Upload 3 files

app.py

@@ -3,15 +3,16 @@ from streamlit_chat import message
 from utils import PAGE, read_pdf
 from prompt_generation import OpenAILLM
 from dotenv import load_dotenv
-
 load_dotenv()
 
 
 def init():
     if 'current_page' not in st.session_state:
         st.session_state.current_page = PAGE.MAIN
-        st.session_state.mcq_question_number = 3
-        st.session_state.llm = OpenAILLM(mcq_question_number=st.session_state.mcq_question_number)
+        st.session_state.mcq_question_number = 10
+        st.session_state.mcq_false_answer_number = 3
+        st.session_state.llm = OpenAILLM(mcq_question_number=st.session_state.mcq_question_number,
+                                         mcq_false_answer_number=st.session_state.mcq_false_answer_number)
         st.session_state.chat_start = False
         st.session_state.chat_messages = []
 
@@ -131,35 +132,37 @@ def mcq_page():
 
     # Setup MCQ
     if st.session_state.current_question == 0:
+        # Start MCQ and get the first question and answer
         st.session_state.llm.start_mcq()
+        st.session_state.question, st.session_state.answers = st.session_state.llm.get_mcq_question()
+        st.session_state.current_question += 1
+
+    # Handler when pressing next
+    def increase_current_question():
+        st.session_state.current_question = st.session_state.current_question + 1
+        st.session_state.llm.mcq_record_answer(st.session_state.selected_answer)
+        st.session_state.question, st.session_state.answers = st.session_state.llm.get_mcq_question()
 
     # For every MCQ question
-    if st.session_state.current_question < st.session_state.mcq_question_number:
+    if st.session_state.current_question <= st.session_state.mcq_question_number:
         # QA header
-        st.header(f"Question {st.session_state.current_question + 1} / {st.session_state.mcq_question_number}")
-
-        # Generate the QA text
-        question, answers = st.session_state.llm.get_mcq_question()
+        st.header(f"Question {st.session_state.current_question} / {st.session_state.mcq_question_number}")
 
         # QA form
         with st.form(key='my_form', clear_on_submit=True):
-            selected_answer = st.radio(f"{question}:", answers)
-            send_button = st.form_submit_button(label="Next")
-            if send_button:
-                print("SELECTED ANSWER: ", selected_answer)
-                st.session_state.llm.mcq_record_answer(selected_answer)
-                st.session_state.current_question += 1
+            st.session_state.selected_answer = st.radio(f"{st.session_state.question}:", st.session_state.answers)
+            st.form_submit_button(label="Next", on_click=increase_current_question)
     else:
         # Results header
         st.header("Results")
 
         # For the last QA, show score
-        st.session_state.current_question += 1
+        # st.session_state.current_question += 1
         score, score_perc = st.session_state.llm.get_mcq_score()
         st.markdown("<h4>" + f"Score: {score} / {st.session_state.mcq_question_number} ({score_perc} %)" + "</h4>", unsafe_allow_html=True)
 
         # List your answers and the correct ones
-        for i, qa in enumerate(st.session_state.llm.mcq_answer_sheet):
+        for i, qa in enumerate(st.session_state.llm.mcq_answer_sheet[:-1]):
             question, answer, user_answer = qa['question'], qa['answer'], qa['user_answer']
             st.write("---")
             st.write(f"**Question {i+1}/{st.session_state.mcq_question_number}:** {question}")

prompt_generation.py

@@ -12,8 +12,9 @@ import random
 
 class OpenAILLM:
     def __init__(self, temperature: float = 1.,
-                 model_name: str = 'gpt-4o',
-                 mcq_question_number: int = 10):
+                 model_name: str = 'gpt-4',
+                 mcq_question_number: int = 10,
+                 mcq_false_answer_number: int = 3):
         # Model-related instantiations
         self.llm = ChatOpenAI(temperature=temperature, model_name=model_name)
         self.Memory = ConversationBufferMemory
@@ -26,8 +27,9 @@ class OpenAILLM:
         self.chat_document_intro = "Read the following document: "
         self.chat_message_begin = "What would you like to know about the uploaded document?"
         self.mcq_question_number = mcq_question_number
-        self.mcq_intro = """
-            Generate a question, correct answer and 3 possible false answers from the inputted document. 
+        self.mcq_false_answer_number = mcq_false_answer_number
+        self.mcq_intro = f"""
+            Generate a question, correct answer and {self.mcq_false_answer_number} possible false answers from the inputted document. 
             Make sure that it is unique from the ones you have generated before!
             Only create 3 possible false answers and a correct answers!
         """
@@ -43,6 +45,7 @@ class OpenAILLM:
     def empty_text(self):
         self.docs = []
         self.chain_chat.memory = self.Memory()
+        self.mcq_answer_sheet = []
 
     def get_text_summary(self):
         summary = self.chain_summary.run(self.docs)
@@ -66,7 +69,7 @@ class OpenAILLM:
             ResponseSchema(name="question", description="Question generated from provided document."),
             ResponseSchema(name="answer", description="One correct answer for the asked question."),
             ResponseSchema(name="choices",
-                           description="3 available false options for a multiple-choice question in comma separated."),
+                           description=f"{self.mcq_false_answer_number} available false options for a multiple-choice question in comma separated."),
         ]
         output_format_instructions = StructuredOutputParser.from_response_schemas(
             response_schemas).get_format_instructions()
@@ -85,16 +88,14 @@ class OpenAILLM:
         self.start_chat()
 
     def get_mcq_question(self):
-        print("HERE")
         while True:
             try:
                 response = self.chain_chat.predict(input=self.mcq_query)
-                print(response)
                 response_parsed = json.loads(response[len(r"```json"):-len(r"```")])
 
                 question = response_parsed["question"]
                 answers = [response_parsed["answer"]] + [false_answer.strip() for false_answer in
-                                                         response_parsed["choices"].split(',')]
+                                                         response_parsed["choices"].split(',')][:self.mcq_false_answer_number]
                 break
             except Exception as e:
                 print(e)