hourianto

Current WebSim prompts and main context. System/User/Assistant blocks denote different roles in the messages array for the API requests. Stuff in {} is either a file that's too big to be inserted directly, or an explanation.

From what I can see, WebSim is mostly "carried" by Claude's creativity.

• Main prompt: main_prompt.txt - also check main_flow.txt to see how a complete request is made.
• Edit prompt: edit_prompt.txt- used when right-click editing the element. Uses the currently selected model. I didn't manage to get the whole prompt with the examples, but most of it at least.
• Fake LLM API prompt: api_prompt.txt - currently WebSim always uses Claude 3.5 Sonnet for this (from info on Discord).
• Image rewriting prompt: image_gen_prompt.txt - also uses Claude (don't know what model). Not sure what image model is being used, probably some version SDXL (like SDXL Turbo and similar)

The temperature used is 1, at least for Claude.

kumorikuma

# Requirements:
# - ImageMagick binary
# - Windows.Media.Ocr.Cli binary
# - VideoSubFinder binary
#
# Official GCloud Translate Setup:
# First 500k characters / mo is free: https://cloud.google.com/translate/pricing
# Install Python Module: pip install google-cloud-translate
# Setup Google Cloud account and billing information: https://cloud.google.com/
# Make a new project and enable "Cloud Translation API": https://console.cloud.google.com/apis/dashboard

kettanaito

Chromium on Vercel (serverless)

This is an up-to-date guide on running Chromium in Vercel serverless functions in 2022. What you will read below is the result of two days of research, debugging, 100+ failed deployments, and a little bit of stress.

Getting started

Step 1: Install dependencies

Use chrome-aws-lambda that comes with Chromium pre-configured to run in serverless, and puppeteer-core due to the smaller size of Chromium distributive.

ESWZY

# Simplified version and explanation at: https://stackoverflow.com/a/64439347/12866353

import os
import ffmpeg

def compress_video(video_full_path, size_upper_bound, two_pass=True, filename_suffix='cps_'):
    """
    Compress video file to max-supported size.
    :param video_full_path: the video you want to compress.
    :param size_upper_bound: Max video size in KB.

Zate

# updates etc
sudo apt update
sudo apt upgrade -y
# install pre-reqs
sudo apt install tasksel -y
# get the file
wget https://dl.google.com/linux/direct/chrome-remote-desktop_current_amd64.deb
sudo dpkg --install chrome-remote-desktop_current_amd64.deb
sudo apt install --assume-yes --fix-broken
sudo tasksel install ubuntu-desktop

erikig

loughlincodes

...
...

{%- assign percentageDiscount = product.compare_at_price_max | minus: product.price | times: 100.0 | divided_by: product.compare_at_price_max | money_without_currency | times: 100 | remove: '.0' -%}

{% if product.compare_at_price_max > product.price %}
  <div class="sale-banner"><span>{{ 'collections.general.sale' | t }}</span><p>{{percentageDiscount}}%<span>OFF!</span></div>
{% endif %}

...

carlosplanchon

#!/usr/bin/env python3

from inspect import _empty, signature


def get_multiparameter_callback(callback, **parameters):
    callback_sig_p = signature(callback).parameters
    # If some provider parameter does not belong to callback parameters.
    unexpected_parameters = list(parameters.keys() - callback_sig_p.keys())
    if len(unexpected_parameters) > 0:

mrf345

#!/bin/bash
pyinstaller -F -w \
--hidden-import='email.mime.multipart' \
--hidden-import='email.mime.message' \
--hidden-import='email.mime.text' \
--hidden-import='email.mime.image' \
--hidden-import='email.mime.audio' \
--hidden-import='sqlalchemy.sql.default_comparator' \
--hidden-import='jinja2' \
main.py

fabtho

#!/usr/bin/python
from selenium import webdriver
from PIL import Image
from cStringIO import StringIO

verbose = 1

browser = webdriver.Firefox()
browser.get('http://stackoverflow.com/questions/37906704/taking-a-whole-page-screenshot-with-selenium-marionette-in-python')