NVIDIA Blueprint: PDF Ingestion

The multimodal PDF data extraction workflow uses NVIDIA NIM microservices to unlock highly accurate insights from massive volumes of enterprise data.

With this enterprise-scale multimodal document retrieval workflow, developers can create digital humans, AI agents, or customer service chatbots that can quickly become experts on any area captured within their corpus of data.

The multimodal retrieval workflow is designed to enhance generative AI applications with RAG capabilities which can be connected to proprietary data–wherever it resides. Use this workflow to supercharge your RAG applications with unprecedented intelligence.

• Understand the capabilities of the NVIDIA Blueprint for Multimodal PDF Data Extraction
• Leverage the NV-Ingest Python SDK to process documents into a RAG pipeline
• Leverage the NV-Ingest CLI to process documents into a Rag pipeline
• Understand how the Blueprint loads data into the S3 bucket and Vector Database

What you will interact with:

• Jupyter Notebook
• NVIDIA Blueprint: Multimodal PDF Data Extraction
• Milvus Database
• MinIO Object Storage

Under the covers, you will be running on:

• Cisco FlashStack for AI and Pure Storage FlashBlade
• Red Hat OpenShift
• Run:ai