1. [Topics](https://developer.nvidia.com/topics/)
2. [AI](https://developer.nvidia.com/topics/ai/)
3. [Generative AI](https://developer.nvidia.com/topics/ai/generative-ai)

cuVS  

# NVIDIA cuVS: GPU-Accelerated Vector Search and Data Clustering   

NVIDIA cuVS is an open source library for GPU-accelerated vector search and data clustering that enables faster vector searches and index builds.

It supports scalable data analysis, enhances semantic search efficiency, and helps developers accelerate existing systems or compose new ones from the ground up. Integrated with key libraries and databases, cuVS also manages complex code updates as new NVIDIA architectures and NVIDIA® CUDA® versions are released, ensuring peak performance and seamless scalability.

[Download cuVS Now](https://github.com/rapidsai/cuvs "Try Now")[View Integrations](https://docs.rapids.ai/api/cuvs/nightly/integrations/ "Request License")[Documentation](https://docs.nvidia.com/cuvs/home "Request License")

* * *

## How NVIDIA cuVS Accelerates Vector Search and Index Builds  

NVIDIA cuVS is designed to accelerate and optimize vector index builds and vector search for existing [databases](https://www.nvidia.com/en-us/glossary/vector-database/) and vector search libraries. It enables developers to enhance data mining and semantic search workloads, such as recommender systems and [retrieval-augmented generation](/topics/ai/retrieval-augmented-generation) (RAG). Built on the [NVIDIA CUDA software stack](https://docs.rapids.ai/api/cuvs/nightly/#cuvs-technology-stack), it contains many building blocks for composing vector search systems and exposes easy-to-use APIs for C, C++, Rust, Java, Python, and Go.

 ![NVIDIA cuVS accelerates and optimizes vector index builds and vector search](https://developer.download.nvidia.com/images/how-nvidia-cu-vs-works.svg)

### Introductory Blog

Get an intro into accelerating vector search with cuVS, popular applications, and performance comparison of GPU-accelerated vector search indexes vs. CPU.

[Read Vector Search Intro  
](https://developer.nvidia.com/blog/accelerating-vector-search-using-gpu-powered-indexes-with-rapids-raft/ "Get Started")

### Getting Started Guide

Understand the differences between vector search indexes and fully-fledged vector databases.

[Get the Vector Search Primer](https://docs.rapids.ai/api/cuvs/nightly/getting_started/ "Get Started")

### Notebooks

Build [IVF-PQ](https://github.com/rapidsai/cuvs/blob/branch-25.02/notebooks/tutorial_ivf_pq.ipynb) index and use it to search approximate nearest neighbors (ANN) or learn how to run approximate nearest neighbor search using [cuVS IVF-Flat](https://github.com/rapidsai/cuvs/blob/branch-25.02/notebooks/ivf_flat_example.ipynb) algorithm.

[Get Notebooks on GitHub](https://github.com/rapidsai/cuvs/tree/branch-25.02/notebooks "Get Started")

### Examples

Get access to drop-in samples to build a new application with cuVS, or use it in an existing project. See cuVS [installation docs](https://docs.rapids.ai/api/cuvs/stable/build.html#cuda-gpu-requirements).

[Explore cuVS Examples on GitHub](https://github.com/rapidsai/cuvs/tree/branch-24.12/examples "Get Started")

* * *

## Key Features of cuVS

### GPU-Accelerated Indexing Algorithms

Optimized GPU indexing enables high-quality index builds and low-latency search. cuVS delivers advanced algorithms for indexing vector embeddings, including exact, tree-based, and graph-based indexes.  

- 

### **GPU-CPU Interoperability**

GPU-built indexes are fully compatible with traditional CPU-based search, enabling fast, cost-effective index creation. In many cases, indexes can be built 40x faster than CPU and converted to compatible CPU formats for search.

