1. [Topics](https://developer.nvidia.com/topics/)
2. [AI](https://developer.nvidia.com/topics/ai/)
3. 
Building an Agent Knowledge Foundation

# Building an Agent Knowledge Foundation

The NVIDIA Agent Knowledge Foundation provides NVIDIA open models and accelerated NVIDIA CUDA-X™ libraries that help agents retrieve relevant context, generate grounded answers, analyze and predict outcomes, and optimize actions.

Find tutorials, samples, videos, and more

[Explore Resources](#learning-library)

Key Topics:

- 
Artificial Intelligence  

- 
Data Indexing / Ingestion
- 
Querying Pipeline

- 
Large Language Models
- 
Generative AI  

## Open Models and Libraries

Choose the components required for your workflow. Each works with existing data platforms, ontologies, vector databases, and agent frameworks; they do not require adopting a new end-to-end platform.

## Reliable Agents: More Accurate, Grounded Answers

### NVIDIA Nemotron Retriever

Open, leaderboard-winning models that improve agent context and lower agentic retrieval by 40%. Nemotron Parse processes multimodal documents up to 3.5x faster; Nemotron Embed produces 24% fewer incorrect answers; Nemotron Rerank improves retrieval accuracy by approximately 5%. 

[Access Nemotron Models](https://developer.nvidia.com/nemo-retriever/)

### NVIDIA Kumo

Open, pretrained foundation models for making predictions with leading accuracy directly from relational, tabular, and time-series data. Kumo gives agents predictive context from structured data, enabling them to forecast outcomes, rank opportunities, recommend actions, and assess risk. 

[Access Kumo Models](https://developer.nvidia.com/nemo-agent-toolkit)

### NVIDIA Auto Ontology

Generates a starting ontology from enterprise data and documentation that business experts can test, refine, and certify. It complements existing ontology platforms and reduced ontology creation time by 90% in NVIDIA testing.

[Get Started With Auto Ontology](https://github.com/NVIDIA/auto-ontology)

## More Performant Agents: Faster Access to Knowledge and Insights

### NVIDIA cuDF

Accelerates the loading, joining, filtering, and transformation of structured data used by agents through familiar tools such as pandas, Polars, Spark, and DuckDB—by up to 5x on supported workloads.

[Get Started With cuDF](/topics/ai/data-science/cuda-x-data-science-libraries/cudf)

### NVIDIA cuML

Accelerates familiar classification, regression, clustering, and anomaly-detection algorithms for custom machine-learning pipelines—by up to 50x on supported workloads.

[Get Started With cuML](/topics/ai/data-science/cuda-x-data-science-libraries/cuml)

### NVIDIA cuOpt

Turns predictions, objectives and business constraints into optimized routes, schedules, and resource allocations—up to 10× faster on supported optimization workloads.

[Get Started With cuOpt](https://www.nvidia.com/en-us/ai-data-science/products/cuopt/)

### NVIDIA cuVS

Accelerates the vector indexing and similarity search used to retrieve context for agents, with integrations for FAISS, Milvus, and OpenSearch—by up to 18x on supported workloads.

[Get Started With cuVS](/cuvs/)

### NVIDIA cuGraph

Accelerates analysis of relationships across customers, products, transactions, and other connected enterprise data, giving agents additional context for analysis and reasoning.

[Get Started With cuGraph](https://docs.rapids.ai/api/cugraph/stable/)

* * *

[![NVIDIA Agent Knowledge Foundation architecture diagram showing Agent Harness stages: Search (cuVS), Analyze (cuDF, cuGraph), Predict (Kumo, cuML), and Prescribe (cuOpt), with Nemotron Retriever and Auto-Ontology for context grounding across unstructured, semi-structured, and structured data.](https://developer.download.nvidia.com/images/agent-knowledge-foundation/From-Company-Data-to-Company-Intelligence.png "NVIDIA Agent Knowledge Foundation architecture diagram showing Agent Harness stages: Search (cuVS), Analyze (cuDF, cuGraph), Predict (Kumo, cuML), and Prescribe (cuOpt), with Nemotron Retriever and Auto-Ontology for context grounding across unstructured, semi-structured, and structured data.")](https://developer.download.nvidia.com/images/agent-knowledge-foundation/From-Company-Data-to-Company-Intelligence.png)

Click to Enlarge

## From Company Data to Company Intelligence:

1. 

**Prepare** : Use Nemotron Parse to preserve document content and structure, and cuDF to prepare structured data.

2. 

**Retrievel** : Use Nemotron Embed and cuVS to find relevant information, then Nemotron Rerank to prioritize the best evidence..

3. 

**Understanding** : Use Auto-Ontology to generate a starting ontology that business experts can test, refine, and certify.

4. 

**Predict** : Use cuGraph to analyze connected data, cuML for custom machine-learning pipelines, and Kumo for pretrained prediction over structured data.

5. 

**Optimize** : Use cuOpt to turn predictions, objectives, and constraints into optimized routes, schedules, and allocations.

* * *

## NVIDIA Agent Knowledge Foundation Use Case Examples

These technologies provide individual value and can be adopted independently or used together for higher-performing enterprise agents with reliable answers, predictions, and optimized decisions at scale.

### Supply Chain  

- 

Tools: cuOpt, cuVS, Nemotron

- 

Blog: [Building an Analysis AI Agent for Industrial Alarm Management with NVIDIA Nemotron](https://developer.nvidia.com/blog/building-an-analysis-ai-agent-for-industrial-alarm-management-with-nvidia-nemotron)

- 

Blog: [Multi-Agent Warehouse AI Command Layer Enables Operational Excellence and Supply Chain Intelligence](https://developer.nvidia.com/blog/multi-agent-warehouse-ai-command-layer-enables-operational-excellence-and-supply-chain-intelligence/)

- 

Developer Example:

### Algorithmic Trading

- 

Tools: cuOpt, cuML, Nemotron

- 

Blog: [Accelerating Real-Time Financial Decisions with Quantitative Portfolio Optimization](https://resources.nvidia.com/en-us-financial-services-industry/accelerating-real-time)

- 

Developer Example: [Portfolio Optimization](https://build.nvidia.com/nvidia/quantitative-portfolio-optimization)

- 

Developer Example: [AI Model Distillation for Financial Data](https://build.nvidia.com/nvidia/ai-model-distillation-for-financial-data)

### Machine Learning Pipelines

- 

Tools: cuML, Nemotron

- 

Blog: [Building an Interactive AI Agent for Lightning-Fast Machine Learning Tasks](https://developer.nvidia.com/blog/building-an-interactive-ai-agent-for-lightning-fast-machine-learning-tasks/)

- 

Notebook: [Data Science ML Agent](https://github.com/NVIDIA-NeMo/Nemotron/tree/main/use-case-examples/Data%20Science%20ML%20Agent)

