Update app.py

app.py

@@ -142,11 +142,11 @@ def get_page_metadata(soup):
 
     return metadata
 
-def generate_summary(bookmark):
+def generate_summary_and_assign_category(bookmark):
     """
-    Generate a concise summary for a bookmark using available content and LLM via the Groq Cloud API.
+    Generate a concise summary and assign a category using a single LLM call.
     """
-    logger.info(f"Generating summary for bookmark: {bookmark.get('url')}")
+    logger.info(f"Generating summary and assigning category for bookmark: {bookmark.get('url')}")
 
     try:
         html_content = bookmark.get('html_content', '')
@@ -182,6 +182,7 @@ def generate_summary(bookmark):
         else:
             use_prior_knowledge = False
 
+        # Prepare the prompt
         if use_prior_knowledge:
             # Construct prompt to use prior knowledge
             prompt = f"""
@@ -189,28 +190,36 @@ You are a knowledgeable assistant with up-to-date information as of 2023.
 
 The user provided a URL: {bookmark.get('url')}
 
-Please provide a concise summary in **no more than two sentences** about this website.
+Please provide:
+1. A concise summary in **no more than two sentences** about this website.
+2. Assign the most appropriate category from the list below for this website.
 
-Focus on:
-- The main purpose or topic of the website.
-- Key information or features.
+Categories:
+{', '.join([f'"{cat}"' for cat in CATEGORIES])}
 
-Be concise and objective.
+Provide your response in the following format:
+Summary: [Your summary here]
+Category: [One of the categories]
 """
         else:
             # Construct the prompt with the extracted content
             prompt = f"""
-You are a helpful assistant that creates concise webpage summaries.
+You are a helpful assistant that creates concise webpage summaries and assigns categories.
 
 Analyze the following webpage content:
 
 {content_text}
 
-Provide a concise summary in **no more than two sentences** focusing on:
-- The main purpose or topic of the page.
-- Key information or features.
+Please provide:
+1. A concise summary in **no more than two sentences** focusing on the main purpose or topic of the page and key information or features.
+2. Assign the most appropriate category from the list below for this webpage.
+
+Categories:
+{', '.join([f'"{cat}"' for cat in CATEGORIES])}
 
-Be concise and objective.
+Provide your response in the following format:
+Summary: [Your summary here]
+Category: [One of the categories]
 """
 
         # Call the LLM via Groq Cloud API
@@ -219,71 +228,37 @@ Be concise and objective.
             messages=[
                 {"role": "user", "content": prompt}
             ],
-            max_tokens=100,
+            max_tokens=200,
             temperature=0.5,
         )
-        summary = response['choices'][0]['message']['content'].strip()
-        if not summary:
-            raise ValueError("Empty summary received from the model.")
-        logger.info("Successfully generated LLM summary")
-        bookmark['summary'] = summary
-        time.sleep(3)  # Wait to respect rate limits
-
-    except Exception as e:
-        logger.error(f"Error generating summary: {e}", exc_info=True)
-        bookmark['summary'] = 'No summary available.'
-
-def assign_category(bookmark):
-    """
-    Assign a category to a bookmark using the LLM based on its summary via the Groq Cloud API.
-    """
-    if bookmark.get('dead_link'):
-        bookmark['category'] = 'Dead Link'
-        logger.info(f"Assigned category 'Dead Link' to bookmark: {bookmark.get('url')}")
-        return
-
-    summary = bookmark.get('summary', '')
-    if not summary:
-        bookmark['category'] = 'Uncategorized'
-        return
-
-    # Prepare the prompt
-    categories_str = ', '.join([f'"{cat}"' for cat in CATEGORIES if cat != 'Dead Link'])
-    prompt = f"""
-You are a helpful assistant that categorizes webpages.
+        content = response['choices'][0]['message']['content'].strip()
+        if not content:
+            raise ValueError("Empty response received from the model.")
 
