Stars
This sample demonstrates how to use GPT-4o with Vision to extract structured JSON data from PDF documents, such as invoices, using the Azure OpenAI Service.
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 ingest…
This repository contains demos I made with the Transformers library by HuggingFace.
A simple OCR labeling tool built on Flask and PyQt5
A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes mos…
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
Start building and deploying Python packages and Docker images for MLOps tasks.
A copilot sample that uses python to ground the copilot responses in company data.
Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment"
This repository contains step by step instructions on how to finetune Microsoft's Phi-2 model with your own data.
🪄 Auto-generate Streamlit UI from Pydantic Models and Dataclasses.
Pure static HTML/JS Streamlit component toggle button implementation
Improve your Elasticsearch, OpenSearch, Solr, Vectara, Algolia and Custom Search search quality.
Promptflow experimentation framework
Adding guardrails to large language models.
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
A guidance language for controlling large language models.
Snips Python library to extract meaning from text
A benchmark of different approaches on the task of Intent Classification
An exploration to see if LLMs can self reason using prompts and under what conditions.
A tool for gender bias identification in text. Part of Microsoft's Responsible AI toolbox.
Evaluation of language models on mono- or multilingual tasks.