app.py

from __future__ import annotations

from functools import lru_cache
from pathlib import Path
from typing import Optional, Union, List
import re
import tempfile
import requests
import urllib.parse as _urlparse
import os
import gradio as gr
import inspect
import pandas as pd

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

import openai

# ‑‑‑ smol‑agents base imports (provided by the framework) ‑‑‑
from smolagents.tools import PipelineTool, Tool
from smolagents import (
    CodeAgent,
    DuckDuckGoSearchTool,
    WikipediaSearchTool,
    OpenAIServerModel,
)

# ---------------------------------------------------------------------------
# Speech‑to‑Text (OpenAI Whisper)
# ---------------------------------------------------------------------------
class SpeechToTextTool(PipelineTool):
    """Transcribe *local* audio files via OpenAI Whisper (cached)."""

    default_checkpoint = "openai/whisper-1"
    name = "transcriber"
    description = (
        "Send a local audio file to OpenAI Whisper (model **whisper‑1**) and "
        "return the plain‑text transcript."
    )
    inputs = {
        "audio": {
            "type": "string",
            "description": "Absolute or relative path to a local audio file.",
        }
    }
    output_type = "string"

    def __call__(self, audio: str) -> str:  # noqa: D401
        return self._transcribe(audio)

    @staticmethod
    @lru_cache(maxsize=64)
    def _transcribe(audio_path: str) -> str:
        path = Path(audio_path).expanduser().resolve()
        if not path.is_file():
            raise FileNotFoundError(f"No such audio file: {path}")

        with path.open("rb") as fp:
            resp = openai.audio.transcriptions.create(
                file=fp,
                model="whisper-1",
                response_format="text",
            )
        return resp


# ---------------------------------------------------------------------------
# Excel → Markdown helper
# ---------------------------------------------------------------------------
class ExcelToTextTool(Tool):
    """Render an Excel worksheet as a Markdown table (GitHub flavour)."""

    name = "excel_to_text"
    description = (
        "Convert an Excel sheet to Markdown. Accepts sheet name *or* index "
        "(as string). Returns a GitHub‑style table without index column."
    )

    inputs = {
        "excel_path": {
            "type": "string",
            "description": "Path to the Excel file (.xlsx / .xls).",
        },
        "sheet_name": {
            "type": "string",
            "nullable": True,
            "description": (
                "Worksheet name or 0‑based index *as string* (optional; "
                "default=first sheet)."
            ),
        },
    }
    output_type = "string"

    @lru_cache(maxsize=32)
    def forward(self, excel_path: str, sheet_name: Optional[str] = None) -> str:  # type: ignore[override]
        path = Path(excel_path).expanduser().resolve()
        if not path.is_file():
            return f"Error: Excel file not found at {path}"

        import importlib.util as _imp
        if not _imp.find_spec("pandas"):
            return "Error: pandas library not available in this environment."
        import pandas as pd

        try:
            sheet: Union[int, str] = 0
            if sheet_name and sheet_name.strip():
                sheet = int(sheet_name) if sheet_name.isdigit() else sheet_name
            df = pd.read_excel(path, sheet_name=sheet)
            if hasattr(pd.DataFrame, "to_markdown"):
                return df.to_markdown(index=False)
            from tabulate import tabulate  # pragma: no cover
            return tabulate(df, headers="keys", tablefmt="github", showindex=False)
        except Exception as exc:  # pragma: no cover – user‑visible error
            return f"Error reading Excel file: {exc}"


# ---------------------------------------------------------------------------
# YouTube Question‑Answer Tool
# ---------------------------------------------------------------------------
class YouTubeQATool(PipelineTool):
    """Answer questions about the spoken content of a YouTube video."""

    default_checkpoint = "openai/gpt-4o"
    name = "youtube_qa"
    description = (
        "Given a YouTube URL and a natural‑language *question*, return an answer "
        "based solely on the video transcript (no hallucinations)."
    )

    inputs = {
        "url": {
            "type": "string",
            "description": "Full YouTube video URL or just the watch ID.",
        },
        "question": {
            "type": "string",
            "description": "Question about the video content (English / French).",
        },
    }
    output_type = "string"

    _TRANSCRIPT_CACHE: dict[str, str] = {}

    @staticmethod
    def _extract_video_id(url: str) -> str:
        if len(url) == 11 and "/" not in url:
            return url
        parsed = _urlparse.urlparse(url)
        if parsed.hostname in ("youtu.be",):
            return parsed.path.lstrip("/")
        if parsed.hostname and "youtube" in parsed.hostname:
            qs = _urlparse.parse_qs(parsed.query)
            if "v" in qs:
                return qs["v"][0]
            return parsed.path.split("/")[-1]
        raise ValueError("Could not parse YouTube video ID from URL")

