Update app.py

app.py

@@ -1,7 +1,9 @@
 import os
+import concurrent.futures
 import gradio as gr
 import requests
 import inspect
+import re
 import pandas as pd
 import markdownify
 from smolagents import tool, CodeAgent, DuckDuckGoSearchTool, InferenceClientModel, OpenAIServerModel, VisitWebpageTool
@@ -62,6 +64,15 @@ class WebSearchAgent:
             print("Agent error:", e)
             return f"AGENT ERROR: {e}"
 
+
+MAX_WORKERS = 4        # questions answered in parallel
+QUESTION_TIMEOUT = 180  # seconds before a single question is abandoned
+
+
+def _answer_question(question_text: str) -> str:
+    """Instantiate a fresh agent and answer one question (safe to run in a thread)."""
+    return WebSearchAgent()(question_text)
+
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
@@ -81,14 +92,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
-    try:
-        # agent = BasicAgent()
-        agent = WebSearchAgent()
-    except Exception as e:
-        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)
+    # 1. Agent is instantiated per-question inside _answer_question for parallel execution
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
@@ -113,23 +117,34 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run your Agent (parallel)
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in 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
-        try:
-            submitted_answer = agent(question_text)
+    valid_items = [
+        item for item in questions_data
+        if item.get("task_id") and item.get("question") is not None
+    ]
+    print(f"Running agent on {len(valid_items)} questions (up to {MAX_WORKERS} in parallel)...")
+
+    with concurrent.futures.ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
+        future_to_item = {
+            executor.submit(_answer_question, item["question"]): item
+            for item in valid_items
+        }
+        for future in concurrent.futures.as_completed(future_to_item):
+            item = future_to_item[future]
+            task_id = item["task_id"]
+            question_text = item["question"]
+            try:
+                submitted_answer = future.result(timeout=QUESTION_TIMEOUT)
+            except concurrent.futures.TimeoutError:
+                print(f"Timeout on task {task_id}")
+                submitted_answer = "TIMEOUT"
+            except Exception as e:
+                print(f"Error running agent on task {task_id}: {e}")
+                submitted_answer = f"AGENT ERROR: {e}"
             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:
-             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 not answers_payload:
         print("Agent did not produce any answers to submit.")