UMAR798 commited on
Commit
a1c67ef
·
verified ·
1 Parent(s): bcc3438

Upload app.py

Browse files
Files changed (1) hide show
  1. app.py +72 -0
app.py ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import re
2
+ import nltk
3
+ import gradio as gr
4
+ from nltk.corpus import stopwords
5
+ from sklearn.feature_extraction.text import TfidfVectorizer
6
+ from sklearn.metrics.pairwise import cosine_similarity
7
+
8
+ nltk.download("stopwords", quiet=True)
9
+
10
+ faq_data = {
11
+ "What is Artificial Intelligence?":"Artificial Intelligence (AI) is the simulation of human intelligence by machines.",
12
+ "What is Machine Learning?":"Machine Learning is a subset of AI that enables computers to learn from data.",
13
+ "What is Deep Learning?":"Deep Learning is a branch of Machine Learning based on neural networks.",
14
+ "What is NLP?":"Natural Language Processing enables computers to understand human language.",
15
+ "What is Python?":"Python is a programming language widely used for AI and web development.",
16
+ "Who developed Python?":"Python was created by Guido van Rossum.",
17
+ "What is Hugging Face?":"Hugging Face is a platform for machine learning models and datasets.",
18
+ "What is Google Colab?":"Google Colab is a free cloud notebook for Python.",
19
+ "What is Gradio?":"Gradio lets you build web interfaces for Python models.",
20
+ "What is cosine similarity?":"Cosine similarity measures similarity between text vectors."
21
+ }
22
+
23
+ stop_words=set(stopwords.words("english"))
24
+
25
+ def preprocess(text):
26
+ text=text.lower()
27
+ text=re.sub(r"[^a-z0-9 ]"," ",text)
28
+ return " ".join([w for w in text.split() if w not in stop_words])
29
+
30
+ questions=list(faq_data.keys())
31
+ answers=list(faq_data.values())
32
+
33
+ vectorizer=TfidfVectorizer()
34
+ X=vectorizer.fit_transform([preprocess(q) for q in questions])
35
+
36
+ def chatbot(msg,history):
37
+ if not msg.strip():
38
+ return "",history
39
+ vec=vectorizer.transform([preprocess(msg)])
40
+ sims=cosine_similarity(vec,X)[0]
41
+ idx=sims.argmax()
42
+ if sims[idx] < 0.25:
43
+ ans="Sorry, I couldn't find a relevant answer."
44
+ else:
45
+ ans=answers[idx]
46
+ history=history or []
47
+ history.append({"role":"user","content":msg})
48
+ history.append({"role":"assistant","content":ans})
49
+ return "",history
50
+
51
+ css="""
52
+ .gradio-container{max-width:1000px!important}
53
+ footer{display:none}
54
+ """
55
+
56
+ with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
57
+ gr.Markdown("# 🤖 FAQ Chatbot\nAsk a question from the FAQ database.")
58
+ chat=gr.Chatbot(type="messages",height=450)
59
+ with gr.Row():
60
+ txt=gr.Textbox(placeholder="Ask your question...",scale=8)
61
+ btn=gr.Button("Send")
62
+ clr=gr.Button("Clear")
63
+ gr.Examples(
64
+ examples=[["What is AI?"],["What is Python?"],["What is Hugging Face?"]],
65
+ inputs=txt
66
+ )
67
+ btn.click(chatbot,[txt,chat],[txt,chat])
68
+ txt.submit(chatbot,[txt,chat],[txt,chat])
69
+ clr.click(lambda:("",[]),outputs=[txt,chat])
70
+
71
+ if __name__=="__main__":
72
+ demo.launch()