awacke1 commited on
Commit
c40be42
Β·
1 Parent(s): 328ed11

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +97 -2
app.py CHANGED
@@ -7,6 +7,9 @@ from transformers import TFAutoModel, AutoTokenizer
7
  import numpy as np
8
  import pandas as pd
9
  import faiss
 
 
 
10
 
11
  try:
12
  nlp = spacy.load("en_core_web_sm")
@@ -110,8 +113,6 @@ def extracted_query_embeddings(queries, max_length=64):
110
  verbose=1)
111
  return query_embeddings
112
 
113
- #Wikipedia API:
114
-
115
  def get_pagetext(page):
116
  s = str(page).replace("/t","")
117
  return s
@@ -119,3 +120,97 @@ def get_pagetext(page):
119
  def get_wiki_summary(search):
120
  wiki_wiki = wikipediaapi.Wikipedia('en')
121
  page = wiki_wiki.page(search)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  import numpy as np
8
  import pandas as pd
9
  import faiss
10
+ import datetime
11
+ import time
12
+
13
 
14
  try:
15
  nlp = spacy.load("en_core_web_sm")
 
113
  verbose=1)
114
  return query_embeddings
115
 
 
 
116
  def get_pagetext(page):
117
  s = str(page).replace("/t","")
118
  return s
 
120
  def get_wiki_summary(search):
121
  wiki_wiki = wikipediaapi.Wikipedia('en')
122
  page = wiki_wiki.page(search)
123
+
124
+
125
+ def get_wiki_summaryDF(search):
126
+ wiki_wiki = wikipediaapi.Wikipedia('en')
127
+ page = wiki_wiki.page(search)
128
+
129
+ isExist = page.exists()
130
+ if not isExist:
131
+ return isExist, "Not found", "Not found", "Not found", "Not found"
132
+
133
+ pageurl = page.fullurl
134
+ pagetitle = page.title
135
+ pagesummary = page.summary[0:60]
136
+ pagetext = get_pagetext(page.text)
137
+
138
+ backlinks = page.backlinks
139
+ linklist = ""
140
+ for link in backlinks.items():
141
+ pui = link[0]
142
+ linklist += pui + " , "
143
+ a=1
144
+
145
+ categories = page.categories
146
+ categorylist = ""
147
+ for category in categories.items():
148
+ pui = category[0]
149
+ categorylist += pui + " , "
150
+ a=1
151
+
152
+ links = page.links
153
+ linklist2 = ""
154
+ for link in links.items():
155
+ pui = link[0]
156
+ linklist2 += pui + " , "
157
+ a=1
158
+
159
+ sections = page.sections
160
+
161
+ ex_dic = {
162
+ 'Entity' : ["URL","Title","Summary", "Text", "Backlinks", "Links", "Categories"],
163
+ 'Value': [pageurl, pagetitle, pagesummary, pagetext, linklist,linklist2, categorylist ]
164
+ }
165
+
166
+ df = pd.DataFrame(ex_dic)
167
+
168
+ return df
169
+
170
+
171
+ def save_message(name, message):
172
+ now = datetime.datetime.now()
173
+ timestamp = now.strftime("%Y-%m-%d %H:%M:%S")
174
+ with open("chat.txt", "a") as f:
175
+ f.write(f"{timestamp} - {name}: {message}\n")
176
+
177
+ def main():
178
+ st.title("Streamlit Chat")
179
+
180
+ name = st.text_input("Name")
181
+ message = st.text_input("Message")
182
+ if st.button("Submit"):
183
+
184
+ # wiki
185
+ df = get_wiki_summaryDF(message)
186
+
187
+ save_message(name, message)
188
+ save_message(name, df)
189
+
190
+ st.text("Message sent!")
191
+
192
+
193
+ st.text("Chat history:")
194
+ with open("chat.txt", "a+") as f:
195
+ f.seek(0)
196
+ chat_history = f.read()
197
+ st.text(chat_history)
198
+
199
+ countdown = st.empty()
200
+ t = 60
201
+ while t:
202
+ mins, secs = divmod(t, 60)
203
+ countdown.text(f"Time remaining: {mins:02d}:{secs:02d}")
204
+ time.sleep(1)
205
+ t -= 1
206
+ if t == 0:
207
+ countdown.text("Time's up!")
208
+ with open("chat.txt", "a+") as f:
209
+ f.seek(0)
210
+ chat_history = f.read()
211
+ st.text(chat_history)
212
+ t = 60
213
+
214
+ if __name__ == "__main__":
215
+ main()
216
+