-Based on the following summary, assign the most appropriate category from the list below.
+        # Parse the response
+        summary_match = re.search(r"Summary:\s*(.*)", content)
+        category_match = re.search(r"Category:\s*(.*)", content)
 
-Summary:
-{summary}
-
-Categories:
-{categories_str}
-
-Respond with only the category name.
-"""
-
-    try:
-        response = openai.ChatCompletion.create(
-            model='llama-3.1-70b-versatile',
-            messages=[
-                {"role": "user", "content": prompt}
-            ],
-            max_tokens=10,
-            temperature=0,
-        )
-        category = response['choices'][0]['message']['content'].strip().strip('"')
-        # Validate the category
-        if category in CATEGORIES:
-            bookmark['category'] = category
-            logger.info(f"Assigned category '{category}' to bookmark: {bookmark.get('url')}")
+        if summary_match:
+            bookmark['summary'] = summary_match.group(1).strip()
+        else:
+            bookmark['summary'] = 'No summary available.'
+
+        if category_match:
+            category = category_match.group(1).strip().strip('"')
+            if category in CATEGORIES:
+                bookmark['category'] = category
+            else:
+                bookmark['category'] = 'Uncategorized'
         else:
             bookmark['category'] = 'Uncategorized'
-            logger.warning(f"Invalid category '{category}' returned by LLM for bookmark: {bookmark.get('url')}")
-        time.sleep(3)  # Wait to respect rate limits
+
+        logger.info("Successfully generated summary and assigned category")
+        time.sleep(1)  # Reduced sleep time
 
     except Exception as e:
-        logger.error(f"Error assigning category: {e}", exc_info=True)
+        logger.error(f"Error generating summary and assigning category: {e}", exc_info=True)
+        bookmark['summary'] = 'No summary available.'
         bookmark['category'] = 'Uncategorized'
 
 def parse_bookmarks(file_content):
@@ -395,15 +370,15 @@ def display_bookmarks():
         if bookmark.get('dead_link'):
             status = "❌ Dead Link"
             card_style = "border: 2px solid red;"
-            text_style = "color: red;"
+            text_style = "color: white;"  # Set font color to white
         elif bookmark.get('slow_link'):
             status = "⏳ Slow Response"
             card_style = "border: 2px solid orange;"
-            text_style = "color: orange;"
+            text_style = "color: white;"  # Set font color to white
         else:
             status = "✅ Active"
             card_style = "border: 2px solid green;"
-            text_style = "color: black;"
+            text_style = "color: white;"  # Set font color to white
 
         title = bookmark['title']
         url = bookmark['url']
@@ -419,7 +394,7 @@ def display_bookmarks():
         category = escape(category)
 
         card_html = f'''
-        <div class="card" style="{card_style}; padding: 10px; margin: 10px; border-radius: 5px;">
+        <div class="card" style="{card_style} padding: 10px; margin: 10px; border-radius: 5px; background-color: #1e1e1e;">
             <div class="card-content">
                 <h3 style="{text_style}">{index}. {title} {status}</h3>
                 <p style="{text_style}"><strong>Category:</strong> {category}</p>
@@ -468,10 +443,14 @@ def process_uploaded_file(file):
     for bookmark in bookmarks:
         fetch_url_info(bookmark)
 
-    # Process bookmarks sequentially with LLM
+    # Process bookmarks sequentially with combined LLM call
     for bookmark in bookmarks:
-        generate_summary(bookmark)
-        assign_category(bookmark)
+        if bookmark.get('dead_link'):
+            bookmark['summary'] = 'No summary available.'
+            bookmark['category'] = 'Dead Link'
+            logger.info(f"Assigned category 'Dead Link' to bookmark: {bookmark.get('url')}")
+        else:
+            generate_summary_and_assign_category(bookmark)
 
     try:
         faiss_index = vectorize_and_index(bookmarks)
@@ -628,7 +607,7 @@ Provide a concise and helpful response.
         )
         answer = response['choices'][0]['message']['content'].strip()
         logger.info("Chatbot response generated")
-        time.sleep(3)  # Wait to respect rate limits
+        time.sleep(1)  # Reduced sleep time
         return answer
 
     except Exception as e: