Added threading

app.py

@@ -3,6 +3,8 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+import json
+import threading
 
 # Import our custom tools from their modules
 from huggingface_hub import login
@@ -155,55 +157,85 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         return f"An unexpected error occurred fetching questions: {e}", None
 
     # 3. Run your Agent
-    # from concurrent.futures import ThreadPoolExecutor, as_completed
-
-    # results_log = []
-    # answers_payload = []
-    # print(f"Running agent on {len(questions_data)} questions...")
-    
-    # def process_question(item):
-    #     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}")
-    #         return None, None, None
-    #     try:
-    #         submitted_answer = agent(question_text)
-    #         return task_id, question_text, submitted_answer
-    #     except Exception as e:
-    #         print(f"Error running agent on task {task_id}: {e}")
-    #         return task_id, question_text, f"AGENT ERROR: {e}"
-    
-    # with ThreadPoolExecutor(max_workers=5) as executor:
-    #     futures = {executor.submit(process_question, item): item for item in questions_data}
-    #     for future in as_completed(futures):
-    #         task_id, question_text, submitted_answer = future.result()
-    #         if task_id is None:
-    #             continue
-    #         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})
     
+    from concurrent.futures import ThreadPoolExecutor, as_completed, TimeoutError
+    cache_lock = threading.Lock()
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+
+    CACHE_FILE = "answer_cache.json"
+    cache = json.load(open(CACHE_FILE)) if os.path.exists(CACHE_FILE) else {}
+
+    def process_question(item):
         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
+            return None, None, None
+
+        # Return cached answer if available
+        if task_id in cache:
+            print(f"Cache hit for task {task_id}")
+            return task_id, question_text, cache[task_id]
+        
         try:
-            # submitted_answer = agent(question_text)
             question_with_context = f"""Task ID: {task_id}
-            If this question refers to an attached file, download it first from:
-            https://agents-course-unit4-scoring.hf.space/files/{task_id}
-            {question_text}"""
-            submitted_answer = agent(question_with_context) # for Excel and audio questions
-            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})
+If this question refers to an attached file, download it first from:
+https://agents-course-unit4-scoring.hf.space/files/{task_id}
+{question_text}"""
+            submitted_answer = agent(question_with_context)
+            # Save to cache
+            with cache_lock:
+                cache[task_id] = submitted_answer
+                json.dump(cache, open(CACHE_FILE, "w"))
+            return task_id, question_text, 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}")
+            return task_id, question_text, f"AGENT ERROR: {e}"
+    
+    with ThreadPoolExecutor(max_workers=3) as executor:
+        futures = {executor.submit(process_question, item): item for item in questions_data}
+        for future in as_completed(futures):
+            item = futures[future]
+            task_id = item.get("task_id")
+            question_text = item.get("question")
+            try:
+                result_task_id, result_question, submitted_answer = future.result(timeout=120)
+                if result_task_id is None:
+                    continue
+                answers_payload.append({"task_id": result_task_id, "submitted_answer": submitted_answer})
+                results_log.append({"Task ID": result_task_id, "Question": result_question, "Submitted Answer": submitted_answer})
+            except TimeoutError:
+                print(f"Task {task_id} timed out after 120s, skipping.")
+                answers_payload.append({"task_id": task_id, "submitted_answer": "TIMEOUT"})
+                results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": "TIMEOUT"})
+            except Exception as e:
+                print(f"Task {task_id} raised an exception: {e}")
+                answers_payload.append({"task_id": task_id, "submitted_answer": f"AGENT ERROR: {e}"})
+                results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+    
+    # 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)
+    #         question_with_context = f"""Task ID: {task_id}
+    #         If this question refers to an attached file, download it first from:
+    #         https://agents-course-unit4-scoring.hf.space/files/{task_id}
+    #         {question_text}"""
+    #         submitted_answer = agent(question_with_context) # for Excel and audio questions
+    #         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.")