StudyBuddy-FAQ-Chatbot/chatbot.py at main · vortex-001/StudyBuddy-FAQ-Chatbot · GitHub

1
2
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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
import json
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity


class FAQChatbot:

    def __init__(self, file_name):

        with open(file_name, "r", encoding="utf-8") as file:
            self.data = json.load(file)

        self.questions = []

        for item in self.data:
            self.questions.append(item["question"])

        self.vectorizer = TfidfVectorizer()

        self.vectors = self.vectorizer.fit_transform(self.questions)

        self.replies = {

            "hi": "Hello! How can I help you today?",

            "hello": "Hi! Ask me anything about StudyBuddy.",

            "hey": "Hey! What would you like to know?",

            "good morning": "Good Morning! 😊",

            "good afternoon": "Good Afternoon! 😊",

            "good evening": "Good Evening! 😊",

            "how are you": "I'm doing great. Thanks for asking!",

            "who are you": "I'm StudyBuddy FAQ Chatbot.",

            "who made you": "I was developed by Harsh Garg during the CodeAlpha AI Internship.",

            "what can you do": "I can answer questions related to StudyBuddy.",

            "thanks": "You're welcome! 😊",

            "thank you": "Happy to help!",

            "bye": "Goodbye! Have a great day!",

            "goodbye": "See you soon!"
        }

    def get_response(self, question):

        question = question.lower().strip()
        keywords = [
            "studybuddy", "study", "task", "planner", "progress",
            "python", "java", "c++", " c ", "html", "css",
            "javascript", "flutter", "git", "github",
            "ai", "artificial intelligence", "machine learning",
            "deep learning", "nlp", "streamlit",
            "algorithm", "algorithms", "dsa",
            "data structure", "coding", "programming",
            "interview", "exam", "sql", "database",
            "password", "profile", "reminder"
        ]
        if not any(word in f" {question} " for word in keywords):
            return (
                "Sorry, I couldn't understand that question. 😊\n\n"
                "I can answer questions related to:\n"
                "• StudyBuddy\n"
                "• Programming\n"
                "• Artificial Intelligence\n"
                "• Machine Learning\n\n"
                "Example questions:\n"
                "• What is Python?\n"
                "• What is Java?\n"
                "• What is StudyBuddy?\n"
                "• What is Machine Learning?"
            )
        for word, reply in self.replies.items():

            if word in question:
                return reply

        user_vector = self.vectorizer.transform([question])

        score = cosine_similarity(user_vector, self.vectors)

        index = score.argmax()

        confidence = score[0][index]
        print("Best Match:", self.data[index]["question"])
        print("Confidence:", confidence)


        if confidence < 0.50:

            text = "Sorry, I don't know the answer to that.\n\n"

            text += "You can ask questions like:\n\n"

            for item in self.data[:5]:
                text += f"• {item['question']}\n"

            return text

        return self.data[index]["answer"]

    def get_questions(self):
        return self.questions