RohanAwhad

// Updated extractLinkedInPosts function with continuous scrolling
async function extractLinkedInPosts() {
    const postsData = [];
    const seenTexts = new Set();
    let lastLength = 0;

    while (postsData.length < 20) {
        window.scrollTo(0, document.body.scrollHeight);
        await new Promise(resolve => setTimeout(resolve, 2000)); // Wait for more posts to load

RohanAwhad

(function() {
    // Initialize an array to hold the conversation data
    let conversationData = [];

    // Select all conversation blocks
    let conversationBlocks = document.querySelectorAll('[data-testid^="conversation-turn"]');

    conversationBlocks.forEach(block => {
        // Determine the role directly from data attributes in the HTML
        let roleElement = block.querySelector('[data-message-author-role]');

RohanAwhad

function extractRowData(rowElement) {
  // Function to extract text or attribute from an element if it exists
  function getElementData(selector, attribute = 'text') {
      const element = rowElement.querySelector(selector);
      if (!element) return null;
      if (attribute === 'text') return element.textContent.trim();
      return element.getAttribute(attribute);
  }

  // Extracting the values based on their aria-label, role, or data-* attributes

RohanAwhad

function sleep(ms) {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

function clickShowTranscriptButton() {
  // Selecting the button based on its class and aria-label
  var buttons = document.querySelectorAll(
    "button.yt-spec-button-shape-next.yt-spec-button-shape-next--outline.yt-spec-button-shape-next--call-to-action.yt-spec-button-shape-next--size-m"
  );

RohanAwhad

# Inspiration from Eric Hartford github2file: https://github.com/cognitivecomputations/github2file

"""
A utility script to download and process files from a GitHub repository based on language-specific criteria.

Features:
- Download files from a specific branch or tag of a GitHub repository.
- Filter files based on their extension to include only those relevant to the specified programming language.
- Exclude files located in certain directories or those that match a set of predefined non-useful criteria.
- Check and exclude test files based on content indicators specific to each supported language.

RohanAwhad

--[[

=====================================================================
==================== READ THIS BEFORE CONTINUING ====================
=====================================================================
========                                    .-----.          ========
========         .----------------------.   | === |          ========
========         |.-""""""""""""""""""-.|   |-----|          ========
========         ||                    ||   | === |          ========
========         ||   KICKSTART.NVIM   ||   |-----|          ========

RohanAwhad

import dataclasses
import openai
import os
import re
import yaml

from pydantic import BaseModel, ValidationError
from typing import Optional

RohanAwhad

from transformers import AutoTokenizer, AutoModel
import torch


# MODEL CKPT is downloaded from: "jinaai/jina-embeddings-v2-base-en"  # has context len of 8192
MODEL_CKPT = "/Users/rohan/3_Resources/ai_models/jina-embeddings-v2-base-en"

def recursive_splitter(text: str, separators: list[str], chunk_size: int) -> list[str]:
  if len(separators) == 0:
    words = text.strip().split(' ')

RohanAwhad

import base64
import cv2
import os
import openai
import whisper
import pyaudio
import wave
import uuid
import threading
from queue import Queue

RohanAwhad

import json
import openai
from typing import Any
from jupyter_client.manager import KernelManager

kernel_manager: KernelManager = None
def execute_code_in_notebook(code: str) -> list[Any]:
  if not code: return []
  global kernel_manager
  if kernel_manager is None: