Create app.py

app.py

@@ -0,0 +1,141 @@
+import os
+import gradio as gr
+from langchain.prompts import ChatPromptTemplate
+from langchain_community.chat_models import ChatOpenAI
+from langchain.schema import StrOutputParser
+
+def create_the_question_prompt_template(num_questions, questions_type, context):
+    """Create the prompt template for the questions generator app."""
+    template = f"""Create {num_questions} {questions_type} questions about the following concept/contents: {context}.
+    The format of the question could be one of the following:
+  - Multiple-choice:
+    Questions:
+       <Question1>:<a. Answer 1>,<b. Answer 2>,<c. Answer 3>,<d. Answer 4>
+       <Question2>:<a. Answer 1>,<b. Answer 2>,<c. Answer 3>,<d. Answer 4>
+       ...
+    Answers:
+       <Answer1>:<a|b|c|d>
+       <Answer2>:<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
+  - True-false:
+    Questions:
+       <Question1>: <True|False>
+       <Question2>: <True|False>
+       ...
+    Answers:
+       <Answer1>: <True|False>
+       <Answer2>: <True|False>
+       ...
+  Example:
+  - Questions:
+    - 1. Binary search trees are implemented using linked lists.
+    - 2. The time complexity of a binary search tree is O(n).
+  - Answers:
+    - 1. False
+    - 2. True
+  - Open-ended:
+    Questions:
+       <Question1>:
+       <Question2>:
+       ...
+    Answers:
+    <Answer1>:
+    <Answer2>:
+   Example:
+   Questions:
+   - 1. What is a binary search tree?
+   - 2. Binary search trees are implemented using linked lists.
+
+   - Answers:
+     1. A binary search tree is a data structure that is used to store data in a sorted manner.
+     2. Binary search trees are implemented using linked lists.
+  """
+    return ChatPromptTemplate.from_template(template)
+
+def create_question_chain(prompt_template, llm):
+    """Creates the chain for the question generator app."""
+    return prompt_template | llm | StrOutputParser()
+
+def split_questions_answers(question_response):
+    print("question_response",question_response)
+    """Function that splits the questions and answers from the question response."""
+    try:
+        questions_section = question_response.split("Answers:")[0].strip()
+
+        if "Answers:" in question_response:
+            answers_section = question_response.split("Answers:")[1].strip()
+        else:
+            answers_section = ""
+
+        # Format answers for better alignment
+        formatted_answers = format_answers(answers_section)
+        print("formatted_answers:",formatted_answers)
+        return questions_section, formatted_answers
+    except IndexError:
+        return "Error: Unable to parse the response.", ""
+
+def format_answers(answers):
+    """Format answers to display with consistent alignment."""
+    lines = answers.split('\n')
+    formatted = []
+
+    for line in lines:
+        if line.strip():  # Only process non-empty lines
+            formatted.append(line.strip())  # Add the line directly without additional numbering
+
+    return "\n".join(formatted)
+
+
+def generate_questions(api_key, context, num_questions, questions_type):
+    """Function to generate questions."""
+    if not api_key.strip():
+        return "Error: Please provide a valid OpenAI API key.", ""
+
+    os.environ["OPENAI_API_KEY"] = api_key
+
+    llm = ChatOpenAI(temperature=0.0)
+    prompt_template = create_the_question_prompt_template(num_questions, questions_type, context)
+    chain = create_question_chain(prompt_template, llm)
+
+    try:
+        question_response = chain.invoke({"questions_type": questions_type, "num_questions": num_questions, "context": context})
+
+        # Log the entire response for debugging
+        print("Question Response:", question_response)
+
+        questions, answers = split_questions_answers(question_response)
+        return questions, answers
+    except Exception as e:
+        return f"Error: {str(e)}", ""
+
+# Define Gradio interface
+# Define Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Quiz App - Generate Questions")
+    with gr.Row():
+        api_key_input = gr.Textbox(label="OpenAI API Key", type="password", placeholder="Enter your OpenAI API key")
+    context_input = gr.Textbox(label="Context/Concept", placeholder="Enter the concept for the questions")
+    num_questions_input = gr.Slider(label="Number of Questions", minimum=1, maximum=5, value=2, step=1)
+    question_type_input = gr.Radio(label="Quiz Type", choices=["multiple-choice", "true-false", "open-ended"], value="multiple-choice")
+    generate_btn = gr.Button("Generate Questions")
+    with gr.Row():
+        questions_output = gr.Textbox(label="Generated Questions", lines=5)
+        answers_output = gr.Textbox(label="Generated Answers", lines=5)
+
+    generate_btn.click(
+        generate_questions,
+        inputs=[api_key_input, context_input, num_questions_input, question_type_input],
+        outputs=[questions_output, answers_output],
+    )
+
+# Launch the app
+demo.launch()