Update app.py

app.py

@@ -1,52 +1,29 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-from smolagent.agents import SimpleAgent
-from transformers import pipeline
+from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- FLAN-T5 Agent Definition ---
-# Load the FLAN-T5 base model for question-answering
-qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-base")
-
-# Define a tool that wraps the FLAN-T5 model
-class FlanT5Tool:
-    def __init__(self):
-        self.name = "flan_t5_qa"
-        self.description = "Answers questions using FLAN-T5 base."
-
-    def __call__(self, question: str) -> str:
-        print(f"FlanT5Tool received: {question}")
-        response = qa_pipeline(question, max_new_tokens=100)
-        return response[0]['generated_text']
-
-# Instantiate the tool
-flan_tool = FlanT5Tool()
-
-# Create a simple agent with the FLAN-T5 tool
+# --- Define Agent ---
 class SmolAgentWrapper:
     def __init__(self):
-        self.agent = SimpleAgent(tools=[flan_tool])
+        self.model = InferenceClientModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct", provider="together")  # Uses flan-t5-base via HF Inference API
+        self.tools = [DuckDuckGoSearchTool()]  # You can add more tools here
+        self.agent = CodeAgent(model=self.model, tools=self.tools)
 
     def __call__(self, question: str) -> str:
-        print(f"SmolAgentWrapper received: {question}")
         return self.agent.run(question)
 
-# --- Run and Submit Logic ---
+
+# --- Evaluation Logic ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the agent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -56,65 +33,51 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent (with FLAN-T5)
+    # Create the agent
     try:
         agent = SmolAgentWrapper()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
+
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    # Fetch questions
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-            print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # Run agent
     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)
             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}"})
+            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.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
+    # Submit answers
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
 
-    # 5. Submit
-    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()
@@ -126,55 +89,28 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
-        print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Smol Agent Evaluation Runner")
+    gr.Markdown("# SmolAgent Evaluation Runner (Flan-T5 + DuckDuckGo Tool)")
     gr.Markdown(
         """
         **Instructions:**
-        1.  Log in to your Hugging Face account using the button below.
-        2.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-        ---
-        **Disclaimers:**
-        This space uses a small agent powered by FLAN-T5 base for answering questions.
+        1. Log in to Hugging Face with the button below.
+        2. Click the button to run all GAIA questions through the SmolAgent.
+        3. Results will be submitted automatically and your score will be shown.
+
+        **Note:** Model runs on Hugging Face Inference API using `flan-t5-base`, optimized for CPU.
         """
     )
 
     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)
 
@@ -184,5 +120,7 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("Launching Gradio Interface for Smol Agent Evaluation...")
+    print("-" * 60)
+    print("Launching SmolAgent Space...")
+    print("-" * 60)
     demo.launch(debug=True, share=False)