Language models, automation, machine learning, text, images and audio: explanations, guides and practical tips.
Explore approaches, choose models and evaluate results. This section covers context, reliable outputs, automation and different data types. Search and RAG are one direction within the section. Time series and forecasting belong to mathematics and models.
A guide to setting up multimodal search in Azure AI Search using vectorization of text and images. Describes steps for creating an index, selecting models (e.g., CLIP), methods for generating embeddings, and executing hybrid queries to improve relevance.
Explore the principles of semantic search, its reliance on embeddings, and the reasons why text that appears similar might not provide the desired answer. Learn about vector search, hybrid search, and their applications in information retrieval.
Learn how to effectively evaluate the precision and recall of AI models, especially when working with small question datasets. This guide covers the concepts, calculation methods, and practical considerations using scikit-learn.
Step-by-step guide to creating an index, generating embeddings, and executing hybrid queries that combine full-text and vector search using Azure AI Search.
This article explains how to choose effective chunk boundaries and overlap in retrieval-augmented generation (RAG) systems, comparing fixed-size and document-aware strategies. Using a hypothetical support note example, it demonstrates the risks of splitting across semantic units and shows how metadata and overlap can preserve context. The guidance is based on Microsoft Azure documentation for chunking in vector search and RAG workflows.
A citation identifier only proves a source was retrieved, not that it supports the claim. This article shows how to decompose answers, locate supporting passages, and separate retrieval checks from groundedness checks using a hypothetical policy example.
Compare three similarity calculations on small vectors and see when normalization changes the ranking.
A technical guide explaining why syntactically correct JSON from Large Language Models (LLMs) is insufficient for production systems and how JSON Schema provides the necessary structural and type guarantees.
How retrieval connects a language model to documents, and why a citation is not a guarantee.