## Building an Agent Knowledge Foundation Learning Resources



The rows below are the raw result records for this component — one row per record. Column names are the source index fields; the full data is also downloadable in the links that follow.

| links | title | excerpt | featured | products | sort_key | created_at | content_type | learning_levels |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| {"url" => "https://developer.nvidia.com/blog/build-an-enterprise-scale-multimodal-document-retrieval-pipeline-with-nvidia-nim-agent-blueprint/", "text" => "Learn more"} | Build an Enterprise-Scale Multimodal PDF Data Extraction Pipeline with an NVIDIA AI Blueprint | Trillions of PDF files are generated every year, each file likely consisting of multiple pages filled with various content types, including text, images, charts… | false | NeMo, NeMo Retriever, NIM | 2\|build an enterprise-scale multimodal pdf data extraction pipeline with an nvidia ai blueprint | 1724832000 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/accelerating-oracle-database-gen-ai-workloads-with-nvidia-nim-and-nvidia-cuvs/", "text" => "Learn more"} | Accelerating Oracle Database Generative AI Workloads with NVIDIA NIM and NVIDIA cuVS | The vast majority of the world’s data remains untapped, and enterprises are looking to generate value from this data by creating the next wave of generative AI… | false | CUDA, cuVS, Fleet Command, NeMo Retriever, NIM | 2\|accelerating oracle database generative ai workloads with nvidia nim and nvidia cuvs | 1726574656 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/how-to-take-a-rag-application-from-pilot-to-production-in-four-steps/", "text" => "Learn more"} | How to Take a RAG Application from Pilot to Production in Four Steps | Generative AI has the potential to transform every industry. Human workers are already using large language models (LLMs) to explain, reason about… | false | AI Enterprise, Metropolis, Morpheus, NeMo, NeMo Microservices, NeMo Retriever, NIM, RAPIDS, Riva | 2\|how to take a rag application from pilot to production in four steps | 1710774000 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/optimizing-data-center-performance-with-ai-agents-and-the-ooda-loop-strategy/", "text" => "Learn more"} | Optimizing Data Center Performance with AI Agents and the OODA Loop Strategy | For any data center, operating large, complex GPU clusters is not for the faint of heart! There is a tremendous amount of complexity. Cooling, power, networking… | false | NeMo Retriever, NIM | 2\|optimizing data center performance with ai agents and the ooda loop strategy | 1726558200 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/building-an-ai-agent-for-supply-chain-optimization-with-nvidia-nim-and-cuopt/", "text" => "Learn more"} | Building an AI Agent for Supply Chain Optimization with NVIDIA NIM and cuOpt | Enterprises face significant challenges in making supply chain decisions that maximize profits while adapting quickly to dynamic changes. | false | cuOpt, NeMo Retriever, NIM | 2\|building an ai agent for supply chain optimization with nvidia nim and cuopt | 1721137904 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/bringing-confidentiality-to-vector-search-with-cyborg-and-nvidia-cuvs/", "text" => "Learn more"} | Bringing Confidentiality to Vector Search with Cyborg and NVIDIA cuVS | In the era of generative AI, vector databases have become indispensable for storing and querying high-dimensional data efficiently. However, like all databases… | false | cuVS, Hopper, LaunchPad, RAPIDS | 2\|bringing confidentiality to vector search with cyborg and nvidia cuvs | 1723712400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/accelerating-vector-search-nvidia-cuvs-ivf-pq-performance-tuning-part-2/", "text" => "Learn more"} | Accelerating Vector Search: NVIDIA cuVS IVF-PQ Part 2, Performance Tuning | In the first part of the series, we presented an overview of the IVF-PQ algorithm and explained how it builds on top of the IVF-Flat algorithm… | false | cuVS, RAPIDS | 2\|accelerating vector search: nvidia cuvs ivf-pq part 2, performance tuning | 1721297403 | Blog | Advanced |
| {"url" => "https://developer.nvidia.com/blog/building-ai-agents-with-nvidia-nim-microservices-and-langchain/", "text" => "Learn more"} | Building AI Agents with NVIDIA NIM Microservices and LangChain | NVIDIA NIM, part of NVIDIA AI Enterprise, now supports tool-calling for models like Llama 3.1. It also integrates with LangChain to provide you with a… | false | NeMo, NeMo Retriever, NIM | 2\|building ai agents with nvidia nim microservices and langchain | 1723021200 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/accelerating-vector-search-nvidia-cuvs-ivf-pq-deep-dive-part-1/", "text" => "Learn more"} | Accelerating Vector Search: NVIDIA cuVS IVF-PQ Part 1, Deep Dive | In this post, we continue the series on accelerating vector search using NVIDIA cuVS. Our previous post in the series introduced IVF-Flat, a fast algorithm for… | false | cuVS, RAPIDS | 2\|accelerating vector search: nvidia cuvs ivf-pq part 1, deep dive | 1721297385 | Blog | Advanced |
| {"url" => "https://developer.nvidia.com/blog/enhancing-rag-applications-with-nvidia-nim/", "text" => "Learn more"} | Enhancing RAG Applications with NVIDIA NIM | The advent of large language models (LLMs) has significantly benefited the AI industry, offering versatile tools capable of generating human-like text and… | false | NeMo Retriever, NIM | 2\|enhancing rag applications with nvidia nim | 1724749200 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/enhancing-rag-pipelines-with-re-ranking/", "text" => "Learn more"} | Enhancing RAG Pipelines with Re-Ranking | In the rapidly evolving landscape of AI-driven applications, re-ranking has emerged as a pivotal technique to enhance the precision and relevance of enterprise… | false | NeMo, NeMo Retriever, NIM | 2\|enhancing rag pipelines with re-ranking | 1722330000 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/transforming-telco-network-operations-centers-with-nvidia-nemo-retriever-and-nvidia-nim/", "text" => "Learn more"} | Transforming Telco Network Operations Centers with NVIDIA NeMo Retriever and NVIDIA NIM | Telecom companies are challenged with consistently meeting service level agreements (SLAs) for end customers that ensure network quality of service. | false | NeMo, NeMo Guardrails, NeMo Retriever, NIM | 2\|transforming telco network operations centers with nvidia nemo retriever and nvidia nim | 1721714400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/expanding-ai-agent-interface-options-with-2d-and-3d-digital-human-avatars/", "text" => "Learn more"} | Expanding AI Agent Interface Options with 2D and 3D Digital Human Avatars | When interfacing with generative AI applications, users have multiple communication options—text, voice, or through digital avatars. | false | Avatar Cloud Engine (ACE), Audio2Face, NeMo Microservices, NeMo Retriever, NIM, NIM Agent Blueprint, Omniverse, Riva | 2\|expanding ai agent interface options with 2d and 3d digital human avatars | 1731516803 