https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/Recent content in NVIDIA Integration onHugo -- gohugo.ioSun, 11 Dec 2022 19:37:55 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/about-nvidia/Sun, 11 Dec 2022 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/about-nvidia/Integrate your model with NVIDIA services like NVIDIA NIM (NVIDIA Inference Microservices) or NVIDIA Triton Inference Server. Add connections for these services and leverage AI models in ETL applications with the NVIDIA NIM and Triton processors to generate inferences on your prediction data. These services allow you to deploy, manage, and scale AI models, as well as integrate them into various data tasks such as classification, information extraction, text summarization, and sentiment analysis.https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-home/Sun, 11 Dec 2022 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-home/Manage and explore NVIDIA models by creating connections for NVIDIA services in Gathr. To access this page, navigate through the Applications > Machine Learning > NVIDIA Tab. Note: For models to display here, ensure at least one NVIDIA NIM or NVIDIA Triton connection has been created in Gathr. Upon selecting a connection, AI models associated with it will display. You can leverage these models within Gathr’s intuitive interface. The actions available on the NVIDIA Models listing page are explained below:https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-nim-connection/Sun, 11 Dec 2022 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-nim-connection/Authenticate to NVIDIA NIM AI and configure any necessary connection properties in the NVIDIA NIM connection. Each connection property available in the NVIDIA NIM connection configuration is explained below. Connection Name # The name of the connection to be created should be provided. This is the name that will display on the list of available connections. Scope # Define the connection scope to customize their accessibility. Organization Accessible to organization users across all Gathr projects for usage in applications.https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-nim-processor/Sun, 11 Dec 2022 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-nim-processor/NVIDIA NIM (NVIDIA Inference Microservices) is a suite of optimized, containerized AI inference endpoints designed to simplify the deployment and scaling of powerful AI models. Built on top of NVIDIA’s cutting-edge inference stack, NIM enables developers to integrate pre-trained generative AI models into applications quickly and efficiently, with minimal infrastructure overhead. Configure the processor parameters as explained below. Model Selection # Under the Model Selection tab of the NVIDIA NIM processor, provide the below details.https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-triton-connection/Sun, 11 Dec 2022 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-triton-connection/NVIDIA Triton Integration Prerequisites # NVIDIA Triton model should be hosted in user’s server. Obtain the hosted model’s connection URL. Ensure the model services are up and running before using them for inferences within Gathr. To access the Connections page, simply navigate through the Connections (main-menu) > Create Connection. To set up a connection with NVIDIA Triton tracking server from Gathr, you need to configure these fields. Component Type # Select NVIDIA Triton as the ‘Component Type’ to create the connection for NVIDIA Triton.https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-triton-processor/Sun, 11 Dec 2022 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/gen-ai-in-gathr/nvidia-integration/nvidia-triton-processor/Triton Inference Server is NVIDIA’s open-source platform for deploying and managing AI models at scale. It supports popular frameworks like TensorFlow, PyTorch, ONNX etc. offering flexibility in model integration. With support for both CPU and GPU, Triton ensures optimized, high-performance inference. Ideal for production workloads, it enables efficient, low-latency AI serving across diverse environments. Configure the processor parameters as explained below. Model Selection # Provide the details of the model to be used.