Deploy and Manage NVIDIA GPU resources in Kubernetes.

gpu-operator

NVIDIA Network Operator Helm Chart provides an easy way to install, configure and manage the lifecycle of NVIDIA Mellanox network operator.

network-operator

mongodb

ds-sdr-envoy

redis

tokkio-ingress-mgr

chat-controller-sdr-envoy

tokkio-ui-server

occupancy-alerts-api

occupancy-alerts

redis-timeseries

renderer-sdr-envoy

The UMIM Action Server for Tokkio together with ACE Agent Chat Controller provide UMIM  compatibility for Tokkio.

tokkio-umim-action-server

anim-graph-sdr-envoy

ds-visionai

Expose NVIDIA GPUs as Resources in Kubernetes

nvidia-device-plugin

riva-api

tao-toolkit-api

tokkio-cart-manager

tokkio-menu-api

A Helm chart for deploying the infrastructure of the Morpheus AI Engine. It includes the Triton Inference Server, Kafka, and Zookeeper.

morpheus-ai-engine

ucs-tokkio-audio-video-app

Helm Chart to deploy NVIDIA Transfer Learning APIs.

nvtl-api

tritoninferenceserver

This example showcases multi modal usecase in a RAG pipeline. It can understand any kind of images in PDF or .pptx (like graphs and plots) alongside text and tables.

rag-app-multimodal-chatbot

This example showcases a RAG workflow with multi-turn conversation capabilities.

rag-app-multiturn-chatbot

Sample RAG application which can handle question-answering from tabular data stored in CSV format.

rag-app-structured-data-chatbot

A helm chart demonstrating a basic RAG pipeline built using langchain leveraging Nvidia NIM LLM's and Retrievers deployed on-prem.