- 

### **High-Efficiency Indexing**

GPU indexing lowers cost compared to CPU-only workflows while maintaining quality at scale. Additionally, the ability to build large indexes out-of-core enables more flexible GPU selection and ultimately lower costs per gigabyte.

- 

### 
**### Scalable Index Building**

For real-time applications and large-scale deployments, cuVS enables both scale-up and scale-out for index creation and search at a fraction of the time it takes on a CPU without compromising quality.

### GPU-Accelerated Search Algorithms

cuVS transforms vector search by integrating optimized CUDA-based algorithms for approximate nearest neighbors and clustering, ideal for large-scale, time-sensitive workloads.  

- 

### 
**### Real-Time Updates for Large Language Models (LLMs)**

cuVS enables real-time updates to search indexes by dynamically integrating new embeddings and data without rebuilding the entire index. By integrating cuVS with LLMs, search results remain fresh and relevant.

- 

### 
**### Low-Latency Performance**

cuVS provides ultra-fast response times for applications such as semantic search, where speed and accuracy are critical. Furthermore, support for binary, 8-, 16-, and 32-bit types means memory use is optimized for high-throughput applications.

- 

### 
**### High-Throughput Processing**

GPUs handle hundreds of thousands of queries per second, making cuVS perfect for demanding use cases like machine learning, data mining, and real-time analytics.

## Get Started With cuVS

Select the right path to get started using cuVS. Integrate it into your existing vector search systems, pipelines, or applications and accelerate your semantic search for data mining use cases in production.  

![Evaluate with cuVS Bench](https://developer.download.nvidia.com/icons/containerized-model.svg)

### Evaluate  

Start using cuVS as a benchmarking tool designed for reproducible comparisons of ANN search implementations, especially between GPU and CPU, by optimizing index configurations and analyzing performance across different hardware environments.

[Start Evaluating With cuVS Bench](https://docs.rapids.ai/api/cuvs/nightly/cuvs_bench/)

![Download Library (GitHub)](https://developer.download.nvidia.com/icons/m48-speech-recognition.svg)

### Develop  

NVIDIA cuVS is available on GitHub with end-to-end examples and an automated tuning guide. Access the source code to get started.

[Download Library (GitHub)](https://github.com/rapidsai/cuvs)

![Launch Through Integrations](https://developer.download.nvidia.com/icons/m48-digital-deep-learning-institute-talks-training.svg)

### Launch  

cuVS can be used as a standalone library or deployed through a number of SDK and vector database integrations like FAISS, Milvus, Lucene, Kinetica, and more.

[Launch Through Integrations](https://docs.rapids.ai/api/cuvs/nightly/integrations/)

* * *

## Performance—World's Fastest Vector Search

NVIDIA cuVS exploits the parallel architecture of NVIDIA GPUs, allowing for easy deployment of popular and performance-critical algorithms. GPU-acceleration of vector similarity search [sets benchmark records](https://github.com/harsha-simhadri/big-ann-benchmarks/blob/main/neurips21/t3/LEADERBOARDS.md#public-dataset-leaderboards-and-winners) for large-scale, high-performance solutions.

### 21x Faster Indexing  

Lower is Better.

 ![A chart showing 21X faster indexing on GPU vs CPU in the cloud](https://developer.download.nvidia.com/images/cuvs/index-build-performance-3691350.svg)

_Time to build an index on GPU (8x A10g) vs CPU (Intel Ice Lake) in the cloud (AWS), reducing from hours to minutes._

### 12.5x Lower Cost  

Lower is Better.

 ![A chart showing 12.5X lower cost indexing on GPU vs CPU in the cloud](https://developer.download.nvidia.com/images/cuvs/index-build-cost-3691350.svg)

_Cost to build an index on the GPU (8x A10g) vs CPU (Intel Ice Lake) in the cloud (AWS)._

### 29x Higher Throughput  

Higher is Better.

