fsndzomga

import json
import boto3
newline, bold, unbold = "\n", "\033[1m", "\033[0m"
endpoint_name = "name_of_your_endpoint"


def query_endpoint(payload):
    client = boto3.client("runtime.sagemaker", region_name="us-east-1")
    response = client.invoke_endpoint(
        EndpointName=endpoint_name, InferenceComponentName='huggingface-llm-mistral-7b-20240210-171055', ContentType="application/json", Body=json.dumps(payload).encode("utf-8")

fsndzomga

require 'nokogiri'
require 'watir'
require 'webdrivers'

def count_happy_scribe_ruby(url)
  browser = Watir::Browser.new :chrome, headless: true
  browser.goto(url)

  browser.execute_script("window.scrollTo(0, document.body.scrollHeight)")
  sleep(10) # Wait a bit more for content to load

fsndzomga

const puppeteer = require('puppeteer');

// Custom delay function
function delay(time) {
    return new Promise(function(resolve) {
        setTimeout(resolve, time);
    });
}

async function countHappyScribeJavaScript(url) {

fsndzomga

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
import time


def count_happy_scribe_selenium(url):
    # Set up Chrome options
    chrome_options = webdriver.ChromeOptions()
    chrome_options.add_argument("--headless")  # Run Chrome in headless mode

fsndzomga

import base64
import os
import requests
from dotenv import load_dotenv
from PIL import Image, ImageOps

# Load environment variables
load_dotenv()

api_key = os.getenv("STABILITY_API_KEY")

fsndzomga

import base64
import os
import requests
from dotenv import load_dotenv
from PIL import Image, ImageOps

# Load environment variables
load_dotenv()

def calculate_best_fit_dimension(original_width, original_height, target_dimensions):

fsndzomga

from ragatouille import RAGPretrainedModel
from ragatouille.utils import get_wikipedia_page


topics = ["Barack_Obama", "Nelson_Mandela", "king"]

RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")

my_documents = []

fsndzomga

import requests
from yahooquery import Ticker
import dspy
from config import OPENAI_API_KEY, SERPAPI_API_KEY

llm = dspy.OpenAI(model='gpt-3.5-turbo',api_key=OPENAI_API_KEY, max_tokens=2000)

dspy.settings.configure(lm=llm)

fsndzomga

from dspy.evaluate.evaluate import Evaluate

evaluator = Evaluate(devset=devset, num_threads=1, display_progress=True, display_table=10)

evaluator(compiled_lie_detector, metric=answer_exact_match)

fsndzomga

from dspy.teleprompt import BootstrapFewShot
from dspy.evaluate import answer_exact_match

text = "Barack Obama was not President of the USA"

# define the fact as input to the lie detector
trainset = [x.with_inputs('fact') for x in few_shot_examples]

# define the signature to be used in by the lie detector module
# for the evaluation, you need to define an answer field