Update app.py

app.py

@@ -9,7 +9,7 @@ import PyPDF2
 from sklearn.metrics.pairwise import cosine_similarity
 from collections import Counter
 
-# ---------------------- Setup ---------------------
+# --------------------- Setup ---------------------
 
 logging.basicConfig(
     filename='query_logs.log',
@@ -23,6 +23,21 @@ PDF_PATH = 'Generative_AI_Foundations_in_Python_Discover_key_techniques_and.pdf'
 sentence_transformer_model = SentenceTransformer('all-MiniLM-L6-v2')
 cache = {}
 
+# --------------------- Vectorization Function ---------------------
+
+def vectorize_text(sentences_with_pages):
+    """Vectorize sentences using SentenceTransformer and create a FAISS index."""
+    try:
+        sentences = [item['sentence'] for item in sentences_with_pages]
+        embeddings = sentence_transformer_model.encode(sentences, show_progress_bar=True)
+        index = faiss.IndexFlatL2(embeddings.shape[1])
+        index.add(np.array(embeddings))
+        logging.info(f"Added {len(sentences)} sentences to the vector store.")
+        return index, sentences_with_pages
+    except Exception as e:
+        logging.error(f"Error during vectorization: {str(e)}")
+        return None, None
+
 # --------------------- PDF Processing ---------------------
 
 def read_pdf(file_path):
@@ -41,21 +56,10 @@ def read_pdf(file_path):
                     sentences_with_pages.append({'sentence': sentence, 'page_number': page_num + 1})
     return sentences_with_pages
 
+# Read and Vectorize PDF Content
 sentences_with_pages = read_pdf(PDF_PATH)
 vector_index, sentences_with_pages = vectorize_text(sentences_with_pages)
 
-def vectorize_text(sentences_with_pages):
-    try:
-        sentences = [item['sentence'] for item in sentences_with_pages]
-        embeddings = sentence_transformer_model.encode(sentences, show_progress_bar=True)
-        index = faiss.IndexFlatL2(embeddings.shape[1])
-        index.add(np.array(embeddings))
-        logging.info(f"Added {len(sentences)} sentences to the vector store.")
-        return index, sentences_with_pages
-    except Exception as e:
-        logging.error(f"Error during vectorization: {str(e)}")
-        return None, None
-
 # --------------------- Query Handling ---------------------
 
 def generate_query_embedding(query):