Skip to content

hyogrin/Azure_OpenAI_samples

Repository files navigation

Azure_OpenAI_samples

๐Ÿ”ฅNew Feature (5-Sep-2025)

GPT-5 Basic

  • This hands-on notebook is designed to rapidly validate the fundamental capabilities of GPT-5 in Azure OpenAI while providing direct comparisons with GPT-4x models. It supports streamlined testing of the Chat Completions API, structured output, function calling, and the Responses API (covering Function Calling, Code, Vision, and Background Tasks) for both GPT-5 series and GPT-4x models. s. Go to notebook

    ์ด ํ•ธ์ฆˆ์˜จ ๋…ธํŠธ๋ถ์€ Azure OpenAI์—์„œ GPT-5์˜ ๊ธฐ๋ณธ ๊ธฐ๋Šฅ์„ ๋น ๋ฅด๊ฒŒ ๊ฒ€์ฆํ•˜๊ณ  ๊ธฐ์กด gpt-4x๋ชจ๋ธ๊ณผ ๋น„๊ตํ•˜๋Š” ๋…ธํŠธ๋ถ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. Chat Completions API, structured output, function calling, Responses API (Function Calling, Code, Vision, Background Task ๋“ฑ) ์‚ฌ์šฉ ์‹œ gpt-5 series ๋ชจ๋ธ๊ณผ gpt-4x๋ชจ๋ธ์„ ์ง์ ‘ ๋น„๊ตํ•ด์•ผํ•˜๋Š” ๊ฒฝ์šฐ ์†์‰ฝ๊ฒŒ ํ…Œ์ŠคํŠธ ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค. Go to notebook

๐Ÿ”ฅNew Feature (29-Apr-2025)

AI Foundry Trace

  • This hands-on demonstrates how to configure trace in AI foundry. It make you understand how to set up the right instruments for Azure Open AI, Azure Inference SDK to view the performance and optimize the LLM application. s. Go to notebook

    ์ด ํ•ธ์ฆˆ์˜จ์€ AI Foundry์˜ trace ๊ธฐ๋Šฅ์„ ์„ค์ •ํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ์ด ํ•ธ์ฆˆ์˜จ์„ ํ†ตํ•ด ์—ฌ๋Ÿฌ๋ถ„์€ tracing ๊ธฐ๋Šฅ์„ ํ™œ์„ฑํ™”ํ•˜๋Š” ๋ฐฉ๋ฒ•๊ณผ ์„ค์ •ํ•˜๋ ค๋Š” ์ฝ”๋“œ์— ๋”ฐ๋ผ ์•Œ๋งž์€ instrument๋ฅผ ์„ค์ •ํ•˜๋Š” ๋ฐฉ๋ฒ•๊ณผ ํ…Œ์ŠคํŠธ๋ฅผ ์ง„ํ–‰ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. Go to notebook

๐Ÿ”ฅNew Feature (06-Apr-2025)

Prompt Optimization

  • This hands-on demonstrates how to optimize prompts using PromptWizard. PromptWizard, released as open source and paper by Microsoft, is a prompt optimization tool for maximizing the performance of LLM. It is a prompt optimization framework that employs a self-evolving mechanism in which LLM generates, critiques, refines, and continuously improves prompts and examples through feedback and synthesis. s. Go to notebook

    ์ด ํ•ธ์ฆˆ์˜จ์€ PromptWizard๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ํ”„๋กฌํ”„ํŠธ๋ฅผ ์ตœ์ ํ™”ํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค. ๋งˆ์ดํฌ๋กœ์†Œํ”„ํŠธ์— ์˜คํ”ˆ ์†Œ์Šค์™€ ๋…ผ๋ฌธ์œผ๋กœ ๊ณต๊ฐœํ•œ PromptWizard๋Š” LLM์˜ ์„ฑ๋Šฅ์„ ๊ทน๋Œ€ํ™”ํ•˜๊ธฐ ์œ„ํ•œ ํ”„๋กฌํ”„ํŠธ ์ตœ์ ํ™” ๋„๊ตฌ์ž…๋‹ˆ๋‹ค. LLM์ด ์Šค์Šค๋กœ ํ”„๋กฌํ”„ํŠธ์™€ ์˜ˆ์ œ๋ฅผ ์ƒ์„ฑ, ๋น„ํ‰, ์ •๊ตํ•˜๊ณ  ํ”ผ๋“œ๋ฐฑ๊ณผ ํ•ฉ์„ฑ์„ ํ†ตํ•ด ์ง€์†์ ์œผ๋กœ ๊ฐœ์„ ํ•˜๋Š” ์ž๊ธฐ ์ง„ํ™” ๋ฉ”์ปค๋‹ˆ์ฆ˜์„ ์ฑ„ํƒํ•œ ํ”„๋กฌํ”„ํŠธ ์ตœ์ ํ™” ํ”„๋ ˆ์ž„์›Œํฌ์ž…๋‹ˆ๋‹ค. Go to notebook

๐Ÿ”ฅNew Feature (15-Jan-2025)

Azure AI Evaluation SDK Code Sample

  • This hands-on workshop is tailored for engineers seeking to deepen their understanding of the Azure AI Evaluation SDK. Participants will explore the distinctions between evaluators and simulators through practical code examples. The workshop will guide you in assessing the quality and safety of your generative AI applications using industry-standard metrics. Leveraging Azure AI Evaluation SDKโ€™s built-in evaluators, you will learn how to compare different versions of your applications and select the optimal solution to meet your specific requirements. Go to notebook

    ์ด ์‹ค์Šต ์›Œํฌ์ƒต์€ Azure AI ํ‰๊ฐ€ SDK๋ฅผ ์ดํ•ดํ•˜๊ณ ์ž ํ•˜๋Š” ์—”์ง€๋‹ˆ์–ด๋ฅผ ์œ„ํ•œ ๋งž์ถคํ˜• ์›Œํฌ์ƒต์ž…๋‹ˆ๋‹ค. ์ฐธ๊ฐ€์ž๋Š” ์‹ค์ œ ์ฝ”๋“œ ์˜ˆ์ œ๋ฅผ ํ†ตํ•ด Evaluator์™€ Simulator์˜ ์ฐจ์ด์ ์„ ์‚ดํŽด๋ด…๋‹ˆ๋‹ค. ์ด ์›Œํฌ์ƒต์—์„œ๋Š” ์—…๊ณ„ ํ‘œ์ค€ ๋ฉ”ํŠธ๋ฆญ์„ ์‚ฌ์šฉํ•˜์—ฌ ์ƒ์„ฑ AI ์• ํ”Œ๋ฆฌ์ผ€์ด์…˜์˜ ํ’ˆ์งˆ๊ณผ ์•ˆ์ „์„ฑ์„ ํ‰๊ฐ€ํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ์•ˆ๋‚ดํ•ฉ๋‹ˆ๋‹ค. Azure AI ํ‰๊ฐ€ SDK์˜ ๊ธฐ๋ณธ ์ œ๊ณต ํ‰๊ฐ€๊ธฐ๋ฅผ ํ™œ์šฉํ•˜์—ฌ ๋‹ค์–‘ํ•œ ๋ฒ„์ „์˜ ์• ํ”Œ๋ฆฌ์ผ€์ด์…˜์„ ๋น„๊ตํ•˜๊ณ  ํŠน์ • ์š”๊ตฌ ์‚ฌํ•ญ์„ ์ถฉ์กฑํ•˜๋Š” ์ตœ์ ์˜ ์†”๋ฃจ์…˜์„ ์„ ํƒํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ๋ฐฐ์›๋‹ˆ๋‹ค. Go to notebook

o1 GA new features Test

  • Test the most basic way to use the o1(GA) with Vision model, Structured Output and gradio sample application as your playgournd Go to notebook

    ๋น„์ „ ๋ชจ๋ธ, ๊ตฌ์กฐํ™”๋œ ์ถœ๋ ฅ ๋ฐ ๊ทธ๋ผ๋””์˜ค ์ƒ˜ํ”Œ ์• ํ”Œ๋ฆฌ์ผ€์ด์…˜์„ ํ”Œ๋ ˆ์ด๊ทธ๋ผ์šด๋“œ๋กœ ์‚ฌ์šฉํ•˜์—ฌ o1(GA)๋ฅผ ์‚ฌ์šฉํ•˜๋Š” ๊ฐ€์žฅ ๊ธฐ๋ณธ์ ์ธ ๋ฐฉ๋ฒ•์„ ํ…Œ์ŠคํŠธํ•ด ๋ณด์„ธ์š”. Go to notebook

๐Ÿ”ฅNew Feature (23-Dec-2024)

Azure Custom Speech

  • Added Audio Data Augmentation using Audiomentations. Audiomentations supports both mono and stereo audio and integrates seamlessly with common audio processing workflows. It's lightweight, efficient, and helps simulate real-world audio conditions for better generalization in models.

Please do not forget to install the audiomentations package. Install with pip install audiomentations or see requirements.txt.