 ![A chart showing 34X higher throughput on GPU vs CPU](https://developer.download.nvidia.com/images/cuvs/search-throughput-3691350.svg)

_Number of vectors that can be queried per second on a GPU (H100) vs CPU (Intel Xeon Platinum 8470Q) when submitted 10,000 at a time._

### 11x Lower Latency  

Lower is Better.

 ![A chart showing 11X lower latency on GPU vs CPU](https://developer.download.nvidia.com/images/cuvs/search-latency-3691350.svg)

_Average time to process each query on a GPU (H100) vs CPU (Intel Xeon Platinum 8470Q) when submitted one at a time._

* * *

## Starter Kits for NVIDIA cuVS

Start accelerating your libraries, databases, and applications with cuVS by accessing tutorials, notebooks, forums, release notes, and comprehensive documentation.

### For Library Development  

cuVS provides easy-to-use Python APIs, which enable straightforward integration into libraries for data mining and analysis. cuVS is also integrated into the popular FAISS library for CPU and GPU interoperability.

- 

[Explore Example Python Notebooks](https://github.com/rapidsai/cuvs/tree/branch-24.12/notebooks)

- 

[Read the Getting Started Guide](https://docs.rapids.ai/api/cuvs/nightly/getting_started/)

- 

[Read API Documentation](https://docs.rapids.ai/api/cuvs/nightly/api_docs/)

### For Database Development  

cuVS building blocks are built in C++ and wrapped in popular languages like C, Python, Rust, Java, and Go, making them easy to integrate into existing databases and vector indexing tools.

- 

[Explore Example Projects and Code](https://github.com/rapidsai/cuvs/tree/branch-24.12/examples)

- 

[Read the Getting Started Guide](https://docs.rapids.ai/api/cuvs/nightly/getting_started/)

- 

[Try the Reproducible Benchmarking Tool](https://docs.rapids.ai/api/cuvs/nightly/cuvs_bench/)

### For Application Development  

cuVS can be used directly or through several database and library integrations to supercharge your applications and workflows with GPU acceleration.

- 

[Try the NVIDIA AI Blueprint for RAG](https://build.nvidia.com/nvidia/build-an-enterprise-rag-pipeline)

- 

[Read the Getting Started Guide](https://docs.rapids.ai/api/cuvs/nightly/getting_started/)

- 

[Explore Library and Database Integrations](https://docs.rapids.ai/api/cuvs/nightly/integrations/)

- 

[Learn About Vector Databases vs. Databases](https://docs.rapids.ai/api/cuvs/nightly/vector_databases_vs_vector_search/)