    @classmethod
    def _get_transcript(cls, video_id: str) -> str:
        if video_id in cls._TRANSCRIPT_CACHE:
            return cls._TRANSCRIPT_CACHE[video_id]
        try:
            from youtube_transcript_api import YouTubeTranscriptApi  # type: ignore
        except ModuleNotFoundError:
            return "Error: youtube‑transcript‑api library not installed."
        try:
            segments: List[dict] = YouTubeTranscriptApi.get_transcript(video_id)
        except Exception as exc:
            return f"Error fetching transcript: {exc}"
        text = " ".join(seg["text"] for seg in segments)
        cls._TRANSCRIPT_CACHE[video_id] = text
        return text

    def forward(self, url: str, question: str) -> str:  # type: ignore[override]
        try:
            vid = self._extract_video_id(url)
        except ValueError as e:
            return str(e)

        transcript = self._get_transcript(vid)
        if transcript.startswith("Error"):
            return transcript

        max_chars = 15000
        if len(transcript) > max_chars:
            transcript = transcript[:max_chars] + " …(truncated)…"

        import openai

        system = (
            "You are a meticulous assistant. Answer the user's question about "
            "the provided YouTube transcript. If the transcript lacks the "
            "information, reply 'I don't know based on the transcript.'"
        )
        messages = [
            {"role": "system", "content": system},
            {"role": "user", "content": f"Transcript:\n{transcript}"},
            {"role": "user", "content": f"Question: {question}"},
        ]
        try:
            resp = openai.chat.completions.create(
                model="gpt-4o",
                messages=messages,
                temperature=0.2,
                max_tokens=256,
            )
            return resp.choices[0].message.content.strip()
        except Exception as exc:
            return f"Error generating answer: {exc}"

# ---------------------------------------------------------------------------
# NEW: Extract text from an image (OCR)
# ---------------------------------------------------------------------------
class ExtractTextFromImageTool(Tool):
    """OCR helper using **pytesseract** + **Pillow** (if available)."""

    name = "image_ocr"
    description = "Extract visible text from a local image file via Tesseract OCR."
    inputs = {"image_path": {"type": "string", "description": "Path to an image."}}
    output_type = "string"

    @lru_cache(maxsize=32)
    def forward(self, image_path: str) -> str:  # type: ignore[override]
        path = Path(image_path).expanduser().resolve()
        if not path.is_file():
            return f"Error: no such image file {path}"
        try:
            import pytesseract
            from PIL import Image
        except ModuleNotFoundError:
            return "Error: pytesseract or Pillow not installed."
        try:
            with Image.open(path) as img:
                text = pytesseract.image_to_string(img)
            return text.strip() or "(No text detected)"
        except Exception as exc:
            return f"Error extracting text: {exc}"


# ---------------------------------------------------------------------------
# NEW: Analyze CSV file
# ---------------------------------------------------------------------------
class AnalyzeCSVFileTool(Tool):
    """Quick CSV introspection & basic descriptive stats with pandas."""

    name = "csv_analyzer"
    description = "Load a CSV file and give column info + summary stats."
    inputs = {
        "file_path": {"type": "string", "description": "Path to CSV file."},
        "query": {"type": "string", "description": "User question (unused for now)."},
    }
    output_type = "string"

    @lru_cache(maxsize=16)
    def forward(self, file_path: str, query: str) -> str:  # type: ignore[override]
        path = Path(file_path).expanduser().resolve()
        if not path.is_file():
            return f"Error: no such CSV file {path}"
        try:
            import pandas as pd
        except ModuleNotFoundError:
            return "Error: pandas not installed."
        try:
            df = pd.read_csv(path)
            desc = df.describe(include="all", datetime_is_numeric=True).T
            buf = [f"Loaded CSV with {len(df)} rows × {len(df.columns)} columns", "Columns: " + ", ".join(df.columns), "", "Summary stats:", desc.to_markdown()]
            return "\n".join(buf)
        except Exception as exc:
            return f"Error reading CSV: {exc}"


# ---------------------------------------------------------------------------
# Helper: download attachment (if any)
# ---------------------------------------------------------------------------

def download_file_if_any(base_api_url: str, task_id: str) -> str | None:
    url = f"{base_api_url}/files/{task_id}"
    try:
        resp = requests.get(url, timeout=30)
        if resp.status_code == 404:
            return None
        resp.raise_for_status()
    except requests.HTTPError:
        raise

    filename = task_id
    if cd := resp.headers.get("content-disposition"):
        if match := re.search(r'filename="([^"]+)"', cd):
            filename = match.group(1)

    tmp_dir = Path(tempfile.gettempdir(), "gaia_files")
    tmp_dir.mkdir(exist_ok=True)
    file_path = tmp_dir / filename
    file_path.write_bytes(resp.content)
    return str(file_path)


# ---------------------------------------------------------------------------
# Minimal agent wired with our custom tools
# ---------------------------------------------------------------------------
class BasicAgent:
    _model = OpenAIServerModel(model_id="gpt-4o")
    _tools = [
        DuckDuckGoSearchTool(),
        WikipediaSearchTool(),
        SpeechToTextTool(),
        ExcelToTextTool(),
        YouTubeQATool(),
        AnalyzeCSVFileTool(),
        ExtractTextFromImageTool()
    ]

    def __init__(self) -> None:
        self.agent = CodeAgent(
            model=self._model,
            tools=self._tools,
            add_base_tools=True,
            additional_authorized_imports=["numpy", "pandas", "csv", "subprocess"],
        )
        print("BasicAgent initialized with YouTubeQATool.")

    def __call__(self, question: str) -> str:  # noqa: D401
        print(f"Agent received question (first 80 chars): {question[:80]}…")
        answer = self.agent.run(question)
        print(f"Agent returning answer: {answer}")
        return 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

    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"

    # 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.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("# 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)