AshtonIzmev

def diciter(d, pad="", list_idx=0):
    for k, v in d.items():
        if isinstance(v, str):
            print(f"{pad}KEY: {k} -> {v[:100]}")
        elif isinstance(v, int) or isinstance(v, float) or isinstance(v, bool):
            print(f"{pad}KEY: {k} -> {v}")
        elif isinstance(v, dict):
            print(f"{pad}KEY: {k} ")
            diciter(v, pad + "   ")
        elif isinstance(v, list):

AshtonIzmev

#%pip install sentence_transformers
#%pip install torch

###########################

import os
os.environ["TOKENIZERS_PARALLELISM"] = "true"

import torch
from sentence_transformers import SentenceTransformer

AshtonIzmev

import requests
import os
import time
from urllib.parse import urlparse
from cvs import cvs

# Fake user agent to mimic a real browser
headers = {

AshtonIzmev

#%pip install openai

from openai import OpenAI
import os
import subprocess
from pydub import AudioSegment
import math


client = OpenAI(api_key="sk-proj-XXX")

AshtonIzmev

const bcrypt = require('bcryptjs');
const CryptoJS = require('crypto-js');

// Generate a strong random password (16 characters, mix of letters, numbers, symbols)
const strongPassword = 'my!!!strong!!password!';
console.log('Strong password:', strongPassword);

// Generate bcrypt hash
const passwordHash = bcrypt.hashSync(strongPassword, 12);
console.log('Password hash:', passwordHash);

AshtonIzmev

const mapStyle = `https://api.maptiler.com/maps/dataviz/style.json?key=${apiKey}`;

map.current = new maplibregl.Map({
    container: mapContainer.current,
    style: mapStyle,
    center: [INITIAL_VIEW_STATE.longitude, INITIAL_VIEW_STATE.latitude],
    zoom: INITIAL_VIEW_STATE.zoom
});

map.current.on('load', () => {

AshtonIzmev

from typing import List, Dict, Optional
from utils import count_tokens, pdf_to_text_with_fonts_pdfplumber
import logging

# Configure logging for the chunker
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

class FontAwareRecursiveChunker:
    """A recursive text chunker that uses font sizes to determine optimal split points.

AshtonIzmev

import enum

class MimeType(str, enum.Enum):
    # Text documents
    TXT = "text/plain"
    PDF = "application/pdf"
    DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
    PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
    

AshtonIzmev

import os
import sys
from datetime import datetime
from cryptography.hazmat.primitives import hashes
from cryptography.hazmat.primitives.asymmetric import rsa, padding
from cryptography.exceptions import InvalidSignature
from cryptography.hazmat.primitives import serialization


def get_private_key():

AshtonIzmev

from openai import OpenAI

client = OpenAI(api_key='sk-proj-XXX')

def gpt_request(prompt, model="gpt-4o-mini", max_tokens=100):
    try:
        response = client.chat.completions.create(
            model=model,
            messages=[{"role": "user", "content": prompt}],
            max_tokens=max_tokens,