## 
## Learning Library



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/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/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/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://docs.nvidia.com/ai-enterprise/workflows-cybersecurity-ai/0.1.0/spear-phishing/technical-brief.html", "text" => "Learn more"} | Spear Phishing Detection Technical Brief | A technical brief on spear phishing details advanced techniques for detecting and mitigating this prevalent cybersecurity threat. | false | NeMo, Morpheus | 1\|spear phishing detection technical brief | 1791277771 | Documentation | Beginner |
| {"url" => "https://developer.nvidia.com/blog/enhancing-anomaly-detection-in-linux-audit-logs-with-ai/", "text" => "Learn more"} | Enhancing Anomaly Detection in Linux Audit Logs | Learn how to use NVIDIA Morpheus cybersecurity AI framework to identify threats in Linux audit logs. | false | Morpheus | 1\|enhancing anomaly detection in linux audit logs | 1791277771 | Blog | Beginner |
| {"url" => "https://developer.nvidia.com/blog/applying-generative-ai-for-cve-analysis-at-an-enterprise-scale/", "text" => "Learn more"} | Applying Generative AI for CVE Analysis | Learn how to use generative AI to accelerate security vulnerability analysis using AI agents and retrieval-augmented generation. | true | Morpheus | 0\|applying generative ai for cve analysis | 1791277771 | Blog | Beginner |
| {"url" => "https://github.com/nv-morpheus/Morpheus/tree/branch-24.03/docs/source/modules/examples/spear_phishing", "text" => "Learn more"} | Spear Phishing Detection | A GitHub repository that provides detailed examples and resources for implementing AI solutions to combat spear phishing attacks effectively. | false | NeMo, Morpheus | 1\|spear phishing detection | 1791277771 | GitHub | Beginner |
| {"url" => "https://www.nvidia.com/en-us/on-demand/session/gtc24-se62821/", "text" => "Learn more"} | Cybersecurity Developer Day | Learn how to use large language models, generative AI, retrieval-augmented generation, and machine learning techniques to dramatically strengthen your cybersecurity posture. | true | Morpheus | 0\|cybersecurity developer day | 1791277771 | Session | Beginner |
| {"url" => "https://docs.nvidia.com/morpheus/getting_started.html", "text" => "Learn more"} | Getting Started with Morpheus | This guide helps users implement AI driven cybersecurity solutions for real time threat detection across diverse IT environments. | false | Morpheus | 1\|getting started with morpheus | 1791277771 | Guide | Beginner |
| {"url" => "https://docs.nvidia.com/morpheus/examples.html", "text" => "Learn more"} | NVIDIA Morpheus | This guide showcases practical applications of AI for cybersecurity, demonstrating real world scenarios and implementation strategies. | false | Morpheus | 1\|nvidia morpheus | 1791277771 | Example | Beginner |
| {"url" => "https://www.youtube.com/watch?v=57dEPP67XrY", "text" => "Learn more"} | Improve Spear Phishing Detection with Generative AI | See how the NVIDIA Morpheus cybersecurity AI framework aids developers in building solutions to detect spear phisihing faster and more efficiently. | false | Morpheus | 1\|improve spear phishing detection with generative ai | 1791277771 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=DgZD3FV8Pz4", "text" => "Learn more"} | Revolutionizing Supercomputing with NVIDIA UFM Cyber AI | See how the NVIDIA UFM Cyber AI harnesses AI powered analytics to minimize downtime in InfiniBand data centers. | false | Morpheus | 1\|revolutionizing supercomputing with nvidia ufm cyber ai | 1791277771 | Video | Beginner |
| {"url" => "https://github.com/nv-morpheus/Morpheus/tree/branch-24.03/examples/developer_guide/2_1_real_world_phishing", "text" => "Learn more"} | Spear Phishing Detection | This GitHub repository includes practical examples and guidelines for implemeting AI solutions to tackle real world phishing threats effectively. | false | NeMo, Morpheus | 1\|spear phishing detection | 1791277771 | GitHub | Beginner |
| {"url" => "https://www.youtube.com/watch?v=UDChsxHx1wc", "text" => "Learn more"} | AI Based, Real Time Threat Detection at Scale | See how NVIDIA Morpheus makes it possible to scan all traffic in real time allowing you to detect and react to threats as they occur. | false | Morpheus | 1\|ai based, real time threat detection at scale | 1791277771 | Video | Beginner |
| {"url" => "https://docs.nvidia.com/morpheus/developer_guide/guides/6_digital_fingerprinting_reference.html", "text" => "Learn more"} | Digital Fingerprinting | A guide that provides a comprehensive reference for implementing digital fingerprinting techniques, essential for enahncing cybersecurity measures with advanced AI capabilities. | false | Morpheus | 1\|digital fingerprinting | 1791277771 | Guide | Beginner |
| {"url" => "https://docs.nvidia.com/morpheus/modules/index.html#digital-fingerprinting-modules", "text" => "Learn more"} | Digital Fingerprinting | Documentation that details specific AI modules designed for digital fingerprinting, bolstering cybersecurity capabilities with advanced detection and repsonse techniques. | false | Morpheus | 1\|digital fingerprinting | 1791277771 | Modules | Intermediate |
