Update app.py

app.py

@@ -82,17 +82,17 @@ class EnhancedContextDrivenChatbot:
 
     def extract_instructions(self, text):
         instruction_patterns = [
-            r"^(?:please\s+)?(?:can\s+you\s+)?(?:could\s+you\s+)?(.*?)\s*(?:for\s+me|for\s+this\s+response|in\s+your\s+response|in\s+your\s+answer)(?:\s*\?)?$",
-            r"^(?:I\s+want\s+you\s+to\s+)?(.*?)\s*(?:for\s+me|for\s+this\s+response|in\s+your\s+response|in\s+your\s+answer)(?:\s*\?)?$",
-            r"^(?:make\s+sure\s+to\s+)?(.*?)\s*(?:for\s+me|for\s+this\s+response|in\s+your\s+response|in\s+your\s+answer)(?:\s*\?)?$",
+            r"(.*?),?\s*(?:please\s+)?(provide\s+(?:me\s+)?a\s+.*?|give\s+(?:me\s+)?a\s+.*?|create\s+a\s+.*?)$",
+            r"(.*?),?\s*(?:please\s+)?(summarize|analyze|explain|describe|elaborate\s+on).*$",
+            r"(.*?),?\s*(?:please\s+)?(in\s+detail|briefly|concisely).*$",
         ]
         
         for pattern in instruction_patterns:
             match = re.match(pattern, text, re.IGNORECASE)
             if match:
-                return match.group(1).strip(), True
+                return match.group(1).strip(), match.group(2).strip()
 
-        return text, False
+        return text, None
 
     def get_most_relevant_context(self, question):
         if not self.history:
@@ -136,21 +136,19 @@ class EnhancedContextDrivenChatbot:
         return rephrased_question.strip()
 
     def process_question(self, question):
-        question, has_instructions = self.extract_instructions(question)
+        core_question, instructions = self.extract_instructions(question)
         
-        if has_instructions:
-            self.last_instructions = question
-            contextualized_question = self.get_most_relevant_context(question)
-        else:
-            contextualized_question = self.get_most_relevant_context(question)
-            if self.is_follow_up_question(question):
-                contextualized_question = self.rephrase_query(contextualized_question, self.last_instructions)
+        contextualized_question = self.get_most_relevant_context(core_question)
+        
+        if self.is_follow_up_question(core_question):
+            contextualized_question = self.rephrase_query(contextualized_question, instructions)
         
         topics = self.extract_topics(contextualized_question)
         
         self.add_to_history(question)
+        self.last_instructions = instructions
         
-        return contextualized_question, topics, self.entity_tracker, self.last_instructions
+        return contextualized_question, topics, self.entity_tracker, instructions
         
 # Initialize LlamaParse
 llama_parser = LlamaParse(
@@ -349,6 +347,8 @@ def ask_question(question, temperature, top_p, repetition_penalty, web_search, c
     if web_search:
         contextualized_question, topics, entity_tracker, instructions = chatbot.process_question(question)
         serializable_entity_tracker = {k: list(v) for k, v in entity_tracker.items()}
+        
+        # Use only the core question for the search
         search_results = google_search(contextualized_question)
         all_answers = []
 
@@ -365,10 +365,10 @@ def ask_question(question, temperature, top_p, repetition_penalty, web_search, c
 
                 context_str = "\n".join([f"Source: {doc.metadata['source']}\nContent: {doc.page_content}" for doc in web_docs])
 
-                instruction_prompt = f"Instructions: {instructions}\n" if instructions else ""
+                instruction_prompt = f"User Instructions: {instructions}\n" if instructions else ""
 
                 prompt_template = f"""
-                Answer the question based on the following web search results, conversation context, entity information, and any provided instructions:
+                Answer the question based on the following web search results, conversation context, entity information, and user instructions:
                 Web Search Results:
                 {{context}}
                 Conversation Context: {{conv_context}}
@@ -377,15 +377,15 @@ def ask_question(question, temperature, top_p, repetition_penalty, web_search, c
                 Entity Information: {{entities}}
                 {instruction_prompt}
                 If the web search results don't contain relevant information, state that the information is not available in the search results.
-                Provide a summarized and direct answer to the question without mentioning the web search or these instructions.
-                Do not include any source information in your answer.                    
+                Provide a response that addresses the question and follows the user's instructions.
+                Do not mention these instructions or the web search process in your answer.
                 """
 
                 prompt_val = ChatPromptTemplate.from_template(prompt_template)
                 formatted_prompt = prompt_val.format(
                     context=context_str, 
                     conv_context=chatbot.get_context(), 
-                    question=contextualized_question,
+                    question=question,  # Use the original question here
                     topics=", ".join(topics),
                     entities=json.dumps(serializable_entity_tracker)
                 )