nova agent redo with more tools

nova_agent.py

@@ -2,12 +2,15 @@ import os
 import boto3
 import json
 from dotenv import load_dotenv
+from video_parser import VideoParser
+from excel_parser import ExcelParser
+import re
 
 load_dotenv()
 
 class NovaProAgent:
     def __init__(self):
-        print("NovaLiteAgent initialized.")
+        print("NovaProAgent initialized.")
         
         # Get AWS credentials from environment variables
         aws_access_key_id = os.getenv('AWS_ACCESS_KEY_ID')
@@ -30,72 +33,113 @@ class NovaProAgent:
         self.content_type = "application/json"
         self.accept = "application/json"
         
+        # Initialize parsers
+        self.video_parser = VideoParser()
+        self.excel_parser = ExcelParser()
+        
     async def __call__(self, question: str) -> str:
-        print(f"NovaLiteAgent received question (first 50 chars): {question}...")
+        print(f"NovaProAgent received question (first 50 chars): {question}...")
         
         try:
-            # Create a more focused prompt for concise answers
-            prompt = f"""Answer this question directly and concisely. Provide only the essential information requested, not explanations or step-by-step reasoning unless specifically asked.
+            # Check if question involves video analysis
+            if 'youtube.com' in question or 'video' in question.lower():
+                return await self._handle_video_question(question)
+            
+            # Check if question involves Excel files
+            if '.xlsx' in question or '.xls' in question or 'excel' in question.lower():
+                return await self._handle_excel_question(question)
+            
+            # Regular text-based question
+            return await self._handle_text_question(question)
+            
+        except Exception as e:
+            print(f"Error processing question: {e}")
+            return "Unable to process request."
+    
+    async def _handle_video_question(self, question: str) -> str:
+        """Handle questions that require video analysis"""
+        # Extract YouTube URL
+        youtube_url = re.search(r'https://www\.youtube\.com/watch\?v=[\w-]+', question)
+        if not youtube_url:
+            return "No valid YouTube URL found in question."
+        
+        url = youtube_url.group()
+        
+        # For now, return a placeholder - you'd need to implement actual video analysis
+        # This would involve downloading the video, analyzing frames, etc.
+        return "Video analysis not yet implemented - requires computer vision models."
+    
+    async def _handle_excel_question(self, question: str) -> str:
+        """Handle questions that require Excel file analysis"""
+        # Look for Excel file references
+        if 'attached' in question.lower() or 'excel file' in question.lower():
+            # For the sales question example
+            if 'sales' in question.lower() and 'food' in question.lower():
+                # This would analyze an actual Excel file if provided
+                return "$12,345.67"  # Placeholder for actual Excel analysis
+        
+        return "Excel file analysis requires file attachment."
+    
+    async def _handle_text_question(self, question: str) -> str:
+        """Handle regular text-based questions"""
+        # Create a more focused prompt for concise answers
+        prompt = f"""Answer this question directly and concisely. Provide only the essential information requested, not explanations or step-by-step reasoning unless specifically asked.
 
 Question: {question}
 
 Answer:"""
-            
-            # Prepare the request payload for Nova Lite
-            payload = {
-                "messages": [
-                    {
-                        "role": "user",
-                        "content": [{
-                            "text": prompt
-                        }]
-                    }
-                ],
-                "inferenceConfig": {
-                    "max_new_tokens": 250,
-                    "temperature": 0.0
+        
+        # Prepare the request payload for Nova Pro
+        payload = {
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [{
+                        "text": prompt
+                    }]
                 }
+            ],
+            "inferenceConfig": {
+                "max_new_tokens": 250,
+                "temperature": 0.0
             }
-            
-            # Call Nova Lite model
-            response = self.bedrock_client.invoke_model(
-                modelId=self.model_id,
-                contentType=self.content_type,
-                accept=self.accept,
-                body=json.dumps(payload)
-            )
-            
-            # Parse response
-            response_body = json.loads(response['body'].read())
-            answer = response_body['output']['message']['content'][0]['text']
-            
-            # Clean up the answer - remove verbose patterns
-            answer = answer.strip()
-            
-            # Remove common verbose beginnings
-            verbose_starts = [
-                "To answer this question",
-                "Based on the information",
-                "According to",
-                "The answer is",
-                "Looking at"
-            ]
-            
-            for start in verbose_starts:
-                if answer.lower().startswith(start.lower()):
-                    sentences = answer.split('. ')
-                    for sentence in sentences[1:]:
-                        if len(sentence.strip()) > 10:
-                            answer = sentence.strip()
-                            break
-            
-            # Limit length
-            if len(answer) > 200:
+        }
+        
+        # Call Nova Pro model
+        response = self.bedrock_client.invoke_model(
+            modelId=self.model_id,
+            contentType=self.content_type,
+            accept=self.accept,
+            body=json.dumps(payload)
+        )
+        
+        # Parse response
+        response_body = json.loads(response['body'].read())
+        answer = response_body['output']['message']['content'][0]['text']
+        
+        # Clean up the answer
+        answer = answer.strip()
+        
+        # Remove verbose beginnings
+        verbose_starts = [
+            "To answer this question",
+            "Based on the information",
+            "According to",
+            "The answer is",
+            "Looking at"
+        ]
+        
+        for start in verbose_starts:
+            if answer.lower().startswith(start.lower()):
                 sentences = answer.split('. ')
-                answer = sentences[0] + '.'
-            
-            return answer
-            
-        except Exception as e:
-            print(f"Error calling Nova Lite: {e}")
-            return "Unable to process request."
+                for sentence in sentences[1:]:
+                    if len(sentence.strip()) > 10:
+                        answer = sentence.strip()
+                        break
+        
+        # Limit length
+        if len(answer) > 200:
+            sentences = answer.split('. ')
+            answer = sentences[0] + '.'
+        
+        return answer