Introduction In my spare time I'm trying to make some progress on a coding project called TherapyBot. Despite its name, it's not strictly about therapy - that's just one potential use case. The main aim? To test out some ideas and, let's be honest, to level up my coding skills. What's TherapyBot, anyway? At its … Continue reading TherapyBot: Exploring Knowledge Graphs and LLMs in Chat-Based Applications
Poet
The author expresses a deep yearning to be a poet, reflecting on the creative process and societal expectations. They grapple with the practicalities of a poetic career, the pressures of performance, and the challenges of convention versus freedom. Ultimately, the desire stems from a love for words and self-expression, amid uncertainties.
Antecedence Matters
Antecedence matters. In the Bible, John 10:22-42 describes Jesus being stoned for blasphemy. Modern translations have Jesus calling himself "the son of God". But it can equally be "a" "son of God". When he is being stoned for blasphemy for calling himself "son of God", modern translations say: 34 Jesus replied, “It is written in … Continue reading Antecedence Matters
A (Working) CI/CD Workflow with GitHub Actions for AI Applications
The post shares their journey of setting up a cost-effective CI/CD pipeline for AI applications using GitHub Actions and Docker. Emphasizing branching, versioning, and meticulous testing, the post highlights the importance of simplicity, efficiency, and automation in achieving a streamlined development workflow.
Process for Dealing with Issues
This post outlines a process for handling GitHub issues, including determining the type of issue, identifying relevant code, and resolving the issue through testing, correction, and pull requests. It also discusses the potential for automation using LLMs and user templates, as well as the use of vector search in repositories.
Self-Coding Repository – Testing for LLM-Coding
Some notes from my project to create self-coding software. The post emphasises the power of testing, "good code" practices, pain points, and cool features we can leverage. These include GitHub/IDE code review GUIs, tools like Ruff and Sphinx, and Test Driven Development, modularity, code duplication, and profiling.
Self-Coding Repository – Idea Update
The author is developing a self-coding project using Large Language Models (LLMs), such as GPT3.5/4-turbo and GPT4, to generate code, tests, and documentation. Existing project files are used as LLM prompt context. Evaluation tools from the Python ecosystem, GitHub API and function calling options are leveraged to streamline the process. The system has been designed to cater for various programming tasks. However, tweaking different agent "personalities" and effectively managing complex project directories remain challenges.
Building a Bible & Quran QA System with Langchain and Flask
If I had lived in the C14, I would have liked to be a monk. This post channels my inner monk to explain how you can build a proof-of-concept exegesis system on the Bible and Quran with langchain.
Cool Personal Datasets for Amateur Data Analysis
I’m an amateur data nerd. Problem is it’s hard to find good datasets that are personally relevant. However, it’s super easy to download some juicy data archives for data crunching at home. Here is a short guide to do this.
Analysing Your Tweets with ChatGPT
This post dives into applying ChatGPT's new Code Interpreter / Advanced Data Analysis to downloaded Twitter data. Keep reading for an insight into the cool things you can do.
Robotic Ape 