This post discusses how to create vector embeddings for documents that are too large to fit into a single embedding vector by chunking data using text splitting. This technique is commonly used when designing Generative AI solutions using Large Language Models.
This post explains how to use Fabric Semantic Link to leverage Power BI as a data source for Machine Learning model development in Fabric Data Science.
This post walks through the creation of a machine learning Jupyter notebook using IBM Watson Studio. The post illustrates the process step-by-step and includes an embedded video demo.
This post demonstrates how to use Retrieval Augmented Generation (RAG) to query OpenAI's Large Language Model (LLM) using a Vector database. This technique leverages the language understanding and summarization capabilities of Generative AI while introducing semantic understanding of our own data.
This post walks through the process of moving desktop-based Anaconda/Jupyter machine learning notebooks to Microsoft Fabric Synapse Data Science. The post illustrates the process and includes an embedded video demo.
This post discusses how Microsoft Azure OpenAI service employed a Retrieval Augmented Generation (RAG) technique called Use Your Data to enable Generative AI queries to incorporate private data. A full walk-through solution is included in text and video.
When coloring series on in a Python Matplotlib plot, you can use color names. This post shows each possible name and a visual example of each corresponding color.
This video is a end-to-end tutorial showing how to deploy a Machine Learning model to a REST endpoint callable from another application via the web.
This post builds on the concepts in a previous post by exporting an Azure AI Custom Vision model to run within an iOS application.
