naufalso

import difflib

def extract_line_differences(source: str, modified: str) -> dict:
    """
    Extracts line-level differences between two multi-line strings and returns a dictionary where:
      - For replacements: key is the differing block of lines in the source and 
        value is the corresponding block of lines in the modified string.
      - For deletions: key is the block of lines deleted from the source, value is an empty string.
      - For insertions: key is a string indicating the insertion location (e.g., "INSERT_AT_LINE_#")
        and value is the inserted block of lines from the modified string.

naufalso

# Author: Naufal Suryanto

import requests
import re
from markdownify import markdownify as md
from urllib.parse import urlparse

def fetch_url_readme_from_git(url):
    """
    Fetch the README file content from a Git repository given a URL.

naufalso

import weave
import pandas as pd
from tqdm import tqdm

def get_calls(project_id, op_name, parent_id = None):
    client = weave.init(project_id)
    query_data = {
        "project_id": project_id,
        "filter": {"op_names": [op_name]},
        "sort_by": [{"field": "started_at", "direction": "desc"}],

naufalso

#!/usr/bin/env python3
"""
Markdown Image Descriptor Script

This script processes a markdown file, extracts images, encodes them in base64,
and sends them with contextual text to a Visual Language Model (VLM) for description extraction.
The image markdown references are then replaced with the structured descriptions provided by the model.
If an image is deemed non-important (e.g., logos) it is replaced with a markdown comment.
Additionally, if an image contains text information (e.g., terminal screenshots, tables, code snippets),
the VLM is instructed to extract and return only the text content using markdown formatting.

naufalso

from typing import Dict, Union
from huggingface_hub import get_safetensors_metadata
import argparse
import sys

# Example: 
# python get_gpu_memory.py Qwen/Qwen2.5-7B-Instruct

# Dictionary mapping dtype strings to their byte sizes
bytes_per_dtype: Dict[str, float] = {

naufalso

import cv2
import numpy as np
import matplotlib.pyplot as plt
import argparse


# --------------------------
# Utility Functions
# --------------------------

naufalso

import os
import re
import base64
import argparse
from typing import List, Dict, Any
from datasets import Dataset

def embed_images_in_markdown(markdown_text: str, base_path: str = ".") -> str:
    """
    Embed images in markdown text as base64 encoded strings.

naufalso

import sqlite3
import pandas as pd
from datetime import datetime, timedelta

# Path to your Chrome history database [Select one based on your os and chrome history path]
history_path = "C:\\Users\\[USER_NAME]\\AppData\\Local\\Google\\Chrome\\User Data\\Default\\History" # Windows
history_path = "~/Library/Application Support/Google/Chrome/Default/History" # MAC
history_path = "~/.config/google-chrome/Default/History" # Linux

# Connect to the database

naufalso

#!/bin/bash

# initialize a semaphore with a given number of tokens
open_sem(){
    mkfifo pipe-$$
    exec 3<>pipe-$$
    rm pipe-$$
    local i=$1
    for((;i>0;i--)); do
        printf %s 000 >&3

naufalso

#!/bin/bash

# Check if the correct number of arguments is provided
if [ "$#" -ne 2 ]; then
    echo "Usage: $0 <input_directory> <output_file>"
    exit 1
fi

# Assign input arguments to variables
input_dir="$1"