Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import logging
 import torch
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import requests
 from bs4 import BeautifulSoup
 import json
@@ -26,7 +26,6 @@ class Config:
     REQUEST_TIMEOUT = 10
     MAX_DEPTH = 1
     SIMILARITY_THRESHOLD = 0.4  # Lowered threshold for testing
-    # Add some example URLs that are publicly accessible
     BASE_URLS = [
         "https://www.sspencer.k12.in.us/",  # Replace with actual school website
         # Add more public URLs here
@@ -44,10 +43,22 @@ class ResourceItem:
 
 class SchoolChatbot:
     def __init__(self):
-        self.setup_models()
+        self.setup_models()  # Ensure this method is defined
         self.resources = []
         self.visited_urls = set()
-        self.crawl_and_index_resources()  # This line will now work
+        self.crawl_and_index_resources()
+
+    def setup_models(self):
+        """Initialize all required models"""
+        try:
+            logger.info("Setting up models...")
+            self.tokenizer = AutoTokenizer.from_pretrained(Config.MODEL_NAME)
+            self.model = AutoModelForCausalLM.from_pretrained(Config.MODEL_NAME)
+            self.embedding_model = SentenceTransformer(Config.EMBEDDING_MODEL)
+            logger.info("Models setup completed successfully")
+        except Exception as e:
+            logger.error(f"Error setting up models: {e}")
+            raise
 
     def crawl_and_index_resources(self):
         """Crawl and index resources from the base URLs."""
@@ -189,6 +200,7 @@ Source: {best_resource.url}
         end_idx = min(len(sentences), best_idx + 2)
         
         return '. '.join(sentences[start_idx:end_idx])
+
 if __name__ == "__main__":
     logger.info("Starting chatbot...")
     chatbot = SchoolChatbot()