Update app.py

app.py

@@ -1,23 +1,163 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+import os
+from agents import manager_agent
+from datetime import datetime
+from typing import Optional
+import time
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        self.agent = manager_agent
+        self.verbose = True
+
+    def __call__(self, question: str, files: list[str] = None) -> str:
+        print(f"Agent received question: {question[:50]}... with files: {files}")
+        result = self.answer_question(question, files)
+        print(f"Agent returning answer: {result}")
+        #time.sleep(60)
+        return result
+    def answer_question(self, question: str, task_file_path: Optional[str] = None) -> str:
+        """
+        Process a GAIA benchmark question and return the answer
+        
+        Args:
+            question: The question to answer
+            task_file_path: Optional path to a file associated with the question
+            
+        Returns:
+            The answer to the question
+        """
+        try:
+            if self.verbose:
+                print(f"Processing question: {question}")
+                if task_file_path:
+                    print(f"With associated file: {task_file_path}")
+            
+            # Create a context with file information if available
+            context = question
+            
+            # If there's a file, read it and include its content in the context
+            if task_file_path:
+                try:
+                    context = f"""
+Question: {question}
+
+This question has an associated file. You can download the file from 
+{DEFAULT_API_URL}/files/{task_file_path}
+using the download_file_from_url tool.
+
+Analyze the file content above to answer the question.
+"""
+                except Exception as file_e:
+                    context = f"""
+Question: {question}
+
+This question has an associated file at path: {task_file_path}
+However, there was an error reading the file: {file_e}
+You can still try to answer the question based on the information provided.
+"""
+            
+            # Check for special cases that need specific formatting
+            # Reversed text questions
+            if question.startswith(".") or ".rewsna eht sa" in question:
+                context = f"""
+This question appears to be in reversed text. Here's the reversed version:
+{question[::-1]}
+
+Now answer the question above. Remember to format your answer exactly as requested.
+"""
+            
+            # Add a prompt to ensure precise answers
+            full_prompt = f"""{context}
+
+When answering, provide ONLY the precise answer requested. 
+Do not include explanations, steps, reasoning, or additional text.
+Be direct and specific. GAIA benchmark requires exact matching answers.
+For example, if asked "What is the capital of France?", respond simply with "Paris".
+"""
+            
+            # Run the agent with the question
+            answer = self.agent.run(full_prompt)
+            
+            # Clean up the answer to ensure it's in the expected format
+            # Remove common prefixes that models often add
+            answer = self._clean_answer(answer)
+            
+            if self.verbose:
+                print(f"Generated answer: {answer}")
+                
+            return answer
+        except Exception as e:
+            error_msg = f"Error answering question: {e}"
+            if self.verbose:
+                print(error_msg)
+            return error_msg
+    
+    def _clean_answer(self, answer: any) -> str:
+        """
+        Clean up the answer to remove common prefixes and formatting
+        that models often add but that can cause exact match failures.
+        
+        Args:
+            answer: The raw answer from the model
+            
+        Returns:
+            The cleaned answer as a string
+        """
+        # Convert non-string types to strings
+        if not isinstance(answer, str):
+            # Handle numeric types (float, int)
+            if isinstance(answer, float):
+                # Format floating point numbers properly
+                # Check if it's an integer value in float form (e.g., 12.0)
+                if answer.is_integer():
+                    formatted_answer = str(int(answer))
+                else:
+                    # For currency values that might need formatting
+                    if abs(answer) >= 1000:
+                        formatted_answer = f"${answer:,.2f}"
+                    else:
+                        formatted_answer = str(answer)
+                return formatted_answer
+            elif isinstance(answer, int):
+                return str(answer)
+            else:
+                # For any other type
+                return str(answer)
+        
+        # Now we know answer is a string, so we can safely use string methods
+        # Normalize whitespace
+        answer = answer.strip()
+        
+        # Remove common prefixes and formatting that models add
+        prefixes_to_remove = [
+            "The answer is ", 
+            "Answer: ",
+            "Final answer: ",
+            "The result is ",
+            "To answer this question: ",
+            "Based on the information provided, ",
+            "According to the information: ",
+        ]
+        
+        for prefix in prefixes_to_remove:
+            if answer.startswith(prefix):
+                answer = answer[len(prefix):].strip()
+        
+        # Remove quotes if they wrap the entire answer
+        if (answer.startswith('"') and answer.endswith('"')) or (answer.startswith("'") and answer.endswith("'")):
+            answer = answer[1:-1].strip()
+        
+        return answer
+
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -45,7 +185,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
     # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    agent_code = f"https://github.com/ssgrummons/huggingface_final_assignment"
     print(agent_code)
 
     # 2. Fetch Questions
@@ -76,11 +216,16 @@ 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")
+        files = 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)
+            if files is None or files == '':
+                print(files)
+                submitted_answer = agent(question_text)
+            else:
+                submitted_answer = agent(question_text, task_id)
             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})
         except Exception as e:
@@ -146,11 +291,9 @@ with gr.Blocks() as demo:
     gr.Markdown(
         """
         **Instructions:**
-
         1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
         2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
         3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
         ---
         **Disclaimers:**
         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
@@ -171,7 +314,38 @@ with gr.Blocks() as demo:
         outputs=[status_output, results_table]
     )
 
+import sys
+from pathlib import Path
+
+class Tee:
+    def __init__(self, file_path):
+        log_path = Path(file_path)
+        log_path.parent.mkdir(parents=True, exist_ok=True)
+        self.terminal_stdout = sys.__stdout__
+        self.terminal_stderr = sys.__stderr__
+        self.log = open(log_path, "a")
+
+    def write(self, message):
+        self.terminal_stdout.write(message)
+        self.log.write(message)
+
+    def flush(self):
+        self.terminal_stdout.flush()
+        self.log.flush()
+
+    def isatty(self):
+        return self.terminal_stdout.isatty()
+
+
 if __name__ == "__main__":
+    
+    # Redirect stdout and stderr
+    log_timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    log_file = f"./logs/output_{log_timestamp}.log"
+    tee = Tee(log_file)
+    sys.stdout = tee
+    sys.stderr = tee
+
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")