Easily automate the translation of your documentation into multiple languages, powered by Azure AI Services
This repository offers a Python framework for a retrieval-augmented generation (RAG) pipeline using text and images from MHTML documents, leveraging Azure AI and OpenAI services. It includes ingestion and enrichment flows, a RAG with Vision pipeline, and evaluation tools.
FancyAlt is a full-stack AI-powered image analysis API built with Node.js, Express.js, Azure AI Vision, and OpenAI. It supports image uploads and public URLs, providing accessible alt-text, content moderation, and creative storytelling.
A secure .NET 8 Azure Function intermediary that processes grocery images via Azure AI Vision for the PantryChef Android app.
Project that will use the AZURE AI services to Analize and detect objects in an image
Passo a passo de experimento utilizando Vision Studio/ Azure AI Vision para extrair texto de imagens sem a utilização de código. Realizado como desafio de projeto no Bootcamp Microsoft Azure AI Fundamentals da Dio.me
App for performing simple (derivation) operations on mathematical expressions by using OCR & Newton API. Distributed .NET apps communicate via Dapr that is run as sidecar for each of the components (as shown on the graph itself). Solution is orchestrated via Aspire.
Project to showcase the usage of Azure Vision AI service
C# implementation of mslearn-ai-vision
Add a description, image, and links to the azure-ai-vision topic page so that developers can more easily learn about it.
To associate your repository with the azure-ai-vision topic, visit your repo's landing page and select "manage topics."