Update app.py

app.py

@@ -3,8 +3,10 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+import time
 from agent import ClaudeAgent
 from dotenv import load_dotenv
+import random
 
 # Load environment variables
 load_dotenv()
@@ -19,17 +21,6 @@ else:
 # --- 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
-
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
@@ -52,7 +43,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         # agent = BasicAgent()
-        agent = ClaudeAgent()
+        agent = GeminiAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -85,19 +76,42 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    
+    # Process with rate limiting to avoid Anthropic API limits
+    for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
+        
+        # Add a progress indicator
+        print(f"Processing question {i+1}/{len(questions_data)}: Task ID {task_id}")
+        
         try:
+            # Add a delay between requests to respect rate limits
+            if i > 0:
+                # Random delay between 2-5 seconds 
+                sleep_time = random.uniform(2, 5)
+                print(f"Waiting {sleep_time:.2f} seconds before next question...")
+                time.sleep(sleep_time)
+            
+            # Process the question
             submitted_answer = agent(question_text)
             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})
+            
+            # Print answer for monitoring
+            print(f"Answer for task {task_id}: {submitted_answer[:100]}..." if len(submitted_answer) > 100 else f"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}"})
+            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}"})
+            
+            # If this was a rate limit error, add a longer cooldown period
+            if "rate_limit" in str(e).lower():
+                cool_down = 60  # 1 minute cooldown
+                print(f"Rate limit detected. Cooling down for {cool_down} seconds...")
+                time.sleep(cool_down)
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
@@ -154,17 +168,18 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Agent Evaluation Runner")
     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).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        1. Make sure your ANTHROPIC_API_KEY is set in the Hugging Face Space secrets
+        2. Log in to your Hugging Face account using the button below
+        3. Click 'Run Evaluation & Submit All Answers' to process all questions
+        
+        **Notes:**
+        - This agent uses Claude 3.5 Sonnet with rate limiting to avoid exceeding API limits
+        - Questions are processed sequentially with delays between requests
+        - The entire process may take several minutes to complete
         """
     )
 
@@ -173,7 +188,6 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -202,5 +216,5 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for GAIA Agent Evaluation...")
     demo.launch(debug=True, share=False)