Update app.py

app.py

@@ -4,14 +4,18 @@ from transformers import pipeline
 from sentence_transformers import SentenceTransformer, util
 import PyPDF2
 
-# Set up logging with immediate writing
-logging.basicConfig(
-    filename='support_bot_log.txt',
-    level=logging.INFO,
-    format='%(asctime)s - %(message)s',
-    force=True  # Ensures any existing handlers are replaced and logging starts fresh
-)
-logger = logging.getLogger()
+# Set up logging with a dedicated file handler
+logger = logging.getLogger('SupportBot')
+logger.setLevel(logging.INFO)
+# Remove any existing handlers to avoid conflicts
+if logger.handlers:
+    logger.handlers.clear()
+# Create a file handler with append mode
+handler = logging.FileHandler('support_bot_log.txt', mode='a')
+handler.setLevel(logging.INFO)
+formatter = logging.Formatter('%(asctime)s - %(message)s')
+handler.setFormatter(formatter)
+logger.addHandler(handler)
 
 # Load models
 qa_model = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
@@ -30,7 +34,7 @@ def extract_text_from_pdf(file_path):
 def find_relevant_section(query, sections, section_embeddings):
     stopwords = {"and", "the", "is", "for", "to", "a", "an", "of", "in", "on", "at", "with", "by", "it", "as", "so", "what"}
     
-    # Semantic search
+    logger.info(f"Searching for relevant section for query: {query}")
     query_embedding = embedder.encode(query, convert_to_tensor=True)
     similarities = util.cos_sim(query_embedding, section_embeddings)[0]
     best_idx = similarities.argmax().item()
@@ -39,39 +43,43 @@ def find_relevant_section(query, sections, section_embeddings):
     
     SIMILARITY_THRESHOLD = 0.4
     if similarity_score >= SIMILARITY_THRESHOLD:
-        logger.info(f"Found relevant section using embeddings for query: {query}")
+        logger.info(f"Found relevant section using embeddings (score: {similarity_score})")
+        handler.flush()  # Ensure log is written immediately
         return best_section
     
     logger.info(f"Low similarity ({similarity_score}). Falling back to keyword search.")
-    
-    # Keyword-based fallback search with stopword filtering
     query_words = {word for word in query.lower().split() if word not in stopwords}
     for section in sections:
         section_words = {word for word in section.lower().split() if word not in stopwords}
         common_words = query_words.intersection(section_words)
         if len(common_words) >= 2:
-            logger.info(f"Keyword match found for query: {query} with common words: {common_words}")
+            logger.info(f"Keyword match found with common words: {common_words}")
+            handler.flush()
             return section
     
-    logger.info(f"No good keyword match found. Returning default fallback response.")
+    logger.info("No good match found. Returning default response.")
+    handler.flush()
     return "I don’t have enough information to answer that."
 
-# Process the uploaded file with detailed logging
+# Process the uploaded file
 def process_file(file, state):
+    logger.info("Received file upload request")
     if file is None:
-        logger.info("No file uploaded.")
+        logger.info("No file uploaded")
+        handler.flush()
         return [("Bot", "Please upload a file.")], state
     
     file_path = file.name
     if file_path.lower().endswith(".pdf"):
-        logger.info(f"Uploaded PDF file: {file_path}")
+        logger.info(f"Processing PDF file: {file_path}")
         text = extract_text_from_pdf(file_path)
     elif file_path.lower().endswith(".txt"):
-        logger.info(f"Uploaded TXT file: {file_path}")
+        logger.info(f"Processing TXT file: {file_path}")
         with open(file_path, 'r', encoding='utf-8') as f:
             text = f.read()
     else:
         logger.error(f"Unsupported file format: {file_path}")
+        handler.flush()
         return [("Bot", "Unsupported file format. Please upload a PDF or TXT file.")], state
     
     sections = text.split('\n\n')
@@ -83,16 +91,19 @@ def process_file(file, state):
     state['feedback_count'] = 0
     state['mode'] = 'waiting_for_query'
     state['chat_history'] = [("Bot", "File processed. You can now ask questions.")]
-    logger.info(f"Processed file: {file_path}")
+    logger.info(f"File processed successfully: {file_path}")
+    handler.flush()
     return state['chat_history'], state
 
 # Handle user input (queries and feedback)
 def handle_input(user_input, state):
     if state['mode'] == 'waiting_for_upload':
+        logger.info("User input received before file upload")
         state['chat_history'].append(("Bot", "Please upload a file first."))
-        logger.info("User attempted to interact without uploading a file.")
+        handler.flush()
     elif state['mode'] == 'waiting_for_query':
         query = user_input
+        logger.info(f"User query: {query}")
         state['current_query'] = query
         state['feedback_count'] = 0
         context = find_relevant_section(query, state['sections'], state['section_embeddings'])
@@ -105,34 +116,40 @@ def handle_input(user_input, state):
         state['mode'] = 'waiting_for_feedback'
         state['chat_history'].append(("User", query))
         state['chat_history'].append(("Bot", f"Answer: {answer}\nPlease provide feedback: good, too vague, not helpful."))
-        logger.info(f"Query: {query}, Answer: {answer}")
+        logger.info(f"Generated answer: {answer}")
+        handler.flush()
     elif state['mode'] == 'waiting_for_feedback':
         feedback = user_input.lower()
+        logger.info(f"User feedback: {feedback}")
         state['chat_history'].append(("User", feedback))
-        logger.info(f"Feedback: {feedback}")
         if feedback == "good" or state['feedback_count'] >= 2:
             state['mode'] = 'waiting_for_query'
             if feedback == "good":
                 state['chat_history'].append(("Bot", "Thank you for your feedback. You can ask another question."))
-                logger.info("Feedback accepted as 'good'. Waiting for next query.")
+                logger.info("Feedback 'good' received. Ready for next query.")
             else:
                 state['chat_history'].append(("Bot", "Maximum feedback iterations reached. You can ask another question."))
-                logger.info("Max feedback iterations reached. Waiting for next query.")
+                logger.info("Max feedback iterations (2) reached. Ready for next query.")
+            handler.flush()
         else:
             query = state['current_query']
             context = find_relevant_section(query, state['sections'], state['section_embeddings'])
             if feedback == "too vague":
                 adjusted_answer = f"{state['last_answer']}\n\n(More details:\n{context[:500]}...)"
+                logger.info("Feedback 'too vague'. Providing context.")
             elif feedback == "not helpful":
                 adjusted_answer = qa_model(question=query + " Please provide more detailed information with examples.", context=context)['answer']
+                logger.info("Feedback 'not helpful'. Re-searching with modified query.")
             else:
                 state['chat_history'].append(("Bot", "Please provide valid feedback: good, too vague, not helpful."))
                 logger.info(f"Invalid feedback received: {feedback}")
+                handler.flush()
                 return state['chat_history'], state
             state['last_answer'] = adjusted_answer
             state['feedback_count'] += 1
             state['chat_history'].append(("Bot", f"Updated answer: {adjusted_answer}\nPlease provide feedback: good, too vague, not helpful."))
-            logger.info(f"Adjusted answer: {adjusted_answer}")
+            logger.info(f"Updated answer: {adjusted_answer}")
+            handler.flush()
     return state['chat_history'], state
 
 # Initial state
@@ -154,12 +171,9 @@ with gr.Blocks() as demo:
     chat = gr.Chatbot()
     user_input = gr.Textbox(label="Your query or feedback")
     submit_btn = gr.Button("Submit")
-    log_file = gr.File(label="Download Log File", value="support_bot_log.txt")  # Added for log download
+    log_file = gr.File(label="Download Log File", value="support_bot_log.txt")
 
-    # Process file upload
     file_upload.upload(process_file, inputs=[file_upload, state], outputs=[chat, state])
-
-    # Handle user input and clear the textbox
     submit_btn.click(handle_input, inputs=[user_input, state], outputs=[chat, state]).then(lambda: "", None, user_input)
 
 demo.launch(share=True)