This project applies the core knowledge from the LLMOps module, including the design and implementation of the API Layer, Inference Layer, Observability Layer, Cache Layer, Guardrails Layer, Routing Layer, and the Data Ingestion Pipeline.

💂🏼 Build your Documentation AI with Nemo Guardrails

LLM tutorial materials include but not limited to NVIDIA NeMo, TensorRT-LLM, Triton Inference Server, and NeMo Guardrails.

Responsible AI Masterclass (June 2024 Run)

RAG with Redis. Parallel implementations with/without guardrails.

A simple Retrieval-Augmented Generation (RAG) pipeline for answering questions based on website content. This project combines retrieval of relevant website information with generative models to deliver contextually accurate answers.

This bootcamp is designed to give NLP researchers an end-to-end overview on the fundamentals of NVIDIA NeMo framework, complete solution for building large language models. It will also have hands-on exercises complimented by tutorials, code snippets, and presentations to help researchers kick-start with NeMo LLM Service and Guardrails.

GitDoc is your ultimate GitHub Documentation Explorer! It's your trusty sidekick for navigating through the vast world of open-source projects, making code exploration and documentation retrieval a breeze. 🚀

Dive into the world of LLM Guardrails using tools like NVIDIA’s NeMo Guardrails. Discover the mechanisms that ensure applications produce reliable, robust, safe, and ethical outputs, and understand their crucial role in LLMs

Generative AI RAG Chatbot for Electricity and Gas Company

AI Application Monitoring and Evaluation Service

Short tutorial on using NVIDIA NeMo Guardrails

CareBear Therapy Chat is an AI-powered conversational companion designed to provide comforting, empathetic support while ensuring safe interactions. Fine-tuned with QLoRA for efficient custom training and protected by guardrails for real-time safety checks, the chatbot delivers soothing, context-aware responses in a friendly chat interface.

NVIDIA NIM based RAG application deployed locally(LLM ,Embedding model and reranking model)which is optimized to use GPU cluster

An end-to-end AI pipeline that scrapes LinkedIn profile and post data to predict 16-personality (MBTI) types using a RAG-enhanced LLM fine-tuned with LoRA. It automates data collection, preprocessing, storage in PostgreSQL, and personality inference from real-world behavioral and linguistic patterns.