File size: 8,403 Bytes
e16a738
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
import os
import streamlit as st
from dotenv import load_dotenv
from langchain.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from langchain.schema import StrOutputParser
from docx import Document
import fitz  # PyMuPDF

def extract_text_from_pdf_or_docx(file):
    """Extract text from PDF or Word document."""
    filename = file.name
    text = ""
    if filename.endswith('.pdf'):
        # Extract text from PDF
        with fitz.open(file) as doc:
            for page in doc:
                text += page.get_text()
    elif filename.endswith('.docx'):
        # Extract text from Word document
        doc = Document(file)
        for paragraph in doc.paragraphs:
            text += paragraph.text + "\n"
    else:
        text = "Unsupported file format. Please upload a PDF or Word document."
    return text

def create_multiple_choice_prompt(num_questions, quiz_context, expertise):
    """Create the prompt template for multiple-choice quiz."""
    template = f"""
You are an expert in {expertise}. Generate a quiz with {num_questions} multiple-choice questions that are relevant to {expertise} based on the following content: {quiz_context}.

The questions should be at the level of {expertise} and should challenge the knowledge of someone proficient in this field.

The format of the quiz is as follows:
- Multiple-choice:
- Questions:
    1. <Question1>:
        a. Answer 1
        b. Answer 2
        c. Answer 3
        d. Answer 4

    2. <Question2>:
        a. Answer 1
        b. Answer 2
        c. Answer 3
        d. Answer 4
    ....
- Answers:
    1. <a|b|c|d>
    2. <a|b|c|d>
    ....
Example:
- Questions:
    1. What is the time complexity of a binary search tree?
        a. O(n)
        b. O(log n)
        c. O(n^2)
        d. O(1)
- Answers:
    1. b
"""
    return template

def create_true_false_prompt(num_questions, quiz_context, expertise):
    """Create the prompt template for true-false quiz."""
    template = f"""
You are an expert in {expertise}. Generate a quiz with {num_questions} true-false questions that are relevant to {expertise} based on the following content: {quiz_context}.

The questions should be at the level of {expertise} and should challenge the knowledge of someone proficient in this field.

The format of the quiz is as follows:
- True-false:
- Questions:
    1. <Question1>: <True|False>
    2. <Question2>: <True|False>
    .....
- Answers:
    1. <True|False>
    2. <True|False>
    .....
Example:
- Questions:
    1. A binary search tree is a type of data structure.
    2. Binary search trees are typically used for sorting and searching operations.
- Answers:
    1. True
    2. True
"""
    return template

def create_open_ended_prompt(num_questions, quiz_context, expertise):
    """Create the prompt template for open-ended quiz."""
    template = f"""
You are an expert in {expertise}. Generate a quiz with {num_questions} open-ended questions that are relevant to {expertise} based on the following content: {quiz_context}.

The questions should be at the level of {expertise} and should challenge the knowledge of someone proficient in this field.

The format of the quiz is as follows:
- Open-ended:
- Questions:
    1. <Question1>
    2. <Question2>
    ....
Example:
- Questions:
    1. What is a binary search tree?
    2. How are binary search trees implemented?
"""
    return template

def create_fill_in_the_blank_prompt(num_questions, quiz_context, expertise):
    """Create the prompt template for fill-in-the-blank quiz."""
    template = f"""
You are an expert in {expertise}. Generate a quiz with {num_questions} fill-in-the-blank questions that are relevant to {expertise} based on the following content: {quiz_context}.

The questions should be at the level of {expertise} and should challenge the knowledge of someone proficient in this field.

The format of the quiz is as follows:
- Fill-in-the-blank:
- Questions:
    1. <Question1>: <Fill-in-the-blank>
    2. <Question2>: <Fill-in-the-blank>
    ....
Example:
- Questions:
    1. A binary search tree is a ________ data structure.
    2. Binary search trees are implemented using ________.
- Answers:
    1. hierarchical
    2. linked lists
"""
    return template

def create_mixed_questions_prompt(num_questions, quiz_context, expertise):
    """Create the prompt template for a mix of all question types."""
    template = f"""
You are an expert in {expertise}. Generate a quiz with {num_questions} questions that include a mix of multiple-choice, true-false, open-ended, and fill-in-the-blank questions relevant to {expertise} based on the following content: {quiz_context}.

