Update app.py

app.py

@@ -3,12 +3,13 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-
+import torch
 from transformers import BartForConditionalGeneration, BartTokenizer
-from smolagents import ToolCallingAgent
+
 from audio_transcriber import AudioTranscriptionTool
 from image_analyzer import ImageAnalysisTool
 from wikipedia_searcher import WikipediaSearcher
+from smolagents import ToolCallingAgent
 
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
@@ -30,37 +31,37 @@ SYSTEM_PROMPT = (
     "Never say 'the answer is...'. Only return the answer.\n"
 )
 
+# Local wrapper for facebook/bart-base that exposes generate()
 class LocalBartModel:
-    def __init__(self, model_name="facebook/bart-base", device=None):
-        import torch
-        self.device = device if device else ("cuda" if torch.cuda.is_available() else "cpu")
+    def __init__(self, model_name="facebook/bart-base"):
         self.tokenizer = BartTokenizer.from_pretrained(model_name)
-        self.model = BartForConditionalGeneration.from_pretrained(model_name).to(self.device)
+        self.model = BartForConditionalGeneration.from_pretrained(model_name)
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model.to(self.device)
 
-    def __call__(self, prompt: str) -> str:
-        import torch
+    def generate(self, input_ids, **generate_kwargs):
+        return self.model.generate(input_ids.to(self.device), **generate_kwargs)
 
-        inputs = self.tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512).to(self.device)
-        outputs = self.model.generate(
-            **inputs,
-            max_length=128,
+    def __call__(self, prompt: str) -> str:
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.device)
+        output_ids = self.generate(
+            inputs.input_ids,
+            max_length=100,
             num_beams=5,
             early_stopping=True
         )
-        decoded = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return decoded.strip()
+        output_text = self.tokenizer.decode(output_ids[0], skip_special_tokens=True)
+        return output_text.strip()
 
 class GaiaAgent:
     def __init__(self):
         print("Gaia Agent Initialized")
         self.model = LocalBartModel()
-
         self.tools = [
             AudioTranscriptionTool(),
             ImageAnalysisTool(),
             WikipediaSearcher()
         ]
-
         self.agent = ToolCallingAgent(
             tools=self.tools,
             model=self.model
@@ -143,79 +144,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             results_log.append({
                 "Task ID": task_id,
                 "Question": item.get("question", ""),
-                "Submitted Answer": error_msg
-            })
-
-    if not answers_payload:
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    submission_data = {
-        "username": username.strip(),
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
-
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
-    try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        try:
-            detail = e.response.json().get("detail", e.response.text)
-        except Exception:
-            detail = e.response.text[:500]
-        return f"Submission Failed: {detail}", pd.DataFrame(results_log)
-    except requests.exceptions.Timeout:
-        return "Submission Failed: The request timed out.", pd.DataFrame(results_log)
-    except Exception as e:
-        return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
-
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown("""
-        **Instructions:**
-        1. Clone this space and define your agent and tools.
-        2. Log in to your Hugging Face account using the button below.
-        3. Click 'Run Evaluation & Submit All Answers' to test your agent and submit results.
-    """)
-
-    gr.LoginButton()
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
-
-if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    space_host = os.getenv("SPACE_HOST")
-    space_id = os.getenv("SPACE_ID")
-
-    if space_host:
-        print(f"✅ SPACE_HOST found: {space_host}")
-        print(f"   Runtime URL should be: https://{space_host}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST not found.")
-
-    if space_id:
-        print(f"✅ SPACE_ID found: {space_id}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id}")
-    else:
-        print("ℹ️  SPACE_ID not found.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-    demo.launch(debug=True, share=False)
+                "Submi