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/customize-generative-ai-models-for-enterprise-applications-with-llama-3-1/", "text" => "Learn more"} | Customize Generative AI Models for Enterprise Applications with Llama 3.1 | The newly unveiled Llama 3.1 collection of 8B, 70B, and 405B large language models (LLMs) is narrowing the gap between proprietary and open-source models. | false | NeMo, NeMo Curator, NeMo Customizer, NeMo Evaluator, NeMo Guardrails, NeMo Retriever, NIM | 2\|customize generative ai models for enterprise applications with llama 3.1 | 1721722500 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/build-an-agentic-rag-pipeline-with-llama-3-1-and-nvidia-nemo-retriever-nims/", "text" => "Learn more"} | Build an Agentic RAG Pipeline with Llama 3.1 and NVIDIA NeMo Retriever NIMs | Employing retrieval-augmented generation (RAG) is an effective strategy for ensuring large language model (LLM) responses are up-to-date and not hallucinated. | false | NeMo, NeMo Microservices, NeMo Retriever, NIM | 2\|build an agentic rag pipeline with llama 3.1 and nvidia nemo retriever nims | 1721722500 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/deliver-personalized-retail-experiences-with-an-ai-powered-shopping-advisor/", "text" => "Learn more"} | Deliver Personalized Retail Experiences with an AI-Powered Shopping Advisor | Imagine being able to put your best sales associate in front of every customer for every interaction. Your best sales associate offers product recommendations… | false | NGC, NeMo, NeMo Retriever, NIM | 2\|deliver personalized retail experiences with an ai-powered shopping advisor | 1722514132 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/accelerating-inference-on-end-to-end-workflows-with-h2o-ai-and-nvidia/", "text" => "Learn more"} | Accelerating Inference on End-to-End Workflows with H2O.ai and NVIDIA | Data scientists are combining generative AI and predictive analytics to build the next generation of AI applications. In financial services… | false | NeMo Guardrails, NeMo Retriever, RAPIDS, Triton Inference Server, Dynamo | 2\|accelerating inference on end-to-end workflows with h2o.ai and nvidia | 1704348000 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/automating-telco-network-design-using-nvidia-nim-and-nvidia-nemo/", "text" => "Learn more"} | Automating Telco Network Design using NVIDIA NIM and NVIDIA NeMo | Telecom wireless network design demands streamlined processes and standardized approaches. Network architects, engineers, and IT professionals are challenged… | false | NeMo, NeMo Guardrails, NeMo Retriever, NIM | 2\|automating telco network design using nvidia nim and nvidia nemo | 1721714400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/a-deep-dive-into-the-latest-ai-models-optimized-with-nvidia-nim/", "text" => "Learn more"} | A Deep Dive into the Latest AI Models Optimized with NVIDIA NIM | Delivered as optimized containers, NVIDIA NIM microservices are designed to accelerate AI application development for businesses of all sizes… | false | NeMo Retriever, NIM | 2\|a deep dive into the latest ai models optimized with nvidia nim | 1722934800 | Blog | General Interest |
| {"url" => "https://developer.nvidia.com/blog/supercharging-llama-3-1-across-nvidia-platforms/", "text" => "Learn more"} | Supercharging Llama 3.1 across NVIDIA Platforms | Meta’s Llama collection of large language models are the most popular foundation models in the open-source community today, supporting a variety of use cases. | false | AI Enterprise, AI Foundation Models, NeMo Curator, NeMo Evaluator, NeMo Guardrails, NeMo Retriever, NIM, TensorRT | 2\|supercharging llama 3.1 across nvidia platforms | 1721722500 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/video-talk-to-your-supply-chain-data-using-nvidia-nim/", "text" => "Learn more"} | Video: Talk to Your Supply Chain Data Using NVIDIA NIM | NVIDIA operates one of the largest and most complex supply chains in the world. The supercomputers we build connect tens of thousands of NVIDIA GPUs with… | false | cuOpt, NeMo, NeMo Microservices, NeMo Retriever, NIM | 2\|video: talk to your supply chain data using nvidia nim | 1718626409 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/three-building-blocks-for-creating-ai-virtual-assistants-for-customer-service-with-an-nvidia-nim-agent-blueprint/", "text" => "Learn more"} | Three Building Blocks for Creating AI Virtual Assistants for Customer Service with an NVIDIA AI Blueprint | In today’s fast-paced business environment, providing exceptional customer service is no longer just a nice-to-have—it’s a necessity. | false | NeMo, NeMo Microservices, NeMo Retriever, NIM | 2\|three building blocks for creating ai virtual assistants for customer service with an nvidia ai blueprint | 1733932156 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/augmenting-security-operations-centers-with-accelerated-alert-triage-and-llm-agents-using-nvidia-morpheus/", "text" => "Learn more"} | Augmenting Security Operations Centers with Accelerated Alert Triage and LLM Agents Using NVIDIA Morpheus | Every day, security operation center (SOC) analysts receive an overwhelming amount of incoming security alerts. To ensure the continued safety of their… | false | Morpheus, NeMo Retriever | 2\|augmenting security operations centers with accelerated alert triage and llm agents using nvidia morpheus | 1729767736 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/develop-multilingual-and-cross-lingual-information-retrieval-systems-with-efficient-data-storage/", "text" => "Learn more"} | Develop Multilingual and Cross-Lingual Information Retrieval Systems with Efficient Data Storage | Efficient text retrieval is critical for a broad range of information retrieval applications such as search, question answering, semantic textual similarity… | false | NeMo Retriever, NIM | 2\|develop multilingual and cross-lingual information retrieval systems with efficient data storage | 1734422400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/advanced-rag-techniques-for-telco-o-ran-specifications-using-nvidia-nim-microservices/", "text" => "Learn more"} | Advanced RAG Techniques for Telco O-RAN Specifications Using NVIDIA NIM Microservices | Mobile communication standards play a crucial role in the telecommunications ecosystem by harmonizing technology protocols to facilitate interoperability… | false | NeMo, NeMo Guardrails, NeMo Retriever, NIM | 2\|advanced rag techniques for telco o-ran specifications using nvidia nim microservices | 1728554081 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/datastax-announces-new-ai-development-platform-built-with-nvidia-ai/", "text" => "Learn more"} | DataStax Announces New AI Development Platform, Built with NVIDIA AI | As enterprises increasingly adopt AI technologies, they face a complex challenge of efficiently developing, securing, and continuously improving AI applications… | false | AI Enterprise, NeMo, NeMo Curator, NeMo Customizer, NeMo Evaluator, NeMo Guardrails, NeMo Microservices, NeMo Retriever, NIM | 2\|datastax announces new ai development platform, built with