Loading repository data…
Loading repository data…
HPInc / repository
📁 This repository hosts a growing collection of AI blueprint projects that run end-to-end using Jupyter notebooks, MLflow deployments, and Streamlit web apps.🛠️ All projects are built using HP AI Studio with ❤️ If you find this useful, please don’t forget to star the repository ⭐ and support our work 🚀
Get started instantly with HP AI Studio — run over 20 fully local AI Blueprint projects with one click in less than 5 minutes:
This repository hosts a growing collection of AI blueprint projects that run end-to-end using Jupyter notebooks, MLflow deployments, and Streamlit web apps. Each blueprint is designed to be plug-and-play, giving you ready-to-use solutions across key AI domains like data science, machine learning, deep learning, and generative AI. All projects are built to work seamlessly with HP AI Studio.
These blueprints make use of local, open-source models including:
In addition, some examples use hosted models from Hugging Face for added flexibility.
We’re actively expanding this collection. If you have ideas or want to suggest a blueprint for HP AI Studio, feel free to open an issue. We’d love to hear from you.
To run any of these projects quickly and effortlessly, you can download HP AI Studio for free.
# Root Directory
├── data-science/ # Projects related to classical machine learning and statistical analysis
│ ├── classification-with-svm/ # SVM-based classification implementation
│ └── data-analysis-with-var/ # Vector AutoRegression analysis workflow
│
├── deep-learning/ # Deep learning applications using popular frameworks
│ ├── classification-with-keras/ # Image classification using Keras
│ ├── question-answering-with-bert/ # QA system built on top of BERT model
│ ├── recommendation-system-with-tensorflow/ # TensorFlow-based recommendation engine
│ ├── spam-detection-with-nlp/ # NLP-driven spam classifier
│ ├── super-resolution-with-fsrcnn/ # Image enhancement using FSRCNN
│ └── text-generation-with-rnn/ # RNN-based generative model for text
│
├── generative-ai/ # Generative AI applications across text, code, and image
│ ├── automated-evaluation-with-structured-outputs/ # Eval pipeline for structured generation
│ ├── code-generation-with-langchain/ # Code synthesis using LangChain
│ ├── fine-tuning-with-orpo/ # ORPO-based fine-tuning procedure
│ ├── image-generation-with-stablediffusion/ # StableDiffusion-powered image generation
│ ├── text-generation-with-langchain/ # Text generation leveraging LangChain stack
│ ├── text-summarization-with-langchain/ # Summarization pipeline using LangChain
│ └── vanilla-rag-with-langchain/ # Basic Retrieval-Augmented Generation with LangChain
│
├── ngc-integration/ # Projects leveraging NVIDIA GPU Cloud and libraries
│ ├── agentic-rag-with-tensorrtllm/ # RAG system using TensorRT-LLM and agentic planning
│ ├── audio-translation-with-nemo/ # Speech translation with NVIDIA NeMo
│ ├── data-analysis-with-cudf/ # RAPIDS cuDF-based data manipulation
│ ├── data-visualization-with-cudf/ # Visualizations using GPU-accelerated tools
│ └── vacation-recommendation-with-bert/ # Recommendation app using BERT embeddings
The blueprint projects in this folder demonstrate how to build data science applications with HP AI Studio.
We provide 2 blueprint projects, each designed for quick and easy use to help you get started efficiently.
This project is a simple classification experiment focused on predicting species of iris flowers.
It runs on the Data Science Workspace, demonstrating basic supervised learning techniques for multi-class classification tasks.
This project explores a regression experiment using mobility data collected during the COVID-19 pandemic.
It highlights how city-level movement patterns changed during the crisis. The experiment runs on the Data Science Workspace.
The blueprint projects in this folder demonstrate how to build deep learning applications with HP AI Studio.
We provide 6 blueprint projects, each designed for quick and easy use to help you get started efficiently.
This project performs basic image classification using the TensorFlow framework.
It trains a model to classify handwritten digits from the MNIST dataset and runs on the Deep Learning Workspace.
This project demonstrates a simple BERT Question Answering (QA) experiment. It provides code to train a BERT-based model, as well as instructions to load a pretrained model from Hugging Face.
The model is deployed using MLflow to expose an inference service capable of answering questions based on input text.
