Update app.py

app.py

@@ -1,9 +1,9 @@
 import gradio as gr
 import requests
 from bs4 import BeautifulSoup, Comment
+import os
 from llama_cpp import Llama
 
-# Function to extract visible text from a webpage
 def tag_visible(element):
     if element.parent.name in ['style', 'script', 'head', 'title', 'meta', '[document]']:
         return False
@@ -14,7 +14,8 @@ def tag_visible(element):
 def get_text_from_url(url):
     response = requests.get(url, timeout=10)
     soup = BeautifulSoup(response.text, 'html.parser')
-    texts = soup.find_all(text=True)
+    # Use 'string=True' instead of deprecated 'text=True'
+    texts = soup.find_all(string=True)
     visible_texts = filter(tag_visible, texts)
     return " ".join(t.strip() for t in visible_texts)
 
@@ -26,35 +27,35 @@ extensions = ["", "pmrf-profile-page"]
 for ext in extensions:
     try:
         full_text = get_text_from_url(homepage_url + ext)
-        truncated_text = full_text[:2000]  # Using first 2000 characters for more context
+        truncated_text = full_text[:2000]  # Adjust truncation length as needed
         text_list.append(truncated_text)
     except Exception as e:
         text_list.append(f"Error fetching {homepage_url+ext}: {str(e)}")
 
 CONTEXT = " ".join(text_list)
 
-# Load the Mistral model (low-latency, CPU optimized)
-llm = Llama(model_path="mistral-7b-instruct-v0.1.Q4_K_M.gguf", n_ctx=4096, n_threads=6, verbose=False)
+# Set the model path. Make sure the model file is downloaded and placed in the 'models' directory.
+model_path = "models/mistral-7b-instruct-v0.1.Q4_K_M.gguf"
+if not os.path.exists(model_path):
+    raise ValueError(f"Model file not found at {model_path}. Please download the model file and place it in the 'models' folder.")
+
+llm = Llama(model_path=model_path, n_ctx=4096, n_threads=6, verbose=False)
 
-# Function to answer queries
 def answer_query(query):
     prompt = (
-        "You are an AI chatbot answering queries based on the homepage of Abhilash Nandy. "
-        "Your responses should be concise (under 30 words) and directly relevant to the provided context.\n\n"
+        "You are an AI chatbot answering queries based on Abhilash Nandy's homepage. "
+        "Provide concise answers (under 30 words).\n\n"
         f"Context: {CONTEXT}\n\nUser: {query}\nAI:"
     )
-    
     response = llm(prompt, max_tokens=50, stop=["\nUser:", "\nAI:"], echo=False)
-    
     return response["choices"][0]["text"].strip()
 
-# Gradio Interface
 iface = gr.Interface(
     fn=answer_query,
-    inputs=gr.Textbox(lines=2, placeholder="Ask a question about Abhilash Nandy..."),
+    inputs=gr.Textbox(lines=2, placeholder="Ask a question about Abhilash Nandy's homepage..."),
     outputs="text",
     title="Homepage QA Chatbot",
-    description="Ask me anything about Abhilash Nandy's homepage."
+    description="A chatbot answering queries based on homepage context."
 )
 
 if __name__ == '__main__':