๐Ÿ”ฅNew Feature (05-Dec-2024)

Azure Custom Speech for multi-language

  • Refactored to make it easier to test custom models for a given language by adding language-specific settings. Added a function to the 3_evaluate_custom_model notebook to retrieve detailed WER information from the notebook based on whether there are insertions, substitutions, or deletions. Go to notebook

    ์–ธ์–ด๋ณ„ ์„ค์ •์„ ์ถ”๊ฐ€ํ•˜๋ฉด ๊ฐ„๋‹จํžˆ ํ•ด๋‹น ์–ธ์–ด์— ๋งž๋Š” ์ปค์Šคํ…€ ๋ชจ๋ธ์„ ํ…Œ์ŠคํŠธํ•ด๋ณผ ์ˆ˜ ์žˆ๋„๋ก ๋ฆฌํŽ™ํ† ๋งํ–ˆ์Šต๋‹ˆ๋‹ค. insertion, substitution, deletion ์—ฌ๋ถ€์— ๋”ฐ๋ผ ์ƒ์„ธํ•œ WER์ •๋ณด๋ฅผ ๋…ธํŠธ๋ถ์—์„œ ์กฐํšŒํ•˜๋Š” ํ•จ์ˆ˜๋ฅผ 3_evaluate_custom_model ๋…ธํŠธ๋ถ์— ์ถ”๊ฐ€ํ–ˆ์Šต๋‹ˆ๋‹ค. Go to notebook

๐Ÿ”ฅNew content (11-Nov-2024)

Azure Custom Speech E2E Training with Python

  • Azure AI Speech is a managed service that provides speech capabilities such as speech-to-text, text-to-speech, voice translation, and speaker recognition. In this lab, you will learn the entire end-to-end process of training a custom speech-to-text (STT) model optimised for a specific language and use case based on synthetic data. You can practice generating synthetic text data (phi3.5), converting generated text files to audio files (text-to-speech), training(speech-to-text), evaluating, and deploying custom AI speech models based on synthetic text/audio files. In addition to generating synthetic data, you can also upload the speech data you use in the field to a specific folder and upload it to the storage account with simple notebook code to proceed with dataset creation, training, and evaluation. If you're looking to train custom speech models with different types of datasets to improve your word error rate (WER), this Python SDK and REST API-based handson makes it easy to automate your end-to-end model training and evaluation pipeline and scale your transformations.
    Go to notebook

    Azure AI Speech๋Š” ์Œ์„ฑ ํ…์ŠคํŠธ ๋ณ€ํ™˜, ํ…์ŠคํŠธ ์Œ์„ฑ ๋ณ€ํ™˜, ์Œ์„ฑ ๋ฒˆ์—ญ, ํ™”์ž ์ธ์‹๊ณผ ๊ฐ™์€ ์Œ์„ฑ ๊ธฐ๋Šฅ์„ ์ œ๊ณตํ•˜๋Š” ๊ด€๋ฆฌํ˜• ์„œ๋น„์Šค์ž…๋‹ˆ๋‹ค. ๋ณธ ํ•ธ์ฆˆ์˜จ์—์„œ๋Š” ํŠน์ • ์–ธ์–ด์™€ ์œ ์Šค์ผ€์ด์Šค์— ์ตœ์ ํ™”๋œ Custom STT(Speech To Text)๋ชจ๋ธ ํ•™์Šต์˜ End2End ์ „์ฒด๊ณผ์ •์„ ํ•ฉ์„ฑ๋ฐ์ดํ„ฐ(Syntethic data)๊ธฐ๋ฐ˜์œผ๋กœ ์‹ค์Šตํ•ฉ๋‹ˆ๋‹ค. ํ•ฉ์„ฑ ํ…์ŠคํŠธ ๋ฐ์ดํ„ฐ ์ƒ์„ฑ(phi3.5), ์ƒ์„ฑ๋œ ํ…์ŠคํŠธํŒŒ์ผ์„ ์˜ค๋””์˜คํŒŒ์ผ๋กœ ๋ณ€ํ™˜ (Text to Speech), ํ•ฉ์„ฑ ํ…์ŠคํŠธ/์˜ค๋””์˜คํŒŒ์ผ ๊ธฐ๋ฐ˜์˜ Custom AI Speech ๋ชจ๋ธ ํ•™์Šต(Speech to Text), ํ‰๊ฐ€, ๋ฐฐํฌ๋ฅผ Python SDK์™€ REST API๊ธฐ๋ฐ˜์œผ๋กœ ์‹ค์Šตํ•ด๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ํ•ฉ์„ฑ๋ฐ์ดํ„ฐ๋ฅผ ์ƒ์„ฑํ•˜๋Š” ๊ฒƒ ์™ธ์—๋„ ํ˜„์žฅ์—์„œ ํ™œ์šฉํ•˜๊ณ  ์žˆ๋Š” ์Œ์„ฑ๋ฐ์ดํ„ฐ๋ฅผ ํŠน์ • ํด๋”์— ์—…๋กœ๋“œํ•˜๋ฉด ๊ฐ„๋‹จํ•œ ๋…ธํŠธ๋ถ ์ฝ”๋“œ๋กœ Storage Account์— ์—…๋กœ๋“œ ๋ฐ ๋ฐ์ดํ„ฐ์…‹ ์ƒ์„ฑ, ํ•™์Šต ๋ฐ ํ‰๊ฐ€ ๊ณผ์ •์„ ์ง„ํ–‰ํ•ด๋ณผ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค. WER(๋‹จ์–ด ์˜ค๋ฅ˜์œจ)์„ ๊ฐœ์„ ํ•˜๊ธฐ ์œ„ํ•ด ๋‹ค์–‘ํ•œ ์œ ํ˜•์˜ ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ ๋งž์ถคํ˜• ์Œ์„ฑ ๋ชจ๋ธ์„ ํ•™์Šต์‹œํ‚ค๋ ค๋Š” ๊ฒฝ์šฐ, Python SDK ๋ฐ REST API๊ธฐ๋ฐ˜์˜ ๋ณธ ํ•ธ์ฆˆ์˜จ์„ ํ™œ์šฉํ•˜์—ฌ ์—”๋“œํˆฌ์—”๋“œ ๋ชจ๋ธ ํ•™์Šต ๋ฐ ํ‰๊ฐ€ ํŒŒ์ดํ”„๋ผ์ธ์„ ์‰ฝ๊ฒŒ ์ž๋™ํ™”ํ•˜๊ณ  ๋ณ€ํ˜•์„ ํ™•์žฅํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. Go to notebook