This project builds a simple recommender system for movies using TensorFlow.
It trains on user-item interaction data to predict movie preferences and runs on the Deep Learning Workspace.
This project implements a text classification system to detect spam messages.
It uses deep learning techniques and requires the Deep Learning Workspace for training and inference.
This project showcases a Computer Vision experiment that applies convolutional neural networks for image super-resolution — enhancing the quality and resolution of input images.
This project illustrates how to build a simple character-by-character text generation model.
It trains on a dataset containing Shakespeare's texts, demonstrating the fundamentals of text generation by predicting one character at a time.
The blueprint projects in this folder demonstrate how to build generative AI applications with HP AI Studio.
We provide 7 blueprint projects, each designed for quick and easy use to help you get started efficiently.
Automated Evaluation with Structured Outputs turns a local Meta-Llama-3 model into an MLflow-served scorer that rates any batch of texts (e.g., project abstracts) against arbitrary rubric criteria.
llama.cpp (no data leaves your machine)/invocations endpointThis notebook performs automatic code explanation by extracting code snippets from Jupyter notebooks and generating natural language descriptions using LLMs. It supports contextual enrichment based on adjacent markdown cells, enables configurable prompt templating, and integrates with PromptQuality and Galileo for evaluation and tracking. The pipeline is modular, supports local or hosted model inference, and is compatible with LLaMA, Mistral, and Hugging Face-based models. It also includes GitHub notebook crawling, metadata structuring, and vector store integration for downstream tasks like RAG and semantic search.
This project demonstrates a full-stack LLM fine-tuning experiment using ORPO (Open-Source Reinforcement Pretraining Objective) to align a base language model with human preference data. It leverages the Z by HP AI Studio Local GenAI environment, and uses models such as LLaMA 3, Gemma 1B, and Mistral 7B as foundations.
We incorporate:
Galileo PromptQuality for evaluating model responses with human-like scorers (e.g., context adherence) TensorBoard for human feedback visualization before fine-tuning A flexible model selector and inference runner architecture A comparative setup to benchmark base vs fine-tuned models on the same prompts
This notebook performs image generation inference using the Stable Diffusion architecture, with support for both standard and DreamBooth fine-tuned models. It loads configuration and secrets from YAML files, enables local or deployed inference execution, and calculates custom image quality metrics, such as entropy and complexity. The pipeline is modular, supports Hugging Face model loading, and integrates with PromptQuality for evaluation and tracking.
This notebook implements a full Retrieval-Augmented Generation (RAG) pipeline for automatically generating a scientific presentation script. It integrates paper retrieval from arXiv, text extraction and chunking, embedding generation with HuggingFace, vector storage with ChromaDB, and context-aware generation using LLMs. It also integrates Galileo Prompt Quality for evaluation and logging, and supports multi-source model loading, including local Llama.cpp, HuggingFace-hosted, and HuggingFace-cloud models like Mistral or DeepSeek.
This project demonstrates how to build a semantic chunking and summarization pipeline for texts using LangChain, Sentence Transformers, and Galileo for model evaluation, protection, and observability. It leverages the Z by HP AI Studio Local GenAI image and the Meta Llama 3.1 model with 8B parameters to generate concise and contextually accurate summaries from text data.
This project is an AI-powered vanilla RAG (Retrieval-Augmented Generation) chatbot built using LangChain and Galileo for model evaluation, protection, and observability. It leverages the Z by HP AI Studio Local GenAI image and the Meta Llama 3.1 model with 8B parameters to generate contextual and document-grounded answers to user queries about Z by HP AI Studio.
The blueprint projects in this folder demonstrate how to integrate NVIDIA NGC (NVIDIA GPU Cloud) resources with HP AI Studio.
We provide 5 blueprint projects, each designed for quick and easy use to help you get started efficiently.
This project contains a single integrated pipeline—Agentic RAG for AI Studio with TRT-LLM and LangGraph—that implements a Retrieval-Augmented Generation (RAG) workflow using:
TensorRT-backed Llama-3.1-Nano (TRT-LLM): for fast, GPU-accelerated inference. LangGraph: to orchestrate an agentic, multi-step decision flow (relevance check, memory lookup, query rewr