种规模，并在同一共享嵌入空间中工作。作者称，可用 9B 模型索引多模态数据、再用 0.6B 模型在端侧查询，且无需 OCR 即可搜索 PDF 页面；他表示该模型在 MADQA 上得分 92.4%，在 BrowseComp+ 上得分 64%。权重已在 Hugging Face 上线。
查看原文
RT Aravind Srinivas We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device with 0.6B. This also enables you to search over PDF pages with no OCR. And scores 92.4% on MADQA, 64% on BrowseComp+. Weights available on @huggingface now. Perplexity: We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying. Both models achieve frontier performance and are publicly available on Hugging Face. https://www.perplexity.ai/hub/blog/multimodal-embeddings-beyond-a-single-vector
前后快讯
上一篇ElevenLabs 模型登陆 OpenRouter：9 款 TTS、2 款 STT，限时五折
下一篇Cloudflare AI Gateway 统一凭据拒绝响应：全部提供商返回 HTTP 401 与错误码 2009