Sign in to confirm you’re not a bot
This helps protect our community. Learn more
Armchair Architects: LLMs & Vector Databases (Part 2)
70Likes
2,890Views
2024Jan 2
In this episode of the #AzureEnablementShow, Uli, Eric (‪@mougue‬) and David continue their discussion of vector databases and LLMS, including when to use prompt engineering, and the importance of fine-tuning your data. Uli suggests that there are two things that LLMs aren’t good at, then offers tips on workarounds. The conversation wraps up with a discussion of some of the pros and cons of vectorization. This is part two of a two-part series. Resources • Submit a training job in Studio https://learn.microsoft.com/en-us/azu... • Artificial intelligence (AI) architecture design https://learn.microsoft.com/en-us/azu... • Prepare for AI engineering https://learn.microsoft.com/en-us/tra... • Fundamentals of Generative AI https://learn.microsoft.com/en-us/tra... • What's new in Azure AI Search https://learn.microsoft.com/en-us/azu... Related episodes • Armchair Architects: LLMs & Vector Databases (Part 1) https://aka.ms/azenable/141 • Watch more episodes in the Armchair Architects Series https://aka.ms/azenable/ArmchairArchi... • Watch more episodes in the Well-Architected Series https://aka.ms/azenable/yt/wa-playlist Chapters 0:00 Introduction 0:15 Recap on Embedding 0:39 Consider prompt engineering first 2:06 Fine tune your data 2:58 Help with hallucinations 4:49 LLMs and math 4:59 LLMs and structured data 5:19 Add code to prompts 5:52 Pipeline based programming 7:54 Vector database vs. vector Index 9:00 Arriving at vectorization 9:52 Vectorization alone isn’t the answer

Follow along using the transcript.

Microsoft Developer

588K subscribers