๐Ÿ”ฅNew content (30-Oct-2024)

Promptflow with Python SDK

  • This hands-on workshop is designed to help engineers who have difficulty developing UI-based Promptflow in Azure ML Studio, AI Studio, and VS Code. Based on the Python Promptflow SDK, you will learn how to develop and run chat, flows with context, phi3 model integration deployed serverlessly, evaluation flows, and filter inappropriate prompts using content safety. Go to notebook

    ์ด ํ•ธ์ฆˆ์˜จ ์›Œํฌ์ƒต์€ Azure ML Studio, AI Studio, VS Code์—์„œ Promptflow๋ฅผ ui๊ธฐ๋ฐ˜์œผ๋กœ ๊ฐœ๋ฐœํ•˜๋Š”๋ฐ ์–ด๋ ค์›€์„ ๋А๋ผ๋Š” ์—”์ง€๋‹ˆ์–ด๋“ค์„ ์ง€์›ํ•˜๊ณ ์ž ๊ฐœ๋ฐœ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. Python Promptflow SDK๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ chat, context๊ฐ€ ํฌํ•จ๋œ flow, serverless๋กœ ๋ฐฐํฌํ•œ phi3๋ชจ๋ธ ์—ฐ๋™, evaluation flow ๊ฐœ๋ฐœ ๋ฐ ์‹คํ–‰ ๋ฐฉ๋ฒ•๊ณผ ๋ถ€์ ์ ˆํ•œ prompt๋ฅผ content safety์„ ํ™œ์šฉํ•ด filteringํ•˜๋Š” ์‹ค์Šต์„ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. Go to notebook

๐Ÿ”ฅNew content (15-Oct-2024)

AI Search Code Sample with AOAI

  • Based on the current version of the Azure AI Search Python client library, azure-search-documents==11.6.0b4. This code sample demonstrates various code patterns to implement AI search using Azure OpenAI and Azure AI Search to create indexes, vector search, change search algorithms, cross-field search, multi-vector search, filtering, hybrid, and reranking. Go to notebook

    ํ˜„์žฌ Azure AI Search Python client library ์ตœ์‹  ๋ฒ„์ „์ธ azure-search-documents==11.6.0b4๋ฅผ ๋ฐ”ํƒ•์œผ๋กœ ์ž‘์„ฑ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ์ด ์ฝ”๋“œ ์ƒ˜ํ”Œ์€ Azure OpenAI์™€ Azure AI Search๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ์ธ๋ฑ์Šค ์ƒ์„ฑ, vector search, ๊ฒ€์ƒ‰ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ๋ณ€๊ฒฝ, Cross-Field๊ฒ€์ƒ‰, Multi-Vector๊ฒ€์ƒ‰, filtering, Hybrid, Reranking์„ ํ™œ์šฉํ•œ AI ๊ฒ€์ƒ‰์„ ๊ตฌํ˜„ํ•˜๋Š” ๋‹ค์–‘ํ•œ ์ฝ”๋“œ ํŒจํ„ด์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค. Go to notebook

๐Ÿฅ‡Other Resources

Azure OpenAI pricing

Diagam of a search scoring workflow

Author

Date of creation: 15-Oct-2024
Updated: 06-Apr-2025

Hyo Choi | hyo.choi@microsoft.com | https://www.linkedin.com/in/hyogrin/ Daekeun Kim | daekeun.kim@microsoft.com | https://www.linkedin.com/in/daekeun-kim/

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •