Cpop cpoptic

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.

Lecture 1: Introduction to Research — [📝Lecture Notebooks] [▶️Video]
Lecture 2: Introduction to Python — [📝Lecture Notebooks] [▶️Video]
Lecture 3: Introduction to NumPy — [📝Lecture Notebooks] [▶️Video]
Lecture 4: Introduction to pandas — [📝Lecture Notebooks] [▶️Video]
Lecture 5: Plotting Data — [📝Lecture Notebooks] [[▶️Vide

Error

$ sudo apt-get update
Err:1 http://archive.ubuntu.com/ubuntu focal InRelease
Temporary failure in name rerolution

$ host google.com
;; connection timed out; no servers could be reached

Deep Learning Hands-On Series with Eric Schles

05/22 - Deep Learning Hands-On Series - Data Exploration and API First Design 🎥

05/29 - Deep Learning Hands-On Series - Model Tuning 🎥

06/05 - Deep Learning Hands-On Series - Monitoring [cancelled]

Resources

Notebooks

Problem, and symptoms:

You experience one or more of these symptoms

you have code in a directory but it's not being pushed to GitHub. You just see an empty directory icon
you see this message when you add code to your git repository from the command prompt

hint: You've added another git repository inside your current repository.
hint: Clones of the outer repository will not contain the contents of
hint: the embedded repository and will not know how to obtain it.

	import datetime
	import pandas as pd
	from ib_insync import *

	pd.set_option('display.max_rows', None)

	ib = IB()
	ib.connect('127.0.0.1', 7496, clientId=15)

	contract = Stock('SPY', 'SMART', 'USD')

	#%% packages
	# data handling
	import numpy as np
	from sklearn.datasets import fetch_california_housing
	from sklearn.preprocessing import StandardScaler
	from sklearn.model_selection import train_test_split
	from sklearn.metrics import r2_score
	# deep learning
	import torch
	import torch.nn as nn

	import uvicorn
	from fastapi import FastAPI
	from model import SentimentModel, SentimentQueryModel

	app = FastAPI()
	model = SentimentModel()

	@app.post('/predict')
	def predict(data: SentimentQueryModel):
	data = data.dict()

	import streamlit as st
	from persist import persist, load_widget_state


	def main():
	if "page" not in st.session_state:
	# Initialize session state.
	st.session_state.update({
	# Default page.
	"page": "home",