| {"url" => "https://docs.nvidia.com/morpheus/modules/index.html#spear-phishing-modules", "text" => "Learn more"} | Spear Phishing Detection | Modules documentation that outlines specific AI modules for detecting and mitigating spear phishing attacks, enhancing cybersecurity defenses. | false | NeMo, Morpheus | 1\|spear phishing detection | 1791277771 | Modules | Intermediate |
| {"url" => "https://docs.nvidia.com/morpheus/developer_guide/guides/5_digital_fingerprinting.html", "text" => "Learn more"} | Digital Fingerprinting | Get insights and instructions on implementing digital fingerprinting for robust cybersecurity, leveraging advanced AI techniques. | false | Morpheus | 1\|digital fingerprinting | 1791277771 | Guide | Beginner |
| {"url" => "https://github.com/nv-morpheus/Morpheus/tree/branch-24.03/examples/digital_fingerprinting", "text" => "Learn more"} | Digital Fingerprinting | Get practical examples and resources for implementing digital fingerprinting techniques to enhane cybersecurity measures. | false | Morpheus | 1\|digital fingerprinting | 1791277771 | GitHub | Beginner |
| {"url" => "https://www.youtube.com/watch?v=8rEPkHRvDq0", "text" => "Learn more"} | Digital Fingerprinting | Explore NVIDIA's demo showcasing digital fingerprinting technology, illustrating its role in enhancing cybersecurity measures with advanced AI capabilities. | false | Morpheus | 1\|digital fingerprinting | 1791277771 | Video | Beginner |
| {"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/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://www.nvidia.com/en-us/on-demand/session/gtc24-s62173/", "text" => "Learn more"} | How to Apply Generative AI to Improve Cybersecurity | Explore how generative AI can be applied to security to reduce the time to detect cyber threats, address data gaps, and enrich models by creating synthetic training data. | true | Morpheus | 0\|how to apply generative ai to improve cybersecurity | 1791277771 | Session | Beginner |
| {"url" => "https://www.youtube.com/watch?v=By5FALKZUoQ", "text" => "Learn more"} | Visualizing Cybersecurity Threats Using Big Data Analytics | Learn how Joshua Patterson uses NVIDIA GPUs to detect security threats by analyzing anomalies in large scale graphs. | false | Morpheus | 1\|visualizing cybersecurity threats using big data analytics | 1791277771 | Video | Beginner |
| {"url" => "https://docs.nvidia.com/ai-enterprise/workflows-cybersecurity-ai/0.1.0/digital-fingerprinting/technical-brief.html", "text" => "Learn more"} | Digital Fingerprinting Technical Brief | Explore innovative techniques for enhancing threat detection and repsonse capabilties. | false | Morpheus | 1\|digital fingerprinting technical brief | 1791278003 | Documentation | Beginner |
| {"url" => "https://www.youtube.com/watch?v=ZA9Ityyk4pg", "text" => "Learn more"} | Hunting Cyber Hackers with Machine Learning | Learn how Leo Meyerovich, CEO of Graphistry, uses NVIDIA GPUs to protect some of the largest companies and organizations in the world by visually alerting them of hackers or outages. | false | Morpheus | 1\|hunting cyber hackers with machine learning | 1791277771 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=xXXrX1CcuBw", "text" => "Learn more"} | Introduction to ConnectX Network Interface Cards | Explore Ethernet smartNICs which boast high data transfer speeds, low latency, advanced processor offloading measures and security features. | false | Morpheus | 1\|introduction to connectx network interface cards | 1791277771 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=UT09801gmec", "text" => "Learn more"} | Boost Data Center Management and Security | See how NVIDIA UFM Cyber AI platform revolutionizes InfiniBand data center networking management. | false | Morpheus | 1\|boost data center management and security | 1791277771 | Video | Beginner |
| {"url" => "https://www.youtube.com/watch?v=UnaPTrbkcrY", "text" => "Learn more"} | What is Digital Fingerprinting? | Learn more about digital fingerprinting and the value it can bring. | false | Morpheus | 1\|what is digital fingerprinting? | 1791277771 | Video | 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://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/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/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/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/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://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://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+C-DS-03+V1", "text" => "Learn more"} | Building AI Based Cybersecurity Pipelines | Explore NVIDIA's course on deep learning for cybersecurity and master techniques to defend against cyber threats using advanced AI algorithms. | false | Morpheus | 1\|building ai based cybersecurity pipelines | 1791278003 | Learning Path | Beginner |
| {"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_cuvs.json)



