You'll need ripgrep
and pandoc
to get started. You can read more about ripgrep here and pandoc here. I use both of these frequently and they're quite helpful.
You can install them both with homebrew
:
brew install pandoc ripgrep
#!/usr/bin/env python3 | |
""" | |
Apply database patches. | |
Applied patches are recorded in the schema_patch table of the database. | |
The dsn to connect to defaults to a local one (empty connection string). It can | |
be chosen using the command line or an environment variable. Patches | |
application is interactive by default. |
""" | |
Located under app/ | |
""" | |
import os | |
from django.apps import apps | |
from django.conf import settings | |
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "settings") |
<? | |
# MIT license, do whatever you want with it | |
# | |
# This is my invoice.php page which I use to make invoices that customers want, | |
# with their address on it and which are easily printable. I love Stripe but | |
# their invoices and receipts were too wild for my customers on Remote OK | |
# | |
require_once(__DIR__.'/../vendor/autoload.php'); |
use any_ascii::any_ascii_char; | |
use unicode_normalization::UnicodeNormalization; | |
use unicode_segmentation::UnicodeSegmentation; | |
use crate::sqlite3_fts5::Tokenizer; | |
/// My own tokenizer | |
/// | |
/// The operations the tokenizer performs, in order: | |
/// 1. Splits data on Unicode-defined words (`UnicodeSegmentation::unicode_word_indices`). |
# From https://stackoverflow.com/a/68876046/1319998, which is itself inspired by https://stackoverflow.com/a/68814418/1319998 | |
from contextlib import contextmanager | |
from collections import namedtuple | |
from ctypes import cdll, byref, string_at, c_char_p, c_int, c_double, c_int64, c_void_p | |
from ctypes.util import find_library | |
from sys import platform | |
def query(db_file, sql, params=()): |
Apologies for the snarky title, but there has been a huge amount of discussion around so called "Prompt Engineering" these past few months on all kinds of platforms. Much of it is coming from individuals who are peddling around an awful lot of "Prompting" and very little "Engineering".
Most of these discussions are little more than users finding that writing more creative and complicated prompts can help them solve a task that a more simple prompt was unable to help with. I claim this is not Prompt Engineering. This is not to say that crafting good prompts is not a difficult task, but it does not involve doing any kind of sophisticated modifications to general "template" of a prompt.
Others, who I think do deserve to call themselves "Prompt Engineers" (and an awful lot more than that), have been writing about and utilizing the rich new eco-system