import gradio as gr
import pandas as pd
import tiktoken
import pandas as pd
import time
import spacy
from spacy.lang.en.stop_words import STOP_WORDS
from string import punctuation
from collections import Counter
from heapq import nlargest
import nltk
import numpy as np
from tqdm import tqdm
from sentence_transformers import SentenceTransformer, util
from sentence_transformers import SentenceTransformer, CrossEncoder, util
import gzip
import os
import torch
import re
import openai
from openai.embeddings_utils import get_embedding, cosine_similarity
import os


# load_dotenv()
# print(os.getcwd())
# openai.api_key = os.environ['OPENAI_KEY']


df = pd.read_pickle('entire_data.pkl') #to load 123.pkl back to the dataframe df
# model = SentenceTransformer('all-mpnet-base-v2')

# def remove_html_tags(text):
#     clean = re.compile('<.*?>')
#     return re.sub(clean, '', text)

# df['content'] = df.content.apply(lambda x: remove_html_tags(x))
# df['summary_html'] = df.summary_html.apply(lambda x: remove_html_tags(x))
# session_prompt = """ A bot that is open to discussions about different cultural, philosophical and political exchanges. I will use do different analysis to the articles provided to me. Stay truthful and if you weren't provided any resources give your oppinion only."""