Delete app.py

app.py

@@ -1,161 +0,0 @@
-import numpy as np
-from sentence_transformers import SentenceTransformer
-import faiss
-import re
-import gradio as gr
-
-def preprocess_text(text):
-    """
-    Preprocess the text into structured question-answer pairs
-    """
-    # Split text into sections by questions
-    sections = []
-    current_section = []
-    
-    for line in text.split('\n'):
-        line = line.strip()
-        if line.startswith('Question'):
-            if current_section:
-                sections.append(' '.join(current_section))
-            current_section = [line]
-        elif line:
-            current_section.append(line)
-    
-    if current_section:
-        sections.append(' '.join(current_section))
-    
-    # Create a structured format
-    structured_sections = []
-    for section in sections:
-        # Remove page numbers and other irrelevant text
-        section = re.sub(r'\d+\s*$', '', section)
-        section = re.sub(r'TRAPS:|BEST ANSWER:|PASSABLE ANSWER:', ' ', section)
-        structured_sections.append(section.strip())
-    
-    return structured_sections
-
-def query_qa_system(question, model, index, text_chunks, similarity_threshold=0.4):
-    """
-    Query the QA system with improved matching
-    """
-    # Encode and normalize the question
-    question_embedding = model.encode([question])
-    faiss.normalize_L2(question_embedding)
-    
-    # Search for the most similar chunks
-    k = 1  # Get only the best match
-    similarities, indices = index.search(question_embedding, k)
-    
-    best_idx = indices[0][0]
-    similarity_score = similarities[0][0]  # Cosine similarity score
-    
-    if similarity_score >= similarity_threshold:
-        matched_text = text_chunks[best_idx]
-        # Extract just the question number for reference
-        question_num = re.search(r'Question \d+:', matched_text)
-        question_num = question_num.group(0) if question_num else "Matching section"
-        
-        return {
-            'question': question_num,
-            'full_text': matched_text,
-            'confidence': float(similarity_score),
-            'found_answer': True
-        }
-    else:
-        return {
-            'question': None,
-            'full_text': "I couldn't find a sufficiently relevant answer to your question in the provided document.",
-            'confidence': float(similarity_score),
-            'found_answer': False
-        }
-
-# Function to handle PDF file upload and initialization
-def initialize_qa_system(pdf_file):
-    # Read the uploaded PDF
-    try:
-        from PyPDF2 import PdfReader
-        pdf_reader = PdfReader(pdf_file.name)
-        pdf_text = ""
-        for page in pdf_reader.pages:
-            text = page.extract_text()
-            if text:
-                pdf_text += text + "\n"
-        
-        # Process text and create embeddings
-        text_chunks = preprocess_text(pdf_text)
-        model = SentenceTransformer("all-MiniLM-L6-v2")
-        embeddings = model.encode(text_chunks)
-        
-        # Create index
-        dimension = embeddings.shape[1]
-        faiss.normalize_L2(embeddings)
-        index = faiss.IndexFlatIP(dimension)
-        index.add(embeddings)
-        
-        return {
-            'model': model,
-            'index': index,
-            'text_chunks': text_chunks,
-            'status': f"System initialized with {len(text_chunks)} text chunks from your PDF!"
-        }
-    except Exception as e:
-        return {
-            'model': None,
-            'index': None,
-            'text_chunks': None,
-            'status': f"Error: {str(e)}"
-        }
-
-# Global variables to store our QA system components
-qa_system = {'model': None, 'index': None, 'text_chunks': None}
-
-# Function to handle file upload
-def upload_file(pdf_file):
-    global qa_system
-    result = initialize_qa_system(pdf_file)
-    qa_system = result
-    return result['status']
-
-# Function to handle questions
-def answer_question(question):
-    global qa_system
-    
-    if not qa_system['model'] or not qa_system['index'] or not qa_system['text_chunks']:
-        return "Please upload a PDF file first."
-    
-    result = query_qa_system(question, qa_system['model'], qa_system['index'], qa_system['text_chunks'])
-    answer_start = result['full_text'].find('Answer:') + len('Answer:')
-    answer = result['full_text'][answer_start:].strip()
-
-    
-    if result['found_answer']:
-        return f"Match (confidence: {result['confidence']:.2f}):\n\n{answer}"
-    else:
-        return f"{answer}\nBest match confidence: {result['confidence']:.2f}"
-
-# Create the Gradio interface
-with gr.Blocks(title="Interview Q&A Assistant") as demo:
-    gr.Markdown("# Interview Q&A Assistant")
-    gr.Markdown("Upload your interview questions PDF and ask questions to get the most relevant sections.")
-    
-    with gr.Row():
-        with gr.Column():
-            pdf_upload = gr.File(label="Upload PDF File")
-            upload_button = gr.Button("Initialize Q&A System")
-            status_text = gr.Textbox(label="Status", value="Upload a PDF to begin")
-        
-    with gr.Row():
-        with gr.Column():
-            question_input = gr.Textbox(label="Ask a question about interview preparation")
-            submit_button = gr.Button("Get Answer")
-        
-    with gr.Row():
-        answer_output = gr.Textbox(label="Answer", lines=10)
-    
-    # Set up events
-    upload_button.click(upload_file, inputs=pdf_upload, outputs=status_text)
-    submit_button.click(answer_question, inputs=question_input, outputs=answer_output)
-
-# Launch the app
-if __name__ == "__main__":
-    demo.launch(share=True)