Tammo van Lessen vanto

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.

Extracting financial disclosure reports and police blotter narratives using OpenAI's Structured Output

tl;dr this demo shows how to call OpenAI's gpt-4o-mini model, provide it with URL of a screenshot of a document, and extract data that follows a schema you define. The results are pretty solid even with little effort in defining the data — and no effort doing data prep. OpenAI's API could be a cost-efficient tool for large scale data gathering projects involving public documents.

OpenAI announced Structured Outputs for its API, a feature that allows users to specify the fields and schema of extracted data, and guarantees that the JSON output will follow that specification.

For example, given a Congressional financial disclosure report, with assets defined in a table like this:

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

Wahoo Elemnt - Tips, tricks and custom images

	FROM traefik:camembert
	ADD traefik.toml .
	EXPOSE 80
	EXPOSE 8080
	EXPOSE 443

	Dear soon-to-be-former user,

	We've got some fantastic news! Well, it's great news for us anyway. You, on
	the other hand, are fucked.

	We've just been acquired by:

	[ ] Facebook
	[ ] Google
	[ ] Twitter