Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,69 +1,112 @@
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
-
from
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
""
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
""
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
),
|
| 59 |
-
],
|
| 60 |
-
)
|
| 61 |
|
| 62 |
-
|
| 63 |
-
with gr.Sidebar():
|
| 64 |
-
gr.LoginButton()
|
| 65 |
-
chatbot.render()
|
| 66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
|
| 68 |
-
|
| 69 |
-
demo.launch()
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
import nltk
|
| 3 |
import gradio as gr
|
| 4 |
+
from nltk.corpus import stopwords
|
| 5 |
+
from nltk.tokenize import word_tokenize
|
| 6 |
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
| 7 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
| 8 |
+
|
| 9 |
+
# Download NLTK data
|
| 10 |
+
nltk.download("punkt")
|
| 11 |
+
nltk.download("stopwords")
|
| 12 |
+
|
| 13 |
+
# -------------------------------
|
| 14 |
+
# FAQ Dataset
|
| 15 |
+
# -------------------------------
|
| 16 |
+
|
| 17 |
+
faq_data = {
|
| 18 |
+
"What is AI?":
|
| 19 |
+
"Artificial Intelligence is the simulation of human intelligence by machines.",
|
| 20 |
+
|
| 21 |
+
"What is Machine Learning?":
|
| 22 |
+
"Machine Learning is a subset of AI that allows systems to learn from data.",
|
| 23 |
+
|
| 24 |
+
"What is Deep Learning?":
|
| 25 |
+
"Deep Learning is a branch of Machine Learning that uses neural networks.",
|
| 26 |
+
|
| 27 |
+
"Who developed Python?":
|
| 28 |
+
"Python was created by Guido van Rossum.",
|
| 29 |
+
|
| 30 |
+
"What is Hugging Face?":
|
| 31 |
+
"Hugging Face is a platform for Machine Learning models and datasets.",
|
| 32 |
+
|
| 33 |
+
"What is Google Colab?":
|
| 34 |
+
"Google Colab is a free cloud-based Jupyter Notebook service.",
|
| 35 |
+
|
| 36 |
+
"What is NLP?":
|
| 37 |
+
"Natural Language Processing enables computers to understand human language.",
|
| 38 |
+
|
| 39 |
+
"What is Streamlit?":
|
| 40 |
+
"Streamlit is a Python framework used to build data apps.",
|
| 41 |
+
|
| 42 |
+
"What is Gradio?":
|
| 43 |
+
"Gradio is a Python library for creating web interfaces for ML models.",
|
| 44 |
+
|
| 45 |
+
"What is cosine similarity?":
|
| 46 |
+
"Cosine similarity measures how similar two text vectors are."
|
| 47 |
+
}
|
| 48 |
+
|
| 49 |
+
# -------------------------------
|
| 50 |
+
# Text Preprocessing
|
| 51 |
+
# -------------------------------
|
| 52 |
+
|
| 53 |
+
stop_words = set(stopwords.words("english"))
|
| 54 |
+
|
| 55 |
+
def preprocess(text):
|
| 56 |
+
text = text.lower()
|
| 57 |
+
text = re.sub(r'[^a-zA-Z ]', '', text)
|
| 58 |
+
|
| 59 |
+
tokens = word_tokenize(text)
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
+
tokens = [word for word in tokens if word not in stop_words]
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
+
return " ".join(tokens)
|
| 64 |
+
|
| 65 |
+
# Preprocess Questions
|
| 66 |
+
questions = list(faq_data.keys())
|
| 67 |
+
answers = list(faq_data.values())
|
| 68 |
+
|
| 69 |
+
processed_questions = [preprocess(q) for q in questions]
|
| 70 |
+
|
| 71 |
+
# TF-IDF Vectorizer
|
| 72 |
+
vectorizer = TfidfVectorizer()
|
| 73 |
+
|
| 74 |
+
question_vectors = vectorizer.fit_transform(processed_questions)
|
| 75 |
+
|
| 76 |
+
# -------------------------------
|
| 77 |
+
# Chatbot Function
|
| 78 |
+
# -------------------------------
|
| 79 |
+
|
| 80 |
+
def chatbot(user_input):
|
| 81 |
+
|
| 82 |
+
processed_input = preprocess(user_input)
|
| 83 |
+
|
| 84 |
+
input_vector = vectorizer.transform([processed_input])
|
| 85 |
+
|
| 86 |
+
similarities = cosine_similarity(input_vector, question_vectors)
|
| 87 |
+
|
| 88 |
+
best_match = similarities.argmax()
|
| 89 |
+
|
| 90 |
+
score = similarities[0][best_match]
|
| 91 |
+
|
| 92 |
+
if score < 0.25:
|
| 93 |
+
return "Sorry, I couldn't find a relevant answer."
|
| 94 |
+
|
| 95 |
+
return answers[best_match]
|
| 96 |
+
|
| 97 |
+
# -------------------------------
|
| 98 |
+
# Gradio UI
|
| 99 |
+
# -------------------------------
|
| 100 |
+
|
| 101 |
+
demo = gr.Interface(
|
| 102 |
+
fn=chatbot,
|
| 103 |
+
inputs=gr.Textbox(
|
| 104 |
+
lines=2,
|
| 105 |
+
placeholder="Ask a question..."
|
| 106 |
+
),
|
| 107 |
+
outputs="text",
|
| 108 |
+
title="🤖 FAQ Chatbot",
|
| 109 |
+
description="FAQ Chatbot using NLP, TF-IDF and Cosine Similarity"
|
| 110 |
+
)
|
| 111 |
|
| 112 |
+
demo.launch()
|
|
|