The questions should be at the level of {expertise} and should challenge the knowledge of someone proficient in this field.

The format of the quiz is as follows:
- Mixed Questions:
- Questions:
    1. <Question1> (Multiple-choice):
        a. Answer 1
        b. Answer 2
        c. Answer 3
        d. Answer 4

    2. <Question2> (True/False):
        <Question2>: <True|False>

    3. <Question3> (Open-ended):
        <Question3>

    4. <Question4> (Fill-in-the-blank):
        <Question4>: <Fill-in-the-blank>
    ....
- Answers:
    1. <a|b|c|d>
    2. <True|False>
    3. <Open-ended Answer>
    4. <Fill-in-the-blank Answer>
    ....
Example:
- Questions:
    1. What is the time complexity of a binary search tree? (Multiple-choice)
        a. O(n)
        b. O(log n)
        c. O(n^2)
        d. O(1)
    2. A binary search tree is a type of data structure. (True/False)
        True
    3. What is a binary search tree? (Open-ended)
    4. A binary search tree is a ________ data structure. (Fill-in-the-blank)
- Answers:
    1. b
    2. True
    3. A binary search tree is a data structure used to store data in a sorted manner.
    4. hierarchical
"""
    return template

def create_quiz_chain(openai_api_key):
    """Creates the chain for the quiz app."""
    llm = ChatOpenAI(temperature=0.0, openai_api_key=openai_api_key)
    return llm | StrOutputParser()

def split_questions_answers(quiz_response):
    """Function that splits the questions and answers from the quiz response."""
    if "Answers:" in quiz_response:
        questions = quiz_response.split("Answers:")[0]
        answers = quiz_response.split("Answers:")[1]
    else:
        questions = quiz_response
        answers = "Answers section not found in the response."
    return questions, answers

def main():
    st.title("QuesPro")
    st.write("This app generates questions based on the uploaded document.")
    load_dotenv()
    openai_api_key = os.getenv("OPENAI_API_KEY")
    
    uploaded_file = st.file_uploader("Upload a PDF or Word document")
    if uploaded_file is not None:
        text = extract_text_from_pdf_or_docx(uploaded_file)
        num_questions = st.number_input("Enter the number of questions", min_value=1, max_value=10, value=3)
        quiz_type = st.selectbox("Select the quiz type", ["multiple-choice", "true-false", "open-ended", "fill-in-the-blank", "mixed"])
        expertise = st.text_input("Enter the field of expertise for the quiz")

        if st.button("Generate Questions"):
            if quiz_type == "multiple-choice":
                prompt_template = create_multiple_choice_prompt(num_questions, text, expertise)
            elif quiz_type == "true-false":
                prompt_template = create_true_false_prompt(num_questions, text, expertise)
            elif quiz_type == "open-ended":
                prompt_template = create_open_ended_prompt(num_questions, text, expertise)
            elif quiz_type == "fill-in-the-blank":
                prompt_template = create_fill_in_the_blank_prompt(num_questions, text, expertise)
            else:  # mixed
                prompt_template = create_mixed_questions_prompt(num_questions, text, expertise)

            chain = create_quiz_chain(openai_api_key)
            quiz_response = chain.invoke(prompt_template)
            st.write("Quiz Generated!")
            questions, answers = split_questions_answers(quiz_response)
            st.session_state.answers = answers
            st.session_state.questions = questions
            st.write(questions)
    
    if st.button("Show Answers"):
        st.markdown(st.session_state.questions)
        st.write("----")
        st.markdown(st.session_state.answers)

if __name__ == "__main__":
    main()