nvidia ai | 1728972000 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/scaling-enterprise-rag-with-accelerated-ethernet-networking-and-networked-storage/", "text" => "Learn more"} | Scaling Enterprise RAG with Accelerated Ethernet Networking and Networked Storage | In the era of generative AI, where machines are not just learning from data but generating human-like text, images, video, and more… | false | NeMo, NeMo Retriever | 2\|scaling enterprise rag with accelerated ethernet networking and networked storage | 1710774000 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/tips-for-building-a-rag-pipeline-with-nvidia-ai-langchain-ai-endpoints/", "text" => "Learn more"} | Tips for Building a RAG Pipeline with NVIDIA AI LangChain AI Endpoints | Retrieval-augmented generation (RAG) is a technique that combines information retrieval with a set of carefully designed system prompts to provide more accurate… | false | AI Foundation Models, NeMo Retriever | 2\|tips for building a rag pipeline with nvidia ai langchain ai endpoints | 1715158800 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/an-easy-introduction-to-multimodal-retrieval-augmented-generation/", "text" => "Learn more"} | An Easy Introduction to Multimodal Retrieval-Augmented Generation | A retrieval-augmented generation (RAG) application has exponentially higher utility if it can work with a wide variety of data types—tables, graphs, charts… | false | General, NeMo Retriever | 2\|an easy introduction to multimodal retrieval-augmented generation | 1710932400 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/harnessing-data-with-ai-to-boost-zero-trust-cyber-defense/", "text" => "Learn more"} | Harnessing Data with AI to Boost Zero Trust Cyber Defense | Modern cyber threats have grown increasingly sophisticated, posing significant risks to federal agencies and critical infrastructure. According to Deloitte… | false | Morpheus, NeMo, NeMo Retriever, NIM | 2\|harnessing data with ai to boost zero trust cyber defense | 1727343355 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/nvidia-text-embedding-model-tops-mteb-leaderboard/", "text" => "Learn more"} | NVIDIA Text Embedding Model Tops MTEB Leaderboard | The latest embedding model from NVIDIA—NV-Embed—set a new record for embedding accuracy with a score of 69.32 on the Massive Text Embedding Benchmark (MTEB)… | false | AI Enterprise, NeMo Retriever | 2\|nvidia text embedding model tops mteb leaderboard | 1718013600 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/build-enterprise-retrieval-augmented-generation-apps-with-nvidia-retrieval-qa-embedding-model/", "text" => "Learn more"} | Build Enterprise Retrieval-Augmented Generation Apps with NVIDIA Retrieval QA Embedding Model | Large language models (LLMs) are transforming the AI landscape with their profound grasp of human and programming languages. Essential for next-generation… | false | NeMo, NeMo Retriever | 2\|build enterprise retrieval-augmented generation apps with nvidia retrieval qa embedding model | 1701166250 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/rag-101-retrieval-augmented-generation-questions-answered/", "text" => "Learn more"} | RAG 101: Retrieval-Augmented Generation Questions Answered | Data scientists, AI engineers, MLOps engineers, and IT infrastructure professionals must consider a variety of factors when designing and deploying a RAG… | false | NeMo Guardrails, NeMo Retriever, TensorRT, Triton Inference Server, Dynamo | 2\|rag 101: retrieval-augmented generation questions answered | 1702899882 | Blog | Intermediate |
| {"url" => "https://www.nvidia.com/en-us/glossary/retrieval-augmented-generation/", "text" => "Learn more"} | What is Retrieval-Augmented Generation? | Retrieval-augmented generation enhances large language model prompts with relevant data for more practical, accurate responses. | true | TensorRT, Triton Inference Server, NeMo Guardrails, Dynamo | 0\|what is retrieval-augmented generation? | 1791277768 | Glossary Page | General Interest, Beginner |
| {"url" => "https://developer.nvidia.com/blog/evaluating-retriever-for-enterprise-grade-rag/", "text" => "Learn more"} | Evaluating Retriever for Enterprise-Grade RAG | The conversation about designing and evaluating Retrieval-Augmented Generation (RAG) systems is a long, multi-faceted discussion. Even when we look at retrieval… | false | NeMo, NeMo Retriever | 2\|evaluating retriever for enterprise-grade rag | 1708686146 | Blog | Intermediate |
| {"url" => "https://www.youtube.com/watch?v=NaT5Eo97_I0", "text" => "Learn more"} | Multimodal AI RAG with LlamaIndex, NVIDIA NIM, and Milvus | This video explains how to create a multimodal AI retrieval-augmented generation (RAG) application | false | NIM | 1\|multimodal ai rag with llamaindex, nvidia nim, and milvus | 1791278003 | Video | Intermediate, Beginner |
| {"url" => "https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-FX-15+V1", "text" => "Learn more"} | Building RAG Agents with LLMs | This course will show you how to deploy an agent system in practice with the flexibility to scale up your system to meet the demands of users and customers. | false | NeMo, NIM | 1\|building rag agents with llms | 1791277768 | Learning Path | Intermediate |
| {"url" => "https://www.youtube.com/watch?v=09uDCmLzYHA", "text" => "Learn more"} | LLM Assistants with LlamaIndex, NVIDIA NIM, and Milvus | In this video, we dive into the essentials of creating a Q&A chatbot. | false | NIM | 1\|llm assistants with llamaindex, nvidia nim, and milvus | 1791278003 | Video | Intermediate, Beginner |
| {"url" => "https://www.nvidia.com/en-us/glossary/large-language-models/", "text" => "Learn more"} | What are Large Language Models? | Large language models largely represent a class of deep learning architectures called transformer networks. | false | NeMo, BioNeMo | 1\|what are large language models? | 1791277768 | Glossary Page | General Interest, Beginner |
| {"url" => "https://github.com/NVIDIA/GenerativeAIExamples", "text" => "Learn more"} | Generative AI Examples | Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture. | true | NeMo, NIM, Triton Inference Server, TensorRT, Dynamo | 0\|generative ai examples | 1791278003 | GitHub | Beginner, Intermediate |
| {"url" => "https://docs.api.nvidia.com/", "text" => "Learn more"} | NVIDIA API Documentation | Your guide to NVIDIA APIs including NIM and CUDA-X microservices | true | NIM, CUDA-X | 0\|nvidia api documentation | 1791277769 | Documentation | Intermediate |
| {"url" => "https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-FX-20+V1", "text" => "Learn more"} | Techniques for Improving the Effectiveness of RAG Systems | Learn techniques that can take your RAG system from an interesting proof-of-concept to a serious asset. | false | NIM | 1\|techniques for improving the effectiveness of rag systems | 1791278003 | Training | Intermediate |
| {"url" => "https://www.youtube.com/watch?v=mg0kwpmUhPU", "text" => "Learn more"} | How to Build a Simple AI Agent in 5 Minutes with NVIDIA NIM | Learn how to build AI agents for content creation and digital design in just 5 minutes using NVIDIA NIM microservices—powered by Llama 3.1 405B and stable diffusion models. | true | NIM | 0\|how to build a simple ai agent in 5 minutes with nvidia nim | 1791277769 | Video | Beginner |
| {"url" => "https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-FX-23+V1", "text" => "Learn more"} | Introduction to NVIDIA NIM™ Microservices | Learn how NIM enables the building, deploying, and scaling of AI applications. | true | NIM | 0\|introduction to nvidia nimtm microservices | 1791278003 | Training | Intermediate |
| {"url" => "https://nvdam.widen.net/s/brxsxxtskb/dli-learning-journey-2009000-r5-web", "text" => "Learn more"} | Generative AI and Large Language Models Training | Discover the generative AI learning path for developers. | false | NIM | 1\|generative ai and large language models training | 1791278003 | Learning Path | Beginner |
| {"url" => "https://www.nvidia.com/en-us/glossary/synthetic-data-generation/", "text" => "Learn more"} | What is Synthetic Data Generation?  | Learn about synthetic data generation, how it works, and why it's important for AI. | false | Omniverse, Omniverse Replicator | 1\|what is synthetic data generation? | 1791278003 | Glossary Page | Beginner |
| {"url" => "https://academy.nvidia.com/en/course/ai-for-all-from-basics-to-genai-practice/?cm=81220", "text" => "Learn more"} | AI for All: From Basics to GenAI Practice | Interactive self-paced learning via the NVIDIA Online Academy | false | NIM | 1\|ai for all: from basics to genai practice | 1791278003 | Training | Beginner |
| {"url" => "https://www.nvidia.com/en-us/glossary/vision-language-models/", "text" => "Learn more"} | What are Vision Language Models?  | Learn about Vision Language Models (VLM), why they are important, and how they work. | false | NIM, Blueprint | 1\|what are vision language models? | 1791278003 | Glossary Page | Beginner |
| {"url" => "https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-FX-07+V1", "text" => "Learn more"} | Generative AI Explained | In this no-coding course, learn Generative AI concepts and applications, as well as the challenges and opportunities in this exciting field. | false | NIM | 1\|generative ai explained | 1791278003 | Training | Beginner |
| {"url" => "https://docs.nvidia.com/ai-enterprise/index.html", "text" => "Learn more"} | NVIDIA AI Enterprise Documentation | Documentation for NVIDIA AI Enterprise, an end-to-end cloud native software platform. | false | NIM | 1\|nvidia ai enterprise documentation | 1791278003 | Documentation | Intermediate |
| {"url" => "https://www.nvidia.com/en-us/glossary/generative-ai/", "text" => "Learn more"} | What is Generative AI? | Learn about generative AI and how it works. | false | NeMo, NIM | 1\|what is generative ai? | 1791278003 | Glossary Page | Beginner |
| {"url" => "https://developer.nvidia.com/blog/access-to-nvidia-nim-now-available-free-to-developer-program-members/", "text" => "Learn more"} | Free NVIDIA NIM Access For Developer Program Members | Join the NVIDIA Registered Developer Program and learn how to access NIM microservices for free. | true | NIM | 0\|free nvidia nim access for developer program members | 1791278003 | Blog | General Interest |
| {"url" => "https://www.youtube.com/watch?v=JlYVBAQC0tQ", "text" => "Learn more"} | How Robots Use Generative AI to Reason and Act with ReMEmbR | This video features ReMEmbR which enable robots to reason and take actions over what they see during a long-horizon deployment to answer user queries and produce navigation goals. | false | Isaac | 1\|how robots use generative ai to reason and act with remembr | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=N_OOfkEWcOk", "text" => "Learn more"} | Build a Retrieval-Augmented Generation Chatbot in 5 Minutes | This demo showcases how to design and create an enterprise-grade retrieval-augmented generation (RAG) pipeline using NVIDIA AI Foundation models. | false | AI Foundation Models | 1\|build a retrieval-augmented generation chatbot in 5 minutes | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=Z-OlJ2oqJno", "text" => "Learn more"} | Deploy Generative AI Coding Agents, Image Search, and More | This video demonstrates how large language models (LLMs) can power various applications and focuses on image search, code assistants, and vision language action (VLA) models. | false | Metropolis | 1\|deploy generative ai coding agents, image search, and more | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=bagJeryUHOk", "text" => "Learn more"} | Build a RAG Application With NVIDIA RTX Virtual Workstation | Develop a retrieval-augmented generation (RAG) application using NVIDIA RTX Virtual Workstation and conduct inference locally on your virtual machines within minutes. | false | RTX GPU | 1\|build a rag application with nvidia rtx virtual workstation | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=Soy_myOfWIU", "text" => "Learn more"} | Efficient Generative AI Tokenizers for Image and Video | NVIDIA Cosmos tokenizer provides open models for efficient image and video compression and high-quality reconstruction, achieving speeds up to 12x faster than other tokenizers. | false | Cosmos | 1\|efficient generative ai tokenizers for image and video | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=bpOvayHifNQ&t=5s", "text" => "Learn more"} | Deploying Generative AI in Production with NVIDIA NIM | Unlock the potential of generative AI with NVIDIA NIM. This video dives into how NVIDIA NIM microservices can transform your AI deployment into a production-ready powerhouse. | false | NIM | 1\|deploying generative ai in production with nvidia nim | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=lqbYP6Cysgw", "text" => "Learn more"} | Unlocking Synthetic Data Generation with Llama 3.1 | Discover how to leverage the synthetic data generation pipeline from NVIDIA NeMo Curator, which enables enterprises to effortlessly produce vast amounts of high-quality data. | false | NeMo Curator | 1\|unlocking synthetic data generation with llama 3.1 | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=KmEX-1mS8Ps", "text" => "Learn more"} | Local AI Copilots with LangChain, NVIDIA NIM, and FAISS  | This video explains how to develop a local AI copilot using LangChain, NVIDIA NIM, and FAISS. | false | NIM | 1\|local ai copilots with langchain, nvidia nim, and faiss | 1791278003 | Video | Intermediate |
| {"url" => "https://www.youtube.com/watch?v=WUBl6SMRy0g&t=32s", "text" => "Learn more"} | Generative AI Inference Performance and TCO Advantage | Visualize the impact of high-performance generative AI inferencing with NVIDIA NIM microservices. | false | NIM | 1\|generative ai inference performance and tco advantage | 1791278003 | Video | Beginner |
