Luca G. Soave lgs

Organizing FastHTML Applications Across Multiple Files

Let's explore two main approaches to splitting FastHTML applications into multiple files: using Mount and using APIRouter. I'll explain the pros and cons of each and provide practical examples.

1. Using Mount - The "Mini-Apps" Approach

Mount is ideal when you want to create semi-independent sub-applications that could potentially be reused across different projects. Think of these as "mini-apps" that handle specific features.

# blog/routes.py

The Surprising Power of Questions

It goes far beyond exchanging information.

by

Alison Wood Brooks
Leslie K. John

From Harvard Business Review Magazine (May–June 2018)

Explaining Pathos in Ancient Epics and today

🧑 human (Sep 21, 2024, 06:13 PM)

What is pathos, and what's it got to do with Virgil or Homer? Explain for a 12 y.o.

🤖 assistant (Sep 21, 2024, 06:13 PM)

Pathos is a way of making people feel emotions when they read or hear something. It's like when a story makes you feel sad, happy, or excited.

Virgil and Homer were famous ancient Greek and Roman poets who wrote epic stories. They used pathos a lot in their writing to make readers really care about what was happening.

For example:

The Future of AI Education: fast.ai Joins Forces with Answer.AI

Date: November 20, 2024
Author: Jeremy Howard
Categories: AI Education, fast.ai, Answer.AI

In the rapidly evolving world of artificial intelligence, the need for accessible, practical education has never been more crucial. Today, I am excited to announce that fast.ai is joining forces with Answer.AI to bring you a new era of AI education. This partnership is not just about combining resources; it's about creating a new kind of learning experience that leverages the power of AI to solve real-world problems.

A guide to George Polya's "How to Solve It"

Introduction

George Polya (1887-1985) was a Hungarian mathematician and educator who revolutionized our understanding of problem-solving and teaching. While he made significant contributions to mathematics, his most enduring legacy is his insights into how people learn and solve problems. His 1945 book "How to Solve It" has influenced educators across numerous fields, extending far beyond mathematics.

Polya's Teaching Philosophy

Polya's approach centered on three key principles. First, he championed active learning, believing students learn best by discovering solutions themselves rather than being told answers. Second, he emphasized heuristic thinking - the art of guided discovery and learning from experience, viewing problem-solving as a skill that can be developed through practice. Third, he developed sophisticated questionin

Setup

Create a new directory with these three files (requirements.txt, main.py, README.md)
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python main.py
Update main() to run the example prompt chains

Initial steps

Launch Cloud9 IDE with SSM option
When it launchers, open the Cloud9 IDE in the AWS Console

With SSM

Install:

AWS CLI

	from fasthtml.common import *
	from datetime import datetime

	def render(todo):
	show = AX(todo.title, f'/todos/{todo.id}', 'current-todo')
	edit = AX('edit', f'/edit/{todo.id}' , 'current-todo')
	dt = ' (done)' if todo.done else ''
	return Li(show, dt, ' \| ', edit, id=f'todo-{todo.id}')

	app,rt,todos,Todo = fast_app('data/todos.db', render, id=int, title=str, done=bool, pk='id', live=True)

	from langchain.chat_models import ChatOpenAI
	from langchain.prompts import ChatPromptTemplate
	from langchain.schema.output_parser import StrOutputParser
	import requests
	from bs4 import BeautifulSoup
	from langchain.schema.runnable import RunnablePassthrough, RunnableLambda
	from langchain.utilities import DuckDuckGoSearchAPIWrapper
	import json

	RESULTS_PER_QUESTION = 3

	# %%
	import os
	import openai
	# import autogen
	from autogen import Agent, ConversableAgent, oai, UserProxyAgent, AssistantAgent
	import types
	from dotenv import load_dotenv, find_dotenv
	from typing import Any, Callable, Dict, List, Optional, Tuple, Type, Union

	_ = load_dotenv(find_dotenv()) # read local .env file