Ricardo Eihara rhiroyuki

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

Shall i implement it?
No ...

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

ChatGPT Resources

Context

ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?

I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.

Model Architecture

Heroku Release Phase + Review Apps + Rails

This is a simplified, but fairly thorough, set of scripts and configuration to enable Heroku Release Phase for Rails apps. Further, this particular set up plays nicely with Heroku Review Apps in that the release phase script will:

Fail, loudly, if the DB does not yet exist.
Load the DB schema if the current schema version (as determined by bin/rails db:version) is 0.
Run DB migrations otherwise.

For a "normal" app that usually means it will run the DB migrations.

Project Ideas

Ok. I'm going to list off some ideas for projects. You will have to determine if any particular idea is good enough to include in a portfolio. These aren't creative ideas. They likely already exist. Some are way too advanced while others are simplistic.

I will recommend to post any project you make to github and make a github project page for it. Explain in as much detail as possible how you made it, how it can be improved etc. Document it.

If you pick an advanced idea, setup a development roadmap and follow it. This will show some project management skills.

Another piece of advice for those who are design challenged. Use different front end frameworks and use different themes for those frameworks to provide appealing designs without looking like yet another bootstrap site.

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

Example

Stack financeira

Indices

Selic - http://www.bcb.gov.br/htms/selic/selicdiarios.asp
- Infos: http://www.bcb.gov.br/pt-br/#!/n/selictaxa
Taxa DI - https://www.cetip.com.br
- DI Futuro - http://br.advfn.com/bolsa-de-valores/bmf/DI1F25/grafico/tempo-real
- O que é CDI - http://www.blog.rendafixa.rocks/pt/2017/06/12/o-impacto-do-cdi-nos-seus-investimentos
IPC-A - http://www.calculador.com.br/tabela/indice/IPCA
Tabela Regressiva IR - http://www.infomoney.com.br/mercados/renda-fixa/noticia/368199/tributa-ccedil-atilde-renda-fixa

	Ruby e Rails

	Guias:
	http://guides.rubyonrails.org/

	Livros (Free mas vale pagar um café para o autor ;) ):
	https://leanpub.com/conhecendo-ruby

	Livros (Pagos):
	https://leanpub.com/conhecendo-rails