bert

On Jun 11, 2:01 pm, Robert Kern <robert.k... at gmail.com> wrote:
> On 2009-06-11 14:56, Captain___nemo wrote:
> > Please advice me very simple implementation of voronoi diagram (given
> > coordinates). Please advice me simple python code preferably without-
> > hash, multi-threading, Delaunay Traingulation,
>
> You can't really do the Voronoi diagram without Delaunay Triangulation. They are
> two ways of looking at the same thing.

bluele

#!/usr/bin/env python
#-*- coding:utf-8 -*-

__author__ = 'bluele'
__version__ = '0.10'
__license__ = 'MIT'

__doc__ = """
# simple running
$ hserve

renzok

FROM debian:jessie

ENV USER=boatswain USER_ID=1000 USER_GID=1000

# now creating user
RUN groupadd --gid "${USER_GID}" "${USER}" && \
    useradd \
      --uid ${USER_ID} \
      --gid ${USER_GID} \
      --create-home \

karpathy

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.