Sign In Start Free Trial
Account

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Unlocking Creativity with Azure OpenAI
  • Toc
  • feedback
Unlocking Creativity with Azure OpenAI

Unlocking Creativity with Azure OpenAI

By : AMIT MUKHERJEE, Adithya Saladi
close
Unlocking Creativity with Azure OpenAI

Unlocking Creativity with Azure OpenAI

By: AMIT MUKHERJEE, Adithya Saladi

Overview of this book

Azure OpenAI, a cutting-edge service by Microsoft, harnesses the power of OpenAI's Large Language Model (LLM) to drive cloud-based innovations within enterprises. This service integrates advanced LLM models into business functions, transforming Microsoft products like GitHub Copilot, Microsoft 365 Copilot, and Bing Chat, making them more advanced and interactive. Azure OpenAI is accessible via REST APIs, Python SDK, or Azure OpenAI Studio, opening doors to build innovative AI applications. This book is a comprehensive guide to build GenAI applications using Azure OpenAI. It begins with the fundamentals, including how to access Azure OpenAI and how to effectively utilize its REST API and Python SDK. It takes a deep dive into various AI models and emphasizes the crucial aspects of prompt engineering and fine-tuning for optimal output. It further underlines the significance of content filters and prevention of misuse, maintaining a strong focus on safety and security protocols and finally the significance of Azure OpenAI Studio in deployment and administration is emphasized. Practical applications are showcased like content generations, summarization, semantic search, code documentation and code generation. Combining Azure Cognitive services amplifies Generative AI potential and finally aligns with Microsoft's ethical AI principles.
Table of Contents (19 chapters)
close
Free Chapter
1
Part 1: Foundations of Generative AI and Azure OpenAI
5
Part 2: Practical Applications of Azure OpenAI: Real-World Use Cases
13
Part 3: Mastering Governance, Operations, and AI Optimization with Azure OpenAI

Prompt engineering versus fine-tuning

Imagine a chef who specializes in a particular cuisine after extensive training. Fine-tuning is akin to this focused training, where the LLM is adjusted based on a curated dataset tailored to specific tasks. This dataset includes input-output pairs that clearly illustrate the task at hand and the expected results. Through this process, the model’s internal parameters are refined, enhancing its ability to perform specialized tasks. However, fine-tuning should be used with caution, as it requires significant computational resources and can be expensive. If not managed properly, it may lead to overfitting, where the model performs well on the fine-tuning dataset but poorly on other tasks, reducing its generalization ability. Additionally, fine-tuning can require substantial time and effort, so it should only be employed when necessary. In some cases, less resource-intensive approaches, such as prompt engineering or transfer learning, may be...

bookmark search playlist download font-size

Change the font size

margin-width

Change margin width

day-mode

Change background colour

Close icon Search
Country selected

Close icon Your notes and bookmarks

Delete Bookmark

Modal Close icon
Are you sure you want to delete it?
Cancel
Yes, Delete