import streamlit as st import spacy import wikipediaapi import wikipedia from wikipedia.exceptions import DisambiguationError from transformers import TFAutoModel, AutoTokenizer import numpy as np import pandas as pd import faiss import datetime import time try: nlp = spacy.load("en_core_web_sm") except: spacy.cli.download("en_core_web_sm") nlp = spacy.load("en_core_web_sm") wh_words = ['what', 'who', 'how', 'when', 'which'] def get_concepts(text): text = text.lower() doc = nlp(text) concepts = [] for chunk in doc.noun_chunks: if chunk.text not in wh_words: concepts.append(chunk.text) return concepts def get_passages(text, k=100): doc = nlp(text) passages = [] passage_len = 0 passage = "" sents = list(doc.sents) for i in range(len(sents)): sen = sents[i] passage_len += len(sen) if passage_len >= k: passages.append(passage) passage = sen.text passage_len = len(sen) continue elif i == (len(sents) - 1): passage += " " + sen.text passages.append(passage) passage = "" passage_len = 0 continue passage += " " + sen.text return passages def get_dicts_for_dpr(concepts, n_results=20, k=100): dicts = [] for concept in concepts: wikis = wikipedia.search(concept, results=n_results) st.write(f"{concept} No of Wikis: {len(wikis)}") for wiki in wikis: try: html_page = wikipedia.page(title=wiki, auto_suggest=False) except DisambiguationError: continue htmlResults = html_page.content passages = get_passages(htmlResults, k=k) for passage in passages: i_dicts = {} i_dicts['text'] = passage i_dicts['title'] = wiki dicts.append(i_dicts) return dicts passage_encoder = TFAutoModel.from_pretrained("nlpconnect/dpr-ctx_encoder_bert_uncased_L-2_H-128_A-2") query_encoder = TFAutoModel.from_pretrained("nlpconnect/dpr-question_encoder_bert_uncased_L-2_H-128_A-2") p_tokenizer = AutoTokenizer.from_pretrained("nlpconnect/dpr-ctx_encoder_bert_uncased_L-2_H-128_A-2") q_tokenizer = AutoTokenizer.from_pretrained("nlpconnect/dpr-question_encoder_bert_uncased_L-2_H-128_A-2") def get_title_text_combined(passage_dicts): res = [] for p in passage_dicts: res.append(tuple((p['title'], p['text']))) return res def extracted_passage_embeddings(processed_passages, max_length=156): passage_inputs = p_tokenizer.batch_encode_plus( processed_passages, add_special_tokens=True, truncation=True, padding="max_length", max_length=max_length, return_token_type_ids=True ) passage_embeddings = passage_encoder.predict([np.array(passage_inputs['input_ids']), np.array(passage_inputs['attention_mask']), np.array(passage_inputs['token_type_ids'])], batch_size=64, verbose=1) return passage_embeddings def extracted_query_embeddings(queries, max_length=64): query_inputs = q_tokenizer.batch_encode_plus( queries, add_special_tokens=True, truncation=True, padding="max_length", max_length=max_length, return_token_type_ids=True ) query_embeddings = query_encoder.predict([np.array(query_inputs['input_ids']), np.array(query_inputs['attention_mask']), np.array(query_inputs['token_type_ids'])], batch_size=1, verbose=1) return query_embeddings def get_pagetext(page): s = str(page).replace("/t","") return s def get_wiki_summary(search): wiki_wiki = wikipediaapi.Wikipedia('en') page = wiki_wiki.page(search) def get_wiki_summaryDF(search): wiki_wiki = wikipediaapi.Wikipedia('en') page = wiki_wiki.page(search) isExist = page.exists() if not isExist: return isExist, "Not found", "Not found", "Not found", "Not found" pageurl = page.fullurl pagetitle = page.title pagesummary = page.summary[0:60] pagetext = get_pagetext(page.text) backlinks = page.backlinks linklist = "" for link in backlinks.items(): pui = link[0] linklist += pui + " , " a=1 categories = page.categories categorylist = "" for category in categories.items(): pui = category[0] categorylist += pui + " , " a=1 links = page.links linklist2 = "" for link in links.items(): pui = link[0] linklist2 += pui + " , " a=1 sections = page.sections ex_dic = { 'Entity' : ["URL","Title","Summary", "Text", "Backlinks", "Links", "Categories"], 'Value': [pageurl, pagetitle, pagesummary, pagetext, linklist,linklist2, categorylist ] } df = pd.DataFrame(ex_dic) return df def save_message(name, message): now = datetime.datetime.now() timestamp = now.strftime("%Y-%m-%d %H:%M:%S") with open("chat.txt", "a") as f: f.write(f"{timestamp} - {name}: {message}\n") def press_release(): st.markdown("""🎉🎊 Breaking News! 📢📣 Introducing StreamlitWikipediaChat - the ultimate way to chat with Wikipedia and the whole world at the same time! 🌎📚👋 Are you tired of reading boring articles on Wikipedia? Do you want to have some fun while learning new things? Then StreamlitWikipediaChat is just the thing for you! 😃💻 With StreamlitWikipediaChat, you can ask Wikipedia anything you want and get instant responses! Whether you want to know the capital of Madagascar or how to make a delicious chocolate cake, Wikipedia has got you covered. 🍰🌍 But that's not all! You can also chat with other people from around the world who are using StreamlitWikipediaChat at the same time. It's like a virtual classroom where you can learn from and teach others. 🌐👨‍🏫👩‍🏫 And the best part? StreamlitWikipediaChat is super easy to use! All you have to do is type in your question and hit send. That's it! 🤯🙌 So, what are you waiting for? Join the fun and start chatting with Wikipedia and the world today! 😎🎉 StreamlitWikipediaChat - where learning meets fun! 🤓🎈""") def main(): st.title("Streamlit Chat") name = st.text_input("Enter your name") message = st.text_input("Enter a topic to share from Wikipedia") if st.button("Submit"): # wiki df = get_wiki_summaryDF(message) save_message(name, message) save_message(name, df) st.text("Message sent!") st.text("Chat history:") with open("chat.txt", "a+") as f: f.seek(0) chat_history = f.read() #st.text(chat_history) st.markdown(chat_history) countdown = st.empty() t = 60 while t: mins, secs = divmod(t, 60) countdown.text(f"Time remaining: {mins:02d}:{secs:02d}") time.sleep(1) t -= 1 if t == 0: countdown.text("Time's up!") with open("chat.txt", "a+") as f: f.seek(0) chat_history = f.read() #st.text(chat_history) st.markdown(chat_history) press_release() t = 60 if __name__ == "__main__": main()