# Network Copilot - Enable GenAI in your Networks with Aviz

May 14, 2024

## The Future of Networks Deployments

The rise of generative AI frameworks based on large language models is transforming the dynamics of human-computer interactions within data-driven applications. Networking is undergoing a similar transformation, given the evolution of data centers to meet the demands of advancing technology and the increased reliance on AI-driven computing. Enterprise and cloud data centers generate extensive operational and application data, offering significant visibility. Aviz envisions leveraging the capabilities of Large Language Models (LLMs) to distill this vast amount of data from Edge, Data Center, and Cloud Network Infrastructure into actionable business-driven summaries.

## Network Copilot - Enable GenAI in your Networks with Aviz

Aviz Network Copilot stands as the industry's pioneering vendor-agnostic Generative AI Solution, harnessing the capabilities of open-source Large Language Models (LLMs) to efficiently process, correlate, and simplify the intricate demands of networks. It is tailored for decision-makers, network administrators, and data center operators. Network Copilot is driven by our ONES multi-vendor, multi-NOS data mobility platform, serving as the backend infrastructure for data ingestion, aggregation, and enrichment across diverse datasets, including Network State, Performance, and Application data.

## Benefits

**Start as a Leader**  
GenAI is future and one of the most important KPI for Executives. Get your KPI with Network CoPilot.

**Train Your Teams**  
Empower your teams with a Data and AI-centric approach through Network Copilot. Facilitate precise and efficient training, allowing them to excel in responding to Generative queries.

**Long Term ROI**  
Copilot is built on community-based LLMs, ensuring there is no vendor lock-in and designed for long-term return on investment (ROI).

**In-House Control**  
Seize control of your internal data instead of relinquishing it to vertically integrated systems that hinder in-house innovations.

## Use Cases

| Use Case | Description | Availability |
| --- | --- | --- |
| **Network Compliance** | Providing insights and recommendations for compliance management tasks, the Copilot ensures that network devices align with business expectations. This covers aspects such as security compliance, resource utilization, and end-of-life hardware inventory. Administrators are promptly alerted to any deviations from best practices. | Yes |
| **Forecasting & Capacity Planning** | Support the network architecture team in strategically forecasting and overseeing the resources needed to meet current and future demands on the network infrastructure. This ensures the data center network operates optimally, delivering performance, scalability, and efficiency. | Yes |
| **On Demand Business Intelligence Analytics** | Unlike traditional applications that come with pre-packaged analytics use cases, Network Copilot delivers ad-hoc business intelligence analytics that suit the spectrum of end users ranging from network practitioners on one hand to decision makers on the other hand. | Yes |
| **Insights on Network State Anomalies** | Leveraging its generative AI capabilities, the copilot excels in identifying anomalous behavior within the network. This includes providing answers on unusual traffic spikes, deviations from normal usage, or potential security breaches. | \* - Coming soon |
| **Troubleshooting & Optimization Assistance** | Help engineering teams optimize troubleshooting with full visibility into network configurations and operations, identifying issues and suggesting informed corrective actions from deployment insights. | \* - Coming soon |

## Capabilities

- Vendor-agnostic data mobility platform (ONES) for ingestion and normalization
- NOS agnostic data collection using standard interfaces (SNMP, streaming, sFlow, etc)
- Dataset comprising network state (inventory, health utilization) & Application L4-L7
- Foundation model (7B) trained and fine-tuned
- Embedding model using RAG
- Simplified Prompt-based UI
- Save and Export customer-driven questions for improvised training
- Import Customer-defined Business Expectation
- Ready for On-prem and Cloud Deployments

## Deployment Specifications

| Deployment | Specification |
| --- | --- |
| **On-Prem** | **Software:** Ubuntu 22.04, Docker, NVIDIA CUDA 12 & Toolkit **Inference on GPU:** Min Recommended 24GB RAM **Supported Models:** RTX 3090 | 24 GB, RTX 4090 | 24 GB, A4000 | 16 GB, A5000 | 24 GB, A6000 | 48 GB, V100 | 16 GB **Inference on CPU:** Min Recommended RAM: 128 GB DDR5 **Supported Models:** 4th Gen Intel Xeon Processors with 32 cores or above (Recommended), Intel Core i9-13900K, Ryzen 9 5900x, AMD Ryzen Threadripper 3990X, Intel 3435x |
| **Cloud** | **Instances GPU for Inference:** Nvidia T4 16 GB, A10 GPU 24 GB |

## Supported Networking Platforms