Update agent.py

agent.py

@@ -1,71 +1,206 @@
 # 17/08/2025 -AO
-import math
-import re
+import os
+import gradio as gr
 import requests
-from typing import Optional
+import pandas as pd
+from transformers import HfAgent
+from transformers.tools import DuckDuckGoSearchTool
 
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class BasicAgent:
+# --- Advanced Agent Definition ---
+class MyAgent:
+    def __init__(self):
+        # Define the LLM for the agent. Use a supported model from the Hugging Face Hub.
+        # Ensure you have the necessary environment variables (e.g., HF_TOKEN).
+        # You'll likely need a powerful model to get a high score.
+        # Example: Using a powerful hosted model
+        self.agent = HfAgent("HuggingFaceH4/zephyr-7b-beta",
+                             additional_tools=[DuckDuckGoSearchTool()])
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question: {question[:50]}...")
+        # Use a try-except block to handle potential errors during execution.
+        try:
+            # Let the agent reason and find the answer.
+            # Use verbose=True to see the agent's thought process for debugging.
+            result = self.agent.run(question)
+            # The GAIA scoring is an "EXACT MATCH".
+            # The prompt asks the agent to just return the answer, not a verbose explanation.
+            # You might need to add a post-processing step to extract the final answer.
+            # For example, by telling the model in the prompt to only output the answer.
+            final_answer = str(result)
+            print(f"Agent returning answer: {final_answer}")
+            return final_answer
+        except Exception as e:
+            print(f"An error occurred during agent execution: {e}")
+            return f"Error: {e}"
+
+# The rest of the `run_and_submit_all` and Gradio code remains the same as in the template.
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Very simple baseline agent.
-    - Tries to solve basic arithmetic expressions found in the question.
-    - If it cannot, returns a default safe string.
-    Keep responses concise because the grader does exact-match comparison.
+    Fetches all questions, runs the agent on them, submits all answers,
+    and displays the results.
     """
+    space_id = os.getenv("SPACE_ID")
 
-    def __init__(self, api_url: str = DEFAULT_API_URL):
-        self.api_url = api_url
-        # Precompile a simple arithmetic pattern like "12 + 3 * 4" or "(5+2)/7"
-        self.expr_pattern = re.compile(r"^[\s\d\+\-\*/\(\)\.]+$")
-
-    def try_eval_math(self, text: str) -> Optional[str]:
-        # Extract a math-like snippet if the whole string looks like math.
-        s = text.strip()
-        if not s:
-            return None
-        if self.expr_pattern.match(s):
-            try:
-                # Safe eval using eval on limited globals/locals.
-                val = eval(s, {"__builtins": {}}, {"math": math})
-                # Format as plain value string.
-                return str(val)
-            except Exception:
-                return None
-        return None
+    if profile:
+        username = f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
 
-    def __call__(self, question: str) -> str:
-        # Try direct arithmetic
-        ans = self.try_eval_math(question)
-        if ans is not None:
-            return ans
-
-        # Extremely small heuristics: look for numbers and operations within the sentence.
-        digits = re.findall(r"[\d\.]+", question)
-        if len(digits) >= 2:
-            try:
-                # If words like 'sum' or 'add' appear, add the numbers.
-                ql = question.lower()
-                nums = list(map(float, digits))
-                if any(k in ql for k in ["sum", "add", "+"]):
-                    return str(sum(nums))
-                if any(k in ql for k in ["difference", "subtract", "-"]):
-                    return str(nums[0] - sum(nums[1:]))
-                if any(k in ql for k in ["product", "multiply", "*"]):
-                    p = 1.0
-                    for n in nums:
-                        p *= n
-                    return str(p)
-                if any(k in ql for k in ["divide", "ratio", "/"]):
-                    try:
-                        res = nums[0]
-                        for n in nums[1:]:
-                            res /= n
-                        return str(res)
-                    except ZeroDivisionError:
-                        return "undefined"
-            except Exception:
-                pass
-
-        # Fallback default answer; keep minimal for exact-match grading.
-        return "unknown"
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # 1. Instantiate Agent
+    try:
+        agent = MyAgent()  # Instantiate your new agent class
+    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}")
+    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
+
+    # 3. Run your 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}"})
+
+    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)
+
+    # 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()
+        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.')}"
+        )
+        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
+
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Advanced Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+
+        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        """
+    )
+    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_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID")
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    if space_id_startup:
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for Advanced Agent Evaluation...")
+    demo.launch(debug=True, share=False)