Update app.py

app.py

@@ -0,0 +1,411 @@
+import os
+import re
+import pathlib
+import tempfile
+from pathlib import Path
+from typing import Union, Optional
+
+import openai
+import requests
+import gradio as gr
+import pandas as pd
+from tabulate import tabulate
+from smolagents import OpenAIServerModel,DuckDuckGoSearchTool,CodeAgent, WikipediaSearchTool
+from smolagents.tools import PipelineTool, Tool
+
+
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+
+class SpeechToTextTool(PipelineTool):
+    """
+    Transcribes an audio file to text using the OpenAI Whisper API.
+    Only local file paths are supported.
+    """
+
+    default_checkpoint = "openai/whisper-1"  # purely informational here
+    description = (
+        "This tool sends an audio file to OpenAI Whisper and returns the "
+        "transcribed text."
+    )
+    name = "transcriber"
+    inputs = {
+        "audio": {
+            "type": "string",
+            "description": "Absolute or relative path to a local audio file.",
+        }
+    }
+    output_type = "string"
+
+    # ──────────────────────────────────────────────────────────────────────────
+    # Public interface
+    # ──────────────────────────────────────────────────────────────────────────
+    def __call__(self, audio: str) -> str:
+        """
+        Convenience wrapper so the tool can be used like a regular function:
+            text = SpeechToTextTool()(path_to_audio)
+        """
+        return self._transcribe(audio)
+
+    # ──────────────────────────────────────────────────────────────────────────
+    # Internal helpers
+    # ──────────────────────────────────────────────────────────────────────────
+    @staticmethod
+    def _transcribe(audio_path: str) -> str:
+        # ----- validation ----------------------------------------------------
+        if not isinstance(audio_path, str):
+            raise TypeError(
+                "Parameter 'audio' must be a string containing the file path."
+            )
+        path = Path(audio_path).expanduser().resolve()
+        if not path.is_file():
+            raise FileNotFoundError(f"No such audio file: {path}")
+
+        # ----- API call ------------------------------------------------------
+        with path.open("rb") as fp:
+            response = openai.audio.transcriptions.create(
+                file=fp,
+                model="whisper-1",  # currently the only Whisper model
+                response_format="text",  # returns plain text instead of JSON
+            )
+
+        # For response_format="text", `response` is already the raw transcript
+        return response
+
+
+class ExcelToTextTool(Tool):
+    """Render an Excel worksheet as Markdown text."""
+
+    # ------------------------------------------------------------------
+    # Required smol‑agents metadata
+    # ------------------------------------------------------------------
+    name = "excel_to_text"
+    description = (
+        "Read an Excel file and return a Markdown table of the requested sheet. "
+        "Accepts either the sheet name or the zero-based index."
+    )
+
+    inputs = {
+        "excel_path": {
+            "type": "string",
+            "description": "Path to the Excel file (.xlsx / .xls).",
+        },
+        "sheet_name": {
+            "type": "string",
+            "description": (
+                "Worksheet name or zero-based index *as a string* (optional; default first sheet)."
+            ),
+            "nullable": True,
+        },
+    }
+
+    output_type = "string"
+
+    def forward(
+        self,
+        excel_path: str,
+        sheet_name: Optional[str] = None,
+    ) -> str:
+        """Load *excel_path* and return the sheet as a Markdown table."""
+
+        path = pathlib.Path(excel_path).expanduser().resolve()
+        if not path.exists():
+            return f"Error: Excel file not found at {path}"
+
+        try:
+            # Interpret sheet identifier -----------------------------------
+            sheet: Union[str, int]
+            if sheet_name is None or sheet_name == "":
+                sheet = 0  # first sheet
+            else:
+                # If the user passed a numeric string (e.g. "1"), cast to int
+                sheet = int(sheet_name) if sheet_name.isdigit() else sheet_name
+
+            # Load worksheet ----------------------------------------------
+            df = pd.read_excel(path, sheet_name=sheet)
+
+            # Render to Markdown; fall back to tabulate if needed ---------
+            if hasattr(pd.DataFrame, "to_markdown"):
+                return df.to_markdown(index=False)
+
+            return tabulate(df, headers="keys", tablefmt="github", showindex=False)
+
+        except Exception as exc:  # pylint: disable=broad-except
+            return f"Error reading Excel file: {exc}"
+
+
+def download_file_if_any(base_api_url: str, task_id: str) -> str | None:
+    """
+    Try GET /files/{task_id}.
+    • On HTTP 200 → save to a temp dir and return local path.
+    • On 404 → return None.
+    • On other errors → raise so caller can log / handle.
+    """
+    url = f"{base_api_url}/files/{task_id}"
+    try:
+        resp = requests.get(url, timeout=30)
+        if resp.status_code == 404:
+            return None  # no file
+        resp.raise_for_status()  # raise on 4xx/5xx ≠ 404
+    except requests.exceptions.HTTPError as e:
+        # propagate non-404 errors (403, 500, …)
+        raise e
+
+    # ▸ Save bytes to a named file inside the system temp dir
+    #    Try to keep original extension from Content-Disposition if present.
+    cdisp = resp.headers.get("content-disposition", "")
+    filename = task_id  # default base name
+    if "filename=" in cdisp:
+        m = re.search(r'filename="([^"]+)"', cdisp)
+        if m:
+            filename = m.group(1)  # keep provided name
+
+    tmp_dir = Path(tempfile.gettempdir()) / "gaia_files"
+    tmp_dir.mkdir(exist_ok=True)
+    file_path = tmp_dir / filename
+    with open(file_path, "wb") as f:
+        f.write(resp.content)
+    return str(file_path)
+
+
+class BasicAgent:
+    """Basic Agent for the evaluation task."""
+
+    def __init__(self):
+        self.agent = CodeAgent(
+            model=OpenAIServerModel(model_id="gpt-4o"),
+            tools=[
+                DuckDuckGoSearchTool(),
+                WikipediaSearchTool(),
+                SpeechToTextTool(),
+                ExcelToTextTool(),
+            ],
+            add_base_tools=True,
+            additional_authorized_imports=["pandas", "numpy", "csv", "subprocess"],
+        )
+
+        print("BasicAgent initialized.")
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = self.agent.run(question)
+        print(f"Agent returning 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")
+
+    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
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    try:
+        agent = BasicAgent()
+    except Exception as e:  # pylint: disable=broad-except
+        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.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.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 requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        return f"Error fetching questions: {e}", None
+    except Exception as e:  # pylint: disable=broad-except
+        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")
+
+        # ----------fetch any attached file ----------
+        try:
+            file_path = download_file_if_any(api_url, task_id)
+        except Exception as e:  # pylint: disable=broad-except
+            file_path = None
+            print(f"[file fetch error] {task_id}: {e}")
+
+        # ---------- Build the prompt sent to the agent ----------
+        if file_path:
+            q_for_agent = (
+                f"{question_text}\n\n"
+                f"---\n"
+                f"A file was downloaded for this task and saved locally at:\n"
+                f"{file_path}\n"
+                f"---\n\n"
+            )
+        else:
+            q_for_agent = question_text
+
+        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(q_for_agent)
+            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:  # pylint: disable=broad-except
+            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:  # pylint: disable=broad-except
+        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("# Basic 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.
+        """
+    )
+
+    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
+    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)
+    # 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)