Update app.py

app.py

@@ -10,10 +10,37 @@ client=InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 # Open the water_cycle.txt file in read mode with UTF-8 encoding
 with open("Safe_restaurant", "r", encoding="utf-8") as file:
   # Read the entire contents of the file and store it in a variable
-  Safe_restaurant = file.read()
+  safe_restaurant = file.read()
 
 # Print the text below
-print(Safe_restaurant)
+print(safe_restaurant)
+
+#step 3 from smentic search(chunck data)
+def preprocess_text(text):
+  # Strip extra whitespace from the beginning and the end of the text
+  cleaned_text = text.strip()
+
+  # Split the cleaned_text by every newline character (\n)
+  chunks = cleaned_text.split("\n")
+
+  # Create an empty list to store cleaned chunks
+  cleaned_chunks = []
+
+  # Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list
+  for chunk in chunks:
+    chunk = chunk.strip()
+    if (chunk != ""):
+      cleaned_chunks.append(chunk)
+    # Print cleaned_chunks
+  print(cleaned_chunks)
+    # Print the length of cleaned_chunks
+  len(cleaned_chunks)
+
+    # Return the cleaned_chunks
+  return cleaned_chunks
+
+# Call the preprocess_text function and store the result in a cleaned_chunks variable
+cleaned_chunks =  preprocess_text(safe_restaurant)
 
 def respond(message, history):
     #responses = ["Yes", "No"]