The NVIDIA AI Blueprint for RAG gives developers a foundational starting point for building scalable, customizable retrieval pipelines that deliver both high accuracy and throughput. Use this blueprint to build RAG applications that provide context-aware responses by connecting LLMs to extensive multimodal enterprise data—including text, tables, charts, and infographics from millions of PDFs. With 15x faster multimodal PDF data extraction and 50% fewer incorrect answers, enterprises can unlock actionable insights from data and drive productivity at scale.

This blueprint can be used as-is, combined with other NVIDIA Blueprints, such as the Digital Human blueprint or the AI Assistant for customer service blueprint, or integrated with an agent to support more advanced use cases. Get started with this reference architecture to ground AI-driven decisions in relevant enterprise data - wherever it resides.

Architecture Diagram

Key Features

• Multimodal PDF data extraction support with text, tables, charts, and infographics
• Hybrid search with dense and sparse search
• Opt-in image captioning with vision language models (VLMs)
• Reranking to further improve accuracy
• GPU-accelerated Index creation and search
• Multi-turn conversations
• Multi-session support
• Telemetry and observability
• Opt-in for reflection to improve accuracy
• Opt-in for guardrailing conversations
• Sample user interface
• OpenAI-compatible APIs
• Decomposable and customizable

Minimum System Requirements

Hardware Requirements The blueprint offers two primary modes of deployment. By default, it deploys the referenced NIM microservices locally. Each method lists its minimum required hardware. This will change if the deployment turns on optional configuration settings.

• Docker
  • 4xH100 or 6xA100
• Kubernetes
  • 9xH100 or 11XA100
• The blueprint provides the alternative to use NGC-hosted models, in which case one GPU will be required to host the NVIDIA cuVS-accelerated vector database.
• The blueprint can be modified to use additional NIM microservices hosted by NVIDIA.

OS Requirements

• Ubuntu 22.04 OS

Deployment Options

• Docker
• Kubernetes

Software used in this blueprint

NVIDIA Technology

• NeMo Retriever Llama 3.2 embedding NIM
• NeMo Retriever Llama 3.2 reranking NIM
• Llama 3.1 70B instruct NIM
• NeMo Retriever page elements NIM
• NeMo Retriever table structure NIM
• NeMo Retriever graphic elements NIM
• PaddleOCR NIM
• NeMo Retriever parse NIM (optional)
• Llama 3.1 NemoGuard 8B content safety NIM (optional)
• Llama 3.1 NemoGuard 8B topic control NIM (optional)
• Llama 3.2 11B vision instruct NIM (optional)
• Mixtral 8x22B instruct 0.1 (optional)

3rd Party Software

• LangChain
• Milvus database (accelerated with NVIDIA cuVS)

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility, and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure the models meet requirements for the relevant industry and use case and address unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI concerns here.

License

Use of the models in this blueprint is governed by the NVIDIA AI Foundation Models Community License.

Terms of Use

This blueprint is governed by the NVIDIA Agreements | Enterprise Software | NVIDIA Software License Agreement and the NVIDIA Agreements | Enterprise Software | Product Specific Terms for AI Product. The models are governed by the NVIDIA Agreements | Enterprise Software | NVIDIA Community Model License and the NVIDIA RAG dataset which is governed by the NVIDIA Asset License Agreement.

The following models that are built with Llama are governed by the Llama 3.2 Community License Agreement: llama-3.1-70b-instruct, nvidia/llama-3.2-nv-embedqa-1b-v2, and nvidia/llama-3.2-nv-rerankqa-1b-v2.