The AI Kit gives data scientists, AI developers, and researchers familiar with Python* tools and frameworks to accelerate end-to-end data science and analytics pipelines on Intel® architecture. The components are built using oneAPI libraries for low-level compute optimizations. This toolkit maximizes performance from preprocessing through machine learning and provides interoperability for efficient model development. The workshop covers the following topics:

• Introduction to the new  Intel® Developer cloud
• Access to Ponte Vecchio instances

• Demo with Llm's using Langchain, Open AI
• Stable Diffusion Demo

 Key Takeaways:

• • Deliver high-performance, deep learning training on Intel® XPUs and integrate fast inference into your AI development workflow with Intel®-optimized, deep learning frameworks for TensorFlow* and PyTorch*, pre-trained models, and low-precision tools.

• Achieve drop-in acceleration for data preprocessing and machine learning workflows with compute-intensive Python packages, Modin*, scikit-learn*, and XGBoost.
• Gain direct access to analytics and AI optimizations from Intel® to ensure that your software works together seamlessly

• Intel® Developer Cloud is a free and ready-to-use sandbox environment for rapid prototyping. For developers, it provides access to the latest Intel® AI hardware and software offerings.
• Concepts and hands-on with Llm's using Langchain within Intel Developer Cloud.
• Exploring Hugging Face with LLMs and Langchain
• Stable diffusion on Intel XPUs and CPU.

Pre-Requisites:

• • Computer/Laptop with the latest Google Chrome/Mozilla Firefox browser which can access the open internet.

• Should have registered for accessing the Intel® Developer cloud for oneAPI - https://scheduler.cloud.intel.com/

• • Should have created an Open AI key using https://platform.openai.com/

• Hugging Face API key https://huggingface.co/docs/api-inference/quicktour

• Basic knowledge of ML concepts, Python programming and Linux bash commands would be nice to have