Duplicate from awacke1/StreamlitWikipediaChat

Co-authored-by: Aaron C Wacker <awacke1@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: 🌎📚👋Streamlit-Wikipedia-Chat
+emoji: 🌐👨‍🏫👩‍🏫
+colorFrom: red
+colorTo: pink
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: awacke1/StreamlitWikipediaChat
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,239 @@
+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()
+

requirements.txt

@@ -0,0 +1,10 @@
+wikipedia
+spacy
+faiss-cpu
+pandas
+transformers
+tensorflow
+wikipedia-api
+beautifulsoup4
+streamlit
+requests