| {"url" => "https://developer.nvidia.com/blog/how-using-a-reranking-microservice-can-improve-accuracy-and-costs-of-information-retrieval/", "text" => "Learn more"} | How Using a Reranking Microservice Can Improve Accuracy and Costs of Information Retrieval | Applications requiring high-performance information retrieval span a wide range of domains, including search engines, knowledge management systems, AI agents… | false | Blueprint, NeMo, NeMo Retriever, NIM | 2\|how using a reranking microservice can improve accuracy and costs of information retrieval | 1741257218 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/developing-an-ai-powered-tool-for-automatic-citation-validation-using-nvidia-nim/", "text" => "Learn more"} | Developing an AI-Powered Tool for Automatic Citation Validation Using NVIDIA NIM | The accuracy of citations is crucial for maintaining the integrity of both academic and AI-generated content. When citations are inaccurate or wrong… | false | A100, NeMo Retriever, NIM | 2\|developing an ai-powered tool for automatic citation validation using nvidia nim | 1744796450 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/evaluating-and-enhancing-rag-pipeline-performance-using-synthetic-data/", "text" => "Learn more"} | Evaluating and Enhancing RAG Pipeline Performance Using Synthetic Data  | As large language models (LLM) gain popularity in various question-answering systems, retrieval-augmented generation (RAG) pipelines have also become a focal… | false | NeMo Curator, NeMo Retriever | 2\|evaluating and enhancing rag pipeline performance using synthetic data | 1744025946 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/accelerated-vector-search-approximating-with-nvidia-cuvs-ivf-flat/", "text" => "Learn more"} | Accelerated Vector Search: Approximating with NVIDIA cuVS Inverted Index | Performing an exhaustive exact k-nearest neighbor (kNN) search, also known as brute-force search, is expensive, and it doesn’t scale particularly well to larger… | false | cuVS, RAPIDS | 2\|accelerated vector search: approximating with nvidia cuvs inverted index | 1696245418 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/accelerating-vector-search-using-gpu-powered-indexes-with-rapids-raft/", "text" => "Learn more"} | Accelerating Vector Search: Using GPU-Powered Indexes with NVIDIA cuVS | In the current AI landscape, vector search is one of the hottest topics due to its applications in large language models (LLM) and generative AI. | false | cuVS, RAPIDS | 2\|accelerating vector search: using gpu-powered indexes with nvidia cuvs | 1694422740 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/build-enterprise-ai-agents-with-advanced-open-nvidia-llama-nemotron-reasoning-models/", "text" => "Learn more"} | Build AI Agents With NVIDIA Llama Nemotron Reasoning Models | Read how NVIDIA developed the Llama Nemotron with reasoning model family, built on top of Llama open models and post-trained with the reasoning expertise of DeepSeek-R1. | true | NIM | 0\|build ai agents with nvidia llama nemotron reasoning models | 1791277769 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/accelerating-vector-search-fine-tuning-gpu-index-algorithms/", "text" => "Learn more"} | Accelerating Vector Search: Fine-Tuning GPU Index Algorithms | In this post, we dive deeper into each of the GPU-accelerated indexes mentioned in part 1 and give a brief explanation of how the algorithms work… | false | cuVS, RAPIDS | 2\|accelerating vector search: fine-tuning gpu index algorithms | 1694422800 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/maximize-ai-agent-performance-with-data-flywheels-using-nvidia-nemo-microservices/", "text" => "Learn more"} | Maximize AI Agent Performance with Data Flywheels | AI agents need to continuously evolve. With NeMo microservices developers can create and maintain a robust data flywheel for AI agents. | true | NeMo, NeMo Retriever, NeMo Curator, NeMo Evaluator | 0\|maximize ai agent performance with data flywheels | 1791278003 | Blog | Beginner |
| {"url" => "https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo-microservices/collections/nemo-microservices", "text" => "Learn more"} | NVIDIA NeMo Microservices | This collection contains the NeMo microservices to build an end-to-end platform for fine-tuning, evaluating, and serving LLMs on your Kubernetes cluster. | true | NeMo, NeMo Evaluator, NeMo Guardrails, NeMo Customizer | 0\|nvidia nemo microservices | 1791278003 | Container | Intermediate |
| {"url" => "https://nvda.ws/3CwRR2w#new_tab", "text" => "Learn more"} | New NVIDIA AI Blueprint: Build a Customizable RAG Pipeline | Connect AI applications to enterprise data using embedding and reranking models for information retrieval. | false | NeMo Retriever, NIM | 2\|new nvidia ai blueprint: build a customizable rag pipeline | 1738247172 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/accelerating-text-to-sql-inference-on-vanna-with-nvidia-nim-for-faster-analytics/", "text" => "Learn more"} | Accelerating Text-to-SQL Inference on Vanna with NVIDIA NIM for Faster Analytics | Slow and inefficient query generation from natural language inputs bottlenecks decision-making. This forces analysts and business users to rely heavily on data… | false | NeMo Retriever, NIM | 2\|accelerating text-to-sql inference on vanna with nvidia nim for faster analytics | 1748594728 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/concept%e2%80%91driven-ai-teaching-assistant-guides-students-to-deeper-insights/", "text" => "Learn more"} | Concept‑Driven AI Teaching Assistant Guides Students to Deeper Insights | In today’s educational landscape, generative AI tools have become both a blessing and a challenge. While these tools offer unprecedented access to information… | false | Blueprint, DGX Cloud, NeMo Guardrails, NeMo Retriever | 2\|concept-driven ai teaching assistant guides students to deeper insights | 1746626271 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/build-efficient-ai-agents-through-model-distillation-with-nvidias-data-flywheel-blueprint/", "text" => "Learn more"} | Build Efficient AI Agents With the Data Flywheel Blueprint | Explore how our new AI blueprint can help enable self-improving AI agents by automating model optimization. | false | NeMo, NeMo Evaluator, NeMo Customizer, NeMo Guardrails | 1\|build efficient ai agents with the data flywheel blueprint | 1791278003 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/chat-with-your-enterprise-data-through-open-source-ai-q-nvidia-blueprint/", "text" => "Learn more"} | Chat With Your Enterprise Data With the AI-Q Blueprint | Learn about AI-Q, a free reference implementation for building advanced AI agents that connect to your data, reason, and deliver fast, accurate answers. | false | NeMo, NeMo Evaluator, NeMo Customizer, NeMo Guardrails | 1\|chat with your enterprise data with the ai-q blueprint | 1791278003 | Blog | Beginner |
| {"url" => "https://www.nvidia.com/en-us/events/supercharge-agentic-ai-build-scalable-data-flywheels/", "text" => "Learn more"} | Supercharge Agentic AI: Build Scalable Data Flywheels | Learn best practices for integrating NeMo components to optimize AI agent performance. | false | NeMo, NeMo Evaluator, NeMo Customizer, NeMo Guardrails | 1\|supercharge agentic ai: build scalable data flywheels | 1791278003 | Webinar | Beginner |