* * *

## Ecosystem

[
 ![NVIDIA cuVS Ecosystem Partner - Datastax](https://developer.download.nvidia.com/images/cuvs/logo-datastax.svg)
](https://www.datastax.com/blog/datastax-ai-paas-integrated-with-nvidia-nemo-retriever)

[
 ![NVIDIA cuVS Ecosystem Partner - Elastic](https://developer.download.nvidia.com/images/cuvs/logo-elastic.svg)
](https://www.nvidia.com/gtc/session-catalog/?tab.catalogallsessionstab=16566177511100015Kus&search=lucene#/session/1725488451726001Mz27)

[
 ![NVIDIA cuVS Ecosystem Partner -](https://developer.download.nvidia.com/images/cuvs/logo-faiss.svg)
](https://docs.rapids.ai/api/cuvs/nightly/integrations/faiss/)

[
 ![NVIDIA cuVS Ecosystem Partner - Kinetica](https://developer.download.nvidia.com/images/cuvs/logo-kinetica.svg)
](https://docs.rapids.ai/api/cuvs/nightly/integrations/kinetica/)

[
 ![NVIDIA cuVS Ecosystem Partner - Lucene](https://developer.download.nvidia.com/images/cuvs/logo-apache-lucene.svg)
](https://docs.rapids.ai/api/cuvs/nightly/integrations/lucene/)

[
 ![NVIDIA cuVS Ecosystem Partner - Solr](https://developer.download.nvidia.com/images/cuvs/logo-solr.svg)
](https://www.nvidia.com/gtc/session-catalog/?tab.catalogallsessionstab=16566177511100015Kus&search=lucene#/session/1725488451726001Mz27)

[
 ![NVIDIA cuVS Ecosystem Partner - Milvus](https://developer.download.nvidia.com/images/cuvs/logo-milvus.svg)
](https://docs.rapids.ai/api/cuvs/nightly/integrations/milvus/)

[
 ![NVIDIA cuVS Ecosystem Partner - OpenSearch](https://developer.download.nvidia.com/images/cuvs/logo-open-search.svg)
](https://opensearch.org/blog/GPU-Accelerated-Vector-Search-OpenSearch-New-Frontier/)

[
 ![NVIDIA cuVS Ecosystem Partner - Weaviate](https://developer.download.nvidia.com/images/cuvs/logo-weaviate.svg)
](https://www.nvidia.com/gtc/session-catalog/?tab.catalogallsessionstab=16566177511100015Kus&search=weaviate#/session/1725741930792001U8IR)

[

](https://docs.rapids.ai/api/cuvs/nightly/integrations/lucene/)

* * *

## More Developer Resources

 ![NVIDIA Developer Newsletter](https://developer.download.nvidia.com/icons/m48-email-settings.svg)

### Sign Up for Developer Newsletter  

 ![NVIDIA Training and Certification](https://developer.download.nvidia.com/icons/m48-certification-ribbon-2.svg)

### Get Training and Certification  

 ![NVIDIA Developer Program](https://developer.download.nvidia.com/images/cuvs/developer-1.svg)

### Join the NVIDIA Developer Program  

### Get Started With NVIDIA cuVS Today

[Download Now](https://github.com/rapidsai/cuvs)