upapp.py

app.py

@@ -1,196 +1,247 @@
 import os
+import re
+import subprocess
+import time
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    LiteLLMModel,
+    VisitWebpageTool,
+    tool,
+)
 
-# (Keep Constants as is)
-# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MODEL_ID = os.getenv("MODEL_ID", "gemini/gemini-2.0-flash")  # modele du LLM (changeable via les variables du Space)
+PAUSE_BETWEEN_QUESTIONS = 8  # secondes, pour eviter les limites de requetes gratuites
+FILES_DIR = "/tmp/task_files"
+os.makedirs(FILES_DIR, exist_ok=True)
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-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):
+
+# ----------------------------------------------------------------------------
+# Outils personnalises
+# ----------------------------------------------------------------------------
+@tool
+def read_excel_file(path: str) -> str:
+    """Reads an Excel file (.xlsx) and returns all its sheets as text.
+
+    Args:
+        path: Local path of the Excel file.
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    sheets = pd.read_excel(path, sheet_name=None)
+    out = []
+    for name, df in sheets.items():
+        out.append(f"--- Sheet: {name} ---\n{df.to_string()}")
+    return "\n\n".join(out)
+
+
+@tool
+def read_text_file(path: str) -> str:
+    """Reads a text or code file (.py, .txt, .csv...) and returns its content.
+
+    Args:
+        path: Local path of the file.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    with open(path, "r", encoding="utf-8", errors="ignore") as f:
+        return f.read()
+
+
+@tool
+def run_python_file(path: str) -> str:
+    """Runs a Python file and returns what it prints (stdout and stderr).
+
+    Args:
+        path: Local path of the Python file to run.
+    """
+    try:
+        result = subprocess.run(
+            ["python", path], capture_output=True, text=True, timeout=60
+        )
+        return (result.stdout + result.stderr).strip()
+    except Exception as e:
+        return f"Execution error: {e}"
+
+
+@tool
+def transcribe_audio(path: str) -> str:
+    """Transcribes an audio file (mp3, wav...) to text using Whisper on Groq.
+
+    Args:
+        path: Local path of the audio file.
+    """
+    api_key = os.getenv("GROQ_API_KEY")
+    if not api_key:
+        return "Error: GROQ_API_KEY is not set in the Space secrets."
+    with open(path, "rb") as f:
+        response = requests.post(
+            "https://api.groq.com/openai/v1/audio/transcriptions",
+            headers={"Authorization": f"Bearer {api_key}"},
+            files={"file": (os.path.basename(path), f)},
+            data={"model": "whisper-large-v3"},
+            timeout=120,
+        )
+    if response.status_code != 200:
+        return f"Transcription error {response.status_code}: {response.text[:300]}"
+    return response.json().get("text", "")
+
+
+# ----------------------------------------------------------------------------
+# Agent
+# ----------------------------------------------------------------------------
+SYSTEM_RULES = """You are answering questions from the GAIA benchmark. Be precise.
+Rules for your final answer:
+- Reply with ONLY the final answer. No explanation, no sentence, no 'FINAL ANSWER'.
+- Numbers: write digits only, without units or thousands separators, unless the question asks otherwise.
+- Lists: comma-separated, in the order requested (alphabetical or ascending if asked).
+- Strings: no articles, no abbreviations unless the question asks for them.
+- Use web search and visit_webpage to verify facts instead of guessing.
+- If a file path is given, use the provided file tools to read it.
+"""
+
+
+class GaiaAgent:
+    def __init__(self):
+        model = LiteLLMModel(
+            model_id=MODEL_ID,
+            api_key=os.getenv("GEMINI_API_KEY"),
+        )
+        self.agent = CodeAgent(
+            tools=[
+                DuckDuckGoSearchTool(),
+                VisitWebpageTool(),
+                read_excel_file,
+                read_text_file,
+                run_python_file,
+                transcribe_audio,
+            ],
+            model=model,
+            max_steps=12,
+            additional_authorized_imports=[
+                "pandas", "numpy", "re", "json", "math", "datetime",
+                "itertools", "collections", "statistics", "unicodedata",
+                "requests", "bs4",
+            ],
+            verbosity_level=0,
+        )
 
-    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, file_path: str | None = None) -> str:
+        prompt = f"{SYSTEM_RULES}\nQuestion: {question}"
+        if file_path:
+            prompt += f"\n\nAn attached file is available locally at: {file_path}"
+        answer = str(self.agent.run(prompt)).strip()
+        answer = re.sub(r"^\s*final answer\s*:\s*", "", answer, flags=re.IGNORECASE)
+        return answer.strip().strip('"').strip()
+
+
+def download_task_file(api_url: str, task_id: str, file_name: str) -> str | None:
+    """Telecharge le fichier associe a une question (si elle en a un)."""
+    if not file_name:
+        return None
+    try:
+        r = requests.get(f"{api_url}/files/{task_id}", timeout=60)
+        r.raise_for_status()
+        local_path = os.path.join(FILES_DIR, file_name)
+        with open(local_path, "wb") as f:
+            f.write(r.content)
+        return local_path
+    except Exception as e:
+        print(f"Could not download file for {task_id}: {e}")
+        return None
+
+
+# ----------------------------------------------------------------------------
+# Evaluation + soumission
+# ----------------------------------------------------------------------------
+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()
+        agent = GaiaAgent()
     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
+        return f"Error 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:
+    for i, item in enumerate(questions):
         task_id = item.get("task_id")
         question_text = item.get("question")
+        file_name = item.get("file_name", "")
         if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
             continue
+        file_path = download_task_file(api_url, task_id, file_name)
         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_text, file_path)
         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 on task {task_id}: {e}")
+            answer = "AGENT ERROR"
+        answers_payload.append({"task_id": task_id, "submitted_answer": answer})
+        results_log.append(
+            {
+                "Task ID": task_id,
+                "Question": question_text[:150],
+                "Submitted Answer": answer,
+            }
+        )
+        print(f"[{i + 1}/{len(questions)}] {answer}")
+        time.sleep(PAUSE_BETWEEN_QUESTIONS)
 
     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 did not produce any 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 = requests.post(f"{api_url}/submit", json=submission, timeout=120)
         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.')}"
+        data = response.json()
+        status = (
+            "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 ---
+# ----------------------------------------------------------------------------
+# Interface Gradio
+# ----------------------------------------------------------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# 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.
-
-        ---
-        **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: the agent answers the 20 questions and submits them.\n"
+        "3. This can take 10 to 20 minutes. Keep the page open."
     )
-
     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=6, 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]
-    )
+    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)