Update app.py

app.py

@@ -3,6 +3,7 @@ import gradio as gr
 import requests
 import pandas as pd
 from typing import Dict, List
+import asyncio
 
 # custom imports
 from agents import Agent
@@ -11,7 +12,8 @@ from model import get_model
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-MODEL_ID = "gemini/gemini-2.0-flash-exp"
+MODEL_ID = "groq/llama-3.3-70b-versatile"  # Groq's fastest model
+RATE_LIMIT_DELAY = 1  # Groq has generous rate limits
 
 
 # --- Async Question Processing ---
@@ -31,13 +33,18 @@ async def process_question(agent, question: str, task_id: str) -> Dict:
         }
 
 async def run_questions_async(agent, questions_data: List[Dict]) -> tuple:
-    """Process questions sequentially"""
+    """Process questions sequentially with minimal rate limiting"""
     submissions = []
     logs = []
     
     total = len(questions_data)
     for idx, q in enumerate(questions_data):
         print(f"Processing {idx+1}/{total}: {q['question'][:80]}...")
+        
+        # Add small delay between requests
+        if idx > 0:
+            await asyncio.sleep(RATE_LIMIT_DELAY)
+        
         result = await process_question(agent, q["question"], q["task_id"])
         submissions.append(result["submission"])
         logs.append(result["log"])
@@ -86,7 +93,8 @@ async def run_and_submit_all(profile: gr.OAuthProfile | None):
             print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-        # Remove this line to process all questions: questions_data = questions_data[:2]
+        estimated_time = len(questions_data) * RATE_LIMIT_DELAY / 60
+        print(f"⏱️ Estimated time: {estimated_time:.1f} minutes")
     except Exception as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
@@ -134,15 +142,18 @@ async def run_and_submit_all(profile: gr.OAuthProfile | None):
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown("# 🤖 GAIA Agent Evaluation")
     gr.Markdown(
-        """
+        f"""
         **Instructions:**
         1. Log in to your Hugging Face account using the button below
         2. Click 'Run Evaluation & Submit' to test your agent
         3. The agent will use web search and other tools to answer questions
         
         **Current Setup:**
-        - Model: Gemini 2.0 Flash (via LiteLLM)
+        - Model: Llama 3.3 70B (via Groq)
         - Tools: Web search, Wikipedia, calculation, and more
+        - Rate Limiting: {RATE_LIMIT_DELAY}s between requests
+        
+        ⚠️ **Note:** Make sure you have set your GROQ_API_KEY in the Space secrets.
         """
     )
 
@@ -162,6 +173,7 @@ if __name__ == "__main__":
     print("\n" + "="*70)
     print("🤖 GAIA Agent Starting")
     print("="*70)
+    print(f"📝 Using Model: {MODEL_ID}")
     
     space_host = os.getenv("SPACE_HOST")
     space_id = os.getenv("SPACE_ID")