| {"url" => "https://youtu.be/1auHkFYrDO4", "text" => "Learn more"} | Unlock the Power of AI Agents with the AI-Q NVIDIA Blueprint | Build AI agents that use reasoning and connect to many data sources and tools to distill in-depth source materials with efficiency and precision. | false | NeMo Agent Toolkit | 1\|unlock the power of ai agents with the ai-q nvidia blueprint | 1791278003 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=TX-NNK2FRdY", "text" => "Learn more"} | Customizing AI Agents for Tool Calling  | Learn how to customize AI agents for precise function calling with this end-to-end example with NVIDIA NeMo microservices. | false | NeMo, NeMo Customizer, NeMo Evaluator, NeMo Guardrails | 1\|customizing ai agents for tool calling | 1791278003 | Video | Beginner |
| {"url" => "https://youtu.be/hTYrjYbFHyU", "text" => "Learn more"} | Optimize AI Agents With a Data Flywheel | Get an overview of what a data flywheel is, how a data flywheel automates the optimization of AI agents by continuously automating model distillation and experimentation. | false | NeMo, NeMo Evaluator, NeMo Customizer, NeMo Guardrails | 1\|optimize ai agents with a data flywheel | 1791278003 | Video | Beginner |
| {"url" => "https://build.nvidia.com/nvidia/build-an-enterprise-data-flywheel", "text" => "Learn more"} | Data Flywheel Blueprint | Build a data flywheel, with NVIDIA NeMo microservices, that continuously optimizes AI agents for latency and cost — while maintaining accuracy targets. | true | NeMo, NeMo Evaluator, NeMo Customizer, NeMo Guardrails | 0\|data flywheel blueprint | 1791278003 | Example | Beginner |
| {"url" => "https://build.nvidia.com/nvidia/aiq", "text" => "Learn more"} | AI-Q Blueprint | Build AGA powered by AGI models that continuously process and synthesize multimodal enterprise data, enabling reasoning, planning, and refinement to generate comprehensive reports. | true | NeMo Agent Toolkit | 0\|ai-q blueprint | 1791278003 | Example | Beginner |
| {"url" => "https://developer.nvidia.com/blog/best-in-class-multimodal-rag-how-the-llama-3-2-nemo-retriever-embedding-model-boosts-pipeline-accuracy/", "text" => "Learn more"} | Best-in-Class Multimodal RAG: How the Llama 3.2 NeMo Retriever Embedding Model Boosts Pipeline Accuracy | Data goes far beyond text—it is inherently multimodal, encompassing images, video, audio, and more, often in complex and unstructured formats. | false | NeMo, NeMo Retriever | 2\|best-in-class multimodal rag: how the llama 3.2 nemo retriever embedding model boosts pipeline accuracy | 1751277394 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/how-to-enhance-rag-pipelines-with-reasoning-using-nvidia-llama-nemotron-models/", "text" => "Learn more"} | How to Enhance RAG Pipelines with Reasoning Using NVIDIA Llama Nemotron Models | A key challenge for retrieval-augmented generation (RAG) systems is handling user queries that lack explicit clarity or carry implicit intent. | false | NeMo Retriever, NIM | 2\|how to enhance rag pipelines with reasoning using nvidia llama nemotron models | 1754301600 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/optimizing-vector-search-for-indexing-and-real-time-retrieval-with-nvidia-cuvs/", "text" => "Learn more"} | Optimizing Vector Search for Indexing and Real-Time Retrieval with NVIDIA cuVS | AI-powered search demands high-performance indexing, low-latency retrieval, and seamless scalability. NVIDIA cuVS brings GPU-accelerated vector search and… | false | cuVS | 2\|optimizing vector search for indexing and real-time retrieval with nvidia cuvs | 1753361140 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/run-multimodal-extraction-for-more-efficient-ai-pipelines-using-one-gpu/", "text" => "Learn more"} | Run Multimodal Extraction for More Efficient AI Pipelines Using One GPU | As enterprises generate and consume increasing volumes of diverse data, extracting insights from multimodal documents, like PDFs and presentations… | false | Blueprint, NeMo Retriever | 2\|run multimodal extraction for more efficient ai pipelines using one gpu | 1750253511 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/turn-complex-documents-into-usable-data-with-vlm-nvidia-nemotron-parse-1-1/", "text" => "Learn more"} | Turn Complex Documents into Usable Data with VLM, NVIDIA Nemotron Parse 1.1 | Enterprises generate and store vast amounts of unstructured data in documents like legal documents, sales documents, statement of work, delivery notices… | false | NeMo Retriever | 2\|turn complex documents into usable data with vlm, nvidia nemotron parse 1.1 | 1753780155 | Blog | Intermediate |
| {"url" => "https://www.nvidia.com/en-us/events/supercharge-agentic-ai-build-scalable-data-flywheels/#new_tab", "text" => "Learn more"} | Upcoming Webinar: Supercharge Agentic AI with Scalable Data Flywheels | Join our live webinar on June 18 to see how NVIDIA NeMo microservices speed AI agent development. | false | NeMo Curator, NeMo Customizer, NeMo Evaluator, NeMo Guardrails, NeMo Microservices, NeMo Retriever | 2\|upcoming webinar: supercharge agentic ai with scalable data flywheels | 1748360626 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/modeling-attacks-on-ai-powered-apps-with-the-ai-kill-chain-framework/", "text" => "Learn more"} | Modeling Attacks on AI-Powered Apps with the AI Kill Chain Framework | AI-powered applications are introducing new attack surfaces that traditional security models don’t fully capture, especially as these agentic systems gain… | false | cuVS, NIM | 2\|modeling attacks on ai-powered apps with the ai kill chain framework | 1757581200 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/approaches-to-pdf-data-extraction-for-information-retrieval/", "text" => "Learn more"} | Approaches to PDF Data Extraction for Information Retrieval | The PDF is among the most common file formats for sharing information such as financial reports, research papers, technical documents, and marketing materials. | false | Blueprint, cuVS, NeMo, NeMo Retriever | 2\|approaches to pdf data extraction for information retrieval | 1753268174 | Blog | Intermediate, Advanced |
| {"url" => "https://huggingface.co/nvidia/llama-nemoretriever-colembed-3b-v1/tree/main#new_tab", "text" => "Learn more"} | NVIDIA NeMo Retriever Scores First Place for Visual Retrieval | NeMo Retriever tops several visual document retrieval leaderboards, setting new standards for RAG apps. | false | NeMo Retriever | 2\|nvidia nemo retriever scores first place for visual retrieval | 1751276579 | Blog | General Interest |
| {"url" => "https://www.youtube.com/watch?v=NBcZOQHn46g", "text" => "Learn more"} | Beyond the Algorithm with NVIDIA | Explore the NVIDIA Data Flywheel Blueprint, an open reference architecture for distilling knowledge from larger models into smaller, faster, and cost-efficient alternatives. | true | NeMo, NeMo Evaluator, NeMo Customizer, NeMo Guardrails | 0\|beyond the algorithm with nvidia | 1791278003 | Video | Beginner |
