Hello :) Today is Day 147!
A quick summary of today:
- attended day 1 of Microsoft Azure hackathon
The learning objectives of the hackathon:
- Understand GenAI concepts and how they can be used to build chat applications
- Learn how to configure the Azure OpenAI service and use Azure AI Search to build private OpenAI with your own data
- Gain practical experience in implementing a chat app architecture with Terraform
- Explore features of chat apps, such as multilingual queries and advanced chat response settings
- Apply GenAI to real-world scenarios, including increased user interactions and dynamic document processing
- Operationalize AI-enabled applications with enterprise-level monitoring and logging
- Scale AI-enabled applications with enterprise-level load balancing
We are assinged to a table and the people on a table work together as a team. It is all about using Azure and its services.
There are in total 6 challenges, 3 for Day 1 and the others for Day 2. Below are some pics/notes from the first three challenges.
We are given access to a VM, and have to do all the challenges in there
Challenge 1: Deploy Azure OpenAI Service and LLM Models
- Deploy Azure OpenAI Service and Large Language Models (LLMs) such as gpt-35-turbo and text-embedding-ada-002 to improve Contoso Ltd.’s customer support operations by handling inquiries efficiently
Challenge 2: Implement Document Search with Azure AI Search
- Leverage Azure AI Search and Azure OpenAI (GPT-3.5-Turbo) to create a document search solution that makes support documents searchable and understands customer queries, enhancing Contoso’s support services
Had to set up Azure AI search, AI service, a Storage account, upload documents to azure, create an indexer. The result:
A simple html with all the reviews (pdf files uploaded) and a way to search using key words.
Challenge 3: Deploy an AI-Powered Chat App
- Deploy an AI-powered chat application for Contoso Electronics. This app showcases advanced features like chat and Q&A interfaces, augmented by AI capabilities, and integrates Azure OpenAI Service with the GPT-3.5 Turbo model and Azure Cognitive Search for efficient data indexing and retrieval
- Actually this one we were not able to complete because non of us had used terraform before and we faced various issues related to running scripts. At the end of the day, even though the final deployment script ran - there were plenty of errors, but our team stayed after everyone as so there was no mentor to help us. Hopefully we can run and complete it tomorrow (along with the rest of the challenges).
Architecture diagram of the implemented app
Here are some pics of the view (hackathon room is on the 13th floor)
Tomorrow is Day 2 with some more challenges ^^
That is all for today!
See you tomorrow :)