Update app.py

app.py

@@ -62,7 +62,10 @@ def initialize_policy_db():
             reader = PyPDF2.PdfReader(f)
             policy_text = "".join([page.extract_text() for page in reader.pages])
         
-        policy_chunks = policy_text.split("\n\n")
+        # There was an issue where the entire policy pdf was being passed in, potentially due to incorrect scraping of n/n/ so switched to characters
+        chunk_size = 1000
+        policy_chunks = [policy_text[i:i + chunk_size] for i in range(0, len(policy_text), chunk_size)]
+        
         ids = [f"chunk_{i}" for i in range(len(policy_chunks))]
         embeddings = embedder.encode(policy_chunks).tolist()
         collection.add(documents=policy_chunks, embeddings=embeddings, ids=ids)