| {"url" => "https://developer.nvidia.com/blog/build-a-log-analysis-multi-agent-self-corrective-rag-system-with-nvidia-nemotron/", "text" => "Learn more"} | Build a Log Analysis Multi-Agent Self-Corrective RAG System with NVIDIA Nemotron | Logs are the lifeblood of modern systems. But as applications scale, logs often grow into endless walls of text—noisy, repetitive, and overwhelming. | false | NeMo Retriever, Nemotron, NIM | 2\|build a log analysis multi-agent self-corrective rag system with nvidia nemotron | 1760086800 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/enabling-horizontal-autoscaling-of-enterprise-rag-components-on-kubernetes/", "text" => "Learn more"} | Enabling Horizontal Autoscaling of Enterprise RAG Components on Kubernetes | Today’s best AI agents rely on retrieval-augmented generation (RAG) to enable more accurate results. A RAG system facilitates the use of a knowledge base to… | false | Blueprint, cuVS, NIM | 2\|enabling horizontal autoscaling of enterprise rag components on kubernetes | 1765544400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/develop-specialized-ai-agents-with-new-nvidia-nemotron-vision-rag-and-guardrail-models/", "text" => "Learn more"} | Develop Specialized AI Agents With NVIDIA Nemotron Models | This blog covers the features, performance, and tutorials on using the new Nemotron models for building multimodal agents, RAG pipelines, and AI with content safety. | true | NeMo, NeMo Retriever, NeMo Customizer, NeMo Guardrails, Blueprint, NeMo Evaluator, Nemotron, NIM | 0\|develop specialized ai agents with nvidia nemotron models | 1791278003 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/build-a-rag-agent-with-nvidia-nemotron/", "text" => "Learn more"} | Build a Retrieval-Augmented Generation (RAG) Agent with NVIDIA Nemotron | Unlike traditional LLM-based systems that are limited by their training data, retrieval-augmented generation (RAG) improves text generation by incorporating… | false | NeMo Retriever, Nemotron, NIM | 2\|build a retrieval-augmented generation (rag) agent with nvidia nemotron | 1758614400 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/enhancing-gpu-accelerated-vector-search-in-faiss-with-nvidia-cuvs/", "text" => "Learn more"} | Enhancing GPU-Accelerated Vector Search in Faiss with NVIDIA cuVS | As companies collect more unstructured data and increasingly use large language models (LLMs), they need faster and more scalable systems. | false | cuVS | 2\|enhancing gpu-accelerated vector search in faiss with nvidia cuvs | 1762432898 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/how-to-build-a-voice-agent-with-rag-and-safety-guardrails/", "text" => "Learn more"} | How to Build a Voice Agent with RAG and Safety Guardrails | Building an agent is more than just “call an API”—it requires stitching together retrieval, speech, safety, and reasoning components so they behave like one… | false | NeMo Retriever, Nemotron | 2\|how to build a voice agent with rag and safety guardrails | 1767621966 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/reducing-cuda-binary-size-to-distribute-cuml-on-pypi/", "text" => "Learn more"} | Reducing CUDA Binary Size to Distribute cuML on PyPI | Starting with the 25.10 release, pip-installable cuML wheels can now be downloaded directly from PyPI. No more complex installation steps or managing Conda… | false | CUDA, cuML, cuVS, RAPIDS | 2\|reducing cuda binary size to distribute cuml on pypi | 1765791000 | Blog | Intermediate |
| {"url" => "https://youtu.be/LOhIdijVno0", "text" => "Learn more"} | Build a Custom AI Agent With NVIDIA Nemotron RAG Models | This hands-on tutorial guides you through creating an Agentic Retrieval-Augmented Generation (RAG) pipeline using NVIDIA's open Nemotron models for embedding and reranking. | false | NeMo, NeMo Retriever | 1\|build a custom ai agent with nvidia nemotron rag models | 1791278003 | Video | Beginner |
| {"url" => "https://youtu.be/uuhEAZjnePk", "text" => "Learn more"} | Culturally-Aware Guardrails With Nemotron Safety Guard  | The Llama 3.1 Nemotron Safety Guard 8b v3 model tackles content moderation challenges by introducing a multilingual moderation system. | false | NeMo, NeMo Guardrails | 1\|culturally-aware guardrails with nemotron safety guard | 1791278003 | Video | Beginner |
| {"url" => "https://youtu.be/bQ7prf_RDMw", "text" => "Learn more"} | Build Multimodal Agents for Document and Video Intelligence | This video presents a unified approach to multimodal and document intelligence using NVIDIA Nemotron models. | false | NIM | 1\|build multimodal agents for document and video intelligence | 1791278003 | Video | Beginner |
| {"url" => "https://developer.nvidia.com/blog/multi-agent-warehouse-ai-command-layer-enables-operational-excellence-and-supply-chain-intelligence/", "text" => "Learn more"} | Multi-Agent Warehouse AI Command Layer Enables Operational Excellence and Supply Chain Intelligence | Warehouses have never been more automated, more data-rich, or more operationally demanding than they are now—yet they still rely on systems that can’t keep up. | false | AI Enterprise, Blueprint, cuML, cuVS, NeMo, NIM | 2\|multi-agent warehouse ai command layer enables operational excellence and supply chain intelligence | 1767938400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/how-to-build-a-document-processing-pipeline-for-rag-with-nemotron/", "text" => "Learn more"} | How to Build a Document Processing Pipeline for RAG with Nemotron  | What if your AI agent could instantly parse complex PDFs, extract nested tables, and “see” data within charts as easily as reading a text file? | false | NeMo, NeMo Microservices, NeMo Retriever, Nemotron | 2\|how to build a document processing pipeline for rag with nemotron | 1770192000 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/24-7-simulation-loops-how-agentic-ai-keeps-subsurface-engineering-moving/", "text" => "Learn more"} | 24/7 Simulation Loops: How Agentic AI Keeps Subsurface Engineering Moving | The subsurface industry is at a critical point in its digital evolution. For decades, unlocking reservoir potential has relied on experts performing essential… | false | NeMo, NeMo Retriever, Nemotron, NIM | 2\|24/7 simulation loops: how agentic ai keeps subsurface engineering moving | 1777363200 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/building-an-analysis-ai-agent-for-industrial-alarm-management-with-nvidia-nemotron/", "text" => "Learn more"} | Building an Analysis AI Agent for Industrial Alarm Management with NVIDIA Nemotron | Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context… | false | Blueprint, CUDA, cuDF, NeMo Retriever, Nemotron, NIM | 2\|building an analysis ai agent for industrial alarm management with nvidia nemotron | 1783418400 | Blog | Intermediate |
| {"url" => "https://developer.nvidia.com/blog/run-massive-scale-umap-in-minutes-using-multiple-gpus-without-losing-accuracy/", "text" => "Learn more"} | Run Massive-Scale UMAP in Minutes Using Multiple GPUs—Without Losing Accuracy | Uniform Manifold Approximation and Projection (UMAP) is a dimensionality reduction technique widely used for visualization and feature extraction. | false | cuML, cuVS, DGX, H100 | 2\|run massive-scale umap in minutes using multiple gpus-without losing accuracy | 1787046488 | Blog | Intermediate |

[Download the raw results data (JSON)](https://developer.nvidia.com/search-data/ll_rag.json)