Tag:others

All the articles with the tag "others".

• A Brief Pause for GPTs

  Posted on:November 13, 2023 |  at 05:35 PM

  I took a detour and decided to build a GPT referenced in OpenAI’s keynote from last week. I wanted to create one that had at least some information attached to the retrieval features and could call an API via a custom action.

• Adding a Database

  Posted on:November 22, 2023 |  at 07:59 PM

  Working in text and JSON files is great for experimentation and speed, but I've been itching to put some of what we've been retrieving and generating into something more permanent like a database.

• Weekly Python Learning Recap – Week 1

  Posted on:April 19, 2025 |  at 12:32 PM

  Working on sharpening my logic skills, week by week. I'll keep a log here and continue to learn in public.

• AI Engineering Course: Day 1

  Posted on:January 12, 2024 |  at 04:08 PM

  I have a proof-of-concept working version of QC Stacks running on Vercel. I'm in the process of migrating the work to Azure and using MongoDB as the database. I chose Azure due to my full-time position at Microsoft and wanted exposure and experience using a more production-ready environment that I might encounter in the real world.

• Further Exploring Summarization

  Posted on:November 7, 2023 |  at 01:19 AM

  I left off the summarization piece with a few outstanding questions: - How best to optimize the chunk size in the `text_splitter` for speed - Is GPT4 worth the increased cost and time? - Why aren't the bullets coming through in GPT4?

• Implementing OpenAI's New DevDay Features

  Posted on:November 7, 2023 |  at 04:46 PM

  A few new features that OpenAI unveiled this week caught my eye. These should be especially helpful in bringing down costs of my requests and ensuring a consistent response.

• AI Engineering Course: Day 2

  Posted on:January 19, 2024 |  at 08:40 PM

  I had done some RAG-style prototypes in a Jupyter Notebook a few months back using LangChain and some hosted vector databases such as Pinecone. While these Notebooks helped me understand the features of what a RAG-style Chatbot might perform, it left a lot to be desired in terms of how it was working under the hood. This Day 2 tutorial really helped me explore what exactly is happening when we used embeddings to create context for a LLM-powered chatbot.

• Moving toward production

  Posted on:November 9, 2023 |  at 04:35 PM

  After experimenting with different approaches in Jupyter notebooks and deciding on the best route to take, I'm ready to move my Notebook code into something that we can use for the final site. I collaborated with ChatGPT to help me modularize and comment out the messy Notebook code into something that exists in individual Python scripts. Here's where we ended up.

• Kicking Things Off

  Posted on:November 2, 2023 |  at 09:02 PM

  Embarking on an AI-driven adventure to transform how we digest city council meetings, I'm channeling my English & Journalism background into a practical project. Join me as I document my journey with GPT-4 at Spellbooks.ai to innovate reporting.

• Retrieving the Meeting Data

  Posted on:November 4, 2023 |  at 04:58 PM

  I'm working with ChatGPT as a pair programmer to help me pull all Cincinnati Council meeting minutes from 2023.

• Let's Summarize the Meetings

  Posted on:November 6, 2023 |  at 01:08 AM

  Now that the meetings are being fetched through a simple Python script, we can begin the work of summarizing the meetings with OpenAI's GPT-4 model.

• Rails Makes Its Wisdom Save: Why ‘Boring’ Technology is Winning the AI Campaign

  Posted on:January 30, 2025 |  at 05:17 PM

  Boring technology might be the future of AI applications. Starting a series building a D&D character generator that challenges our industry's obsession with complexity. Rails - with its predictable conventions, server-rendered HTML, and focus on simplicity - is an excellent match for the generative AI era. Rails' established patterns align well with the needs of generative AI applications. The framework's steady evolution and focus on simplicity offer some interesting advantages for LLM integration. Part 1 examines how Rails' approach to web development might be particularly relevant in the AI era. While our industry often equates innovation with complexity, there's value in examining proven patterns through this new lens.

• Rails Makes LLMs Boring (And That's Good): A Service Layer Implementation

  Posted on:February 26, 2025 |  at 04:44 PM

  Rails service patterns provide an elegant solution for LLM integration without specialized frameworks or microservices. Our D&D character generator demonstrates how standard Rails conventions can handle complex AI capabilities, proving that "boring" technology delivers powerful results with superior maintainability and development speed.

• Weekly Python Learning Recap – Week 2

  Posted on:April 28, 2025 |  at 07:04 PM

  Working on sharpening my logic skills, week by week. I'll keep a log here and continue to learn in public.

• Weekly Python Learning Recap - Week 3

  Posted on:May 9, 2025 |  at 08:08 PM

  Working on sharpening my logic skills, week by week. I'll keep a log here and continue to learn in public.