Update app.py

app.py

@@ -1,196 +1,175 @@
 import os
+import re
+import tempfile
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    VisitWebpageTool,
+    tool,
+)
+
+try:
+    from smolagents import InferenceClientModel as HFModel
+except ImportError:  # older smolagents versions
+    from smolagents import HfApiModel as HFModel
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MODEL_ID = os.getenv("MODEL_ID", "Qwen/Qwen2.5-Coder-32B-Instruct")
+
+
+# --- Tools ---
+@tool
+def get_task_file(task_id: str) -> str:
+    """Download the file attached to a task (if any) and return its content or local path.
+
+    Args:
+        task_id: The task_id of the question that has an attached file.
+    """
+    try:
+        r = requests.get(f"{DEFAULT_API_URL}/files/{task_id}", timeout=60)
+        r.raise_for_status()
+    except Exception as e:
+        return f"No file could be downloaded for this task: {e}"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+    disposition = r.headers.get("content-disposition", "")
+    match = re.search(r'filename="?([^";]+)"?', disposition)
+    name = match.group(1) if match else f"{task_id}.bin"
+    path = os.path.join(tempfile.gettempdir(), name)
+    with open(path, "wb") as f:
+        f.write(r.content)
+
+    lower = name.lower()
+    try:
+        if lower.endswith((".xlsx", ".xls")):
+            sheets = pd.read_excel(path, sheet_name=None)
+            return "\n\n".join(
+                f"Sheet '{s}':\n{df.to_string()}" for s, df in sheets.items()
+            )[:20000]
+        if lower.endswith((".txt", ".csv", ".py", ".json", ".md")):
+            return r.content.decode("utf-8", errors="replace")[:20000]
+    except Exception as e:
+        return f"File saved at {path} but could not be parsed: {e}"
+    return (
+        f"File saved at {path} (type: {name.split('.')[-1]}). "
+        "It is a binary file (image/audio/other); handle it with Python code."
+    )
+
+
+SYSTEM_HINT = """You are solving GAIA-style questions. Rules:
+- Use tools (web search, visiting pages, reading attached files, Python) to find the answer.
+- Your final answer must be ONLY the answer: a number, a short string, or a comma-separated list.
+- Do NOT write 'FINAL ANSWER', explanations, units unless asked, or full sentences.
+- Numbers: no thousands separators, no currency/percent symbols unless asked.
+- Strings: no articles (a, the) and no abbreviations unless asked.
+- Lists: comma-separated, in the order requested.
+- If the question mentions an attached file, call get_task_file with the given task_id.
+"""
+
+
+# --- Agent ---
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+        model = HFModel(model_id=MODEL_ID, token=os.getenv("HF_TOKEN"))
+        self.agent = CodeAgent(
+            tools=[DuckDuckGoSearchTool(), VisitWebpageTool(), get_task_file],
+            model=model,
+            additional_authorized_imports=[
+                "pandas", "numpy", "requests", "re", "json",
+                "datetime", "math", "bs4", "collections", "itertools",
+            ],
+            max_steps=12,
+        )
+
+    def __call__(self, question: str, task_id: str = "", has_file: bool = False) -> str:
+        prompt = f"{SYSTEM_HINT}\n\ntask_id: {task_id}\n"
+        if has_file:
+            prompt += "This task has an attached file (use get_task_file).\n"
+        prompt += f"\nQuestion: {question}"
+        answer = str(self.agent.run(prompt)).strip()
+        answer = re.sub(r"(?i)^\s*final answer\s*:\s*", "", answer)
+        return answer.strip().rstrip(".") if len(answer) > 1 else answer
 
-    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
+
+# --- Run & submit ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+    if not profile:
+        return "Please log in to Hugging Face with the button.", None
+    username = profile.username
 
     api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
     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)
-    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 = requests.get(f"{api_url}/questions", timeout=30)
         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
+        questions = response.json()
     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:
+        return f"Error fetching questions: {e}", None
+
+    results_log, answers_payload = [], []
+    for item in questions:
         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}")
+        question = item.get("question")
+        has_file = bool(item.get("file_name"))
+        if not task_id or question is None:
             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})
+            answer = agent(question, task_id=task_id, has_file=has_file)
         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}"})
+            answer = f"AGENT ERROR: {e}"
+        answers_payload.append({"task_id": task_id, "submitted_answer": answer})
+        results_log.append(
+            {"Task ID": task_id, "Question": question, "Submitted Answer": answer}
+        )
 
     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)
+        return "Agent produced no answers.", pd.DataFrame(results_log)
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    submission = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
     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.')}"
+        resp = requests.post(f"{api_url}/submit", json=submission, timeout=120)
+        resp.raise_for_status()
+        data = resp.json()
+        status = (
+            f"Submission successful!\n"
+            f"User: {data.get('username')}\n"
+            f"Score: {data.get('score')}% "
+            f"({data.get('correct_count')}/{data.get('total_attempted')} correct)\n"
+            f"Message: {data.get('message')}"
         )
-        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
+        return status, pd.DataFrame(results_log)
     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 UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Agents Course - Final Assignment")
     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.
-
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-        """
+        "1. Log in with your Hugging Face account.\n"
+        "2. Click the button to run the agent on all questions and submit.\n"
+        "This can take several minutes."
     )
-
     gr.LoginButton()
-
     run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5)
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    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 repo URLs if SPACE_ID is found
-        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 Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)