Video Player is loading.
Current Time 0:00
Duration 0:00
Loaded: 0%
Stream Type LIVE
Remaining Time 0:00
 
1x
    • Chapters
    • descriptions off, selected
    • default, selected

    PDFSpeak: Unlocking Multimodal PDF Intelligence Through Speech

    , Solutions Architect, Generative AI, NVIDIA
    , Sr. Solution Architect , NVIDIA
    , AI Solutions Architect, NVIDIA
    , AI Solutions Architect, NVIDIA
    Gain next-level insights from PDF documents just by speaking to your data. This hands-on session shows participants how to build and run PDFSpeak, an innovative approach to interacting with complex PDF documents using NVIDIA's cutting-edge AI technologies through speech, vision, and text.
    Prerequisite(s):

    GitHub, Docker, Bash, familiarity with Python.
    活动: GTC 25
    日期: March 2025
    行业: 所有行业
    级别: 通用
    话题: Generative AI - Retrieval-Augmented Generation (RAG)
    NVIDIA 技术: Riva,NVIDIA NIM,NVIDIA AI Enterprise
    语言: 英语
    所在地: