Update app.py

app.py

@@ -61,12 +61,14 @@ class NewAgent:
             sys_msg = SystemMessage(
                 content=f"""
                 You are a general AI assistant. I will ask you a question. 
+                If a file_name is provided, it indicates there's an associated file you may need to analyze:
                 If you cannot find an answer, you may report your thoughts.
                 If you find an answer, your response should only contain your final answer. Report nothing before or after this answer.
                 YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
                 If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise.
                 If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
-                If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."""
+                If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+                Current file (if any): {file_name}"""
                                    )
             return {
                 "messages": [llm_with_tools.invoke([sys_msg] + state["messages"])],
@@ -91,128 +93,6 @@ class NewAgent:
         messages = [HumanMessage(content=question)]
         response = alfred.invoke({"messages": messages})
         return response['messages'][-1].content
-
-
-class NewAgent2:
-    def __init__(self):
-        print("NewAgent initialized.")
-    
-    def _process_question_input(self, question_input: Union[str, Dict[str, Any]]) -> tuple:
-        """
-        Process the question input which could be:
-        - A simple string
-        - A dictionary with text and image data
-        """
-        if isinstance(question_input, str):
-            return question_input, None
-        
-        # If it's a dictionary, extract text and image
-        if isinstance(question_input, dict):
-            text = question_input.get('text', question_input.get('question', ''))
-            image_data = question_input.get('image', question_input.get('image_url', None))
-            return text, image_data
-        
-        return str(question_input), None
-    
-    def _create_message_content(self, text: str, image_data: str = None) -> Union[str, list]:
-        """
-        Create message content that can handle both text and images
-        """
-        if not image_data:
-            return text
-        
-        # Handle different image formats
-        if image_data.startswith('http'):
-            # URL format
-            return [
-                {"type": "text", "text": text},
-                {"type": "image_url", "image_url": {"url": image_data}}
-            ]
-        elif image_data.startswith('data:image'):
-            # Base64 data URL format
-            return [
-                {"type": "text", "text": text},
-                {"type": "image_url", "image_url": {"url": image_data}}
-            ]
-        else:
-            # Assume it's base64 encoded image data
-            image_url = f"data:image/jpeg;base64,{image_data}"
-            return [
-                {"type": "text", "text": text},
-                {"type": "image_url", "image_url": {"url": image_url}}
-            ]
-
-    def __call__(self, question: Union[str, Dict[str, Any]]) -> str:
-        print(f"Agent received question input: {str(question)[:100]}...")
-        
-        # Process the input to extract text and image
-        question_text, image_data = self._process_question_input(question)
-        print(f"Extracted text: {question_text[:50]}...")
-        print(f"Image data present: {image_data is not None}")
-        
-        # Initialize the web search tool
-        search_tool = DuckDuckGoSearchRun()
-        # Initialize the Hub stats tool
-        hub_stats_tool = Tool(
-            name="get_hub_stats",
-            func=get_hub_stats,
-            description="Fetches the most downloaded model from a specific author on the Hugging Face Hub."
-        )
-        # Generate the chat interface, including the tools
-        tools = [
-            search_tool,
-            hub_stats_tool,
-        ]
-        
-        # Use a vision-capable model
-        llm = ChatOpenAI(model="gpt-4o")  # Vision-capable model
-        llm_with_tools = llm.bind_tools(tools, parallel_tool_calls=False)
-        
-        # Generate the AgentState and Agent graph
-        class AgentState(TypedDict):
-            messages: Annotated[list[AnyMessage], add_messages]
-            
-        def assistant(state: AgentState):
-            sys_msg = SystemMessage(
-                content=f"""
-                You are a general AI assistant. I will ask you a question that may include text and/or images. 
-                If you cannot find an answer, you may report your thoughts.
-                If you find an answer, your response should only contain your final answer. Report nothing before or after this answer.
-                YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings.
-                If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise.
-                If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
-                If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
-                
-                If an image is provided, analyze it carefully and answer based on what you see in the image.
-                """
-            )
-            
-            return {
-                "messages": [llm_with_tools.invoke([sys_msg] + state["messages"])],
-            }
-            
-        ## The graph
-        builder = StateGraph(AgentState)
-        # Define nodes: these do the work
-        builder.add_node("assistant", assistant)
-        builder.add_node("tools", ToolNode(tools))
-        # Define edges: these determine how the control flow moves
-        builder.add_edge(START, "assistant")
-        builder.add_conditional_edges(
-            "assistant",
-            # If the latest message requires a tool, route to tools
-            # Otherwise, provide a direct response
-            tools_condition,
-        )
-        builder.add_edge("tools", "assistant")
-        alfred = builder.compile()
-        
-        # Create the human message with proper content format
-        message_content = self._create_message_content(question_text, image_data)
-        messages = [HumanMessage(content=message_content)]
-        
-        response = alfred.invoke({"messages": messages})
-        return response['messages'][-1].content
         
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
@@ -237,8 +117,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         # agent = BasicAgent()
-        # agent = NewAgent()
-        agent = NewAgent2()
+        agent = NewAgent()
+        # agent = NewAgent2()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -274,16 +154,17 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+        file_name = item.get("file_name", "")
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, file_name)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "File": file_name, "Submitted Answer": submitted_answer})
         except Exception as e:
              print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+             results_log.append({"Task ID": task_id, "Question": question_text, "File": file_name, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")