A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.
A demo app showcasing Vector Search using Azure AI Search, Azure OpenAI for text embeddings, and Azure AI Vision for image embeddings.
Quick start. Index multiple documents in a repository using HuggingFace embeddings. Save them in Chroma and / or FAISS for recall. Choose OpenAI or Azure OpenAI APIs to get answers to your questions - Q&A with OpenAI and Azure OpenAI.
Official GitHub repo for your Teams copilot Timon (or Tima)
We've moved beyond the limitations of traditional text length-based segmentation, opting for a smarter approach—semantic segmentation. This innovative method ensures unparalleled precision in identifying both overarching themes and nuanced details within your content.
Smart Python OpenAI Load Balancer using priority endpoints and request retries. | Python package at link below:
Providing high-quality translations for docx while maintaining document formattin
This demo repository demonstrates how to create ChatGPT infused chatbot with Azure OpenAI Service (AOAI)'s GPT-3.5-Turbo model.
Calculate exact USD cost of each OpenAI API call — no guesswork.
Companion Repository for: Deploying Azure OpenAI and Building a Custom Science Article Recommender App with ChatGPT
Create 3D celestial models with Azure OpenAI, Python, and Blender! AzureOpenAI-SpaceGen-Py leverages LLM-powered prompts to generate Python scripts, utilizing Azure Compute for intensive rendering tasks. Explore space-themed modeling while learning Python, Azure Bicep, and Blender.
AI chat client supporting OpenAI, Google Gemini, and Claude. This is a version without ZundaGPT2's speech synthesis. / AIチャットクライアント。OpenAI、Google Gemini、Claudeに対応しているのだ。ZundaGPT2の読み上げなし版なのだ。
Generative AI Accelerators
Benchmarking the performance of proprietary vs open-source LLMs in industrial QnA tasks using various RAG-based implementations and evaluation metrics.
Implement a Retrieval Augmented Generation (RAG) with a user interface for performing contextual comparisons between two uploaded documents. The system leverages RAG to extract relevant segments from each document, compare them, and provide meaningful insights on differences and relationships between the content of the two documents.
Add a description, image, and links to the azureopenai topic page so that developers can more easily learn about it.
To associate your repository with the azureopenai topic, visit your repo's landing page and select "manage topics."