app.py

import os
from dotenv import load_dotenv
import gradio as gr
import requests

import os
import requests
from typing import List, Dict, Union
import pandas as pd
import wikipediaapi
import PyPDF2
from docx import Document

load_dotenv()

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


# --- Basic Agent Definition ---
class BasicAgent:
    def __init__(self, model="gemini-2.0-flash-lite"):
        self.api_url = f"https://api-inference.huggingface.co/models/{model}"
        self.headers = {"Authorization": f"Bearer {os.getenv('HF_API_KEY')}"}
        # Wikipedia setup (with proper User-Agent)
        self.wiki = wikipediaapi.Wikipedia(
            language='en',
            user_agent='SearchAgent/1.0 ([email protected])'  # CHANGE THIS!
        )
        
        # SearxNG meta-search (replace with your instance)
        self.searx_url = "https://searx.space/search"  # CHANGE THIS!
        print("BasicAgent initialized.")

    def __call__(self, question: str) -> str:
        print(f"Agent received question (first 50 chars): {question[:50]}...")
        fixed_answer = self.generate_response(question)
        print(f"Agent returning answer: {fixed_answer}")
        return fixed_answer


    def generate_response(self, prompt: str) -> str:
        """Get response from HuggingFace model"""
        try:
            response = requests.post(
                self.api_url,
                headers=self.headers,
                json={"inputs": prompt}
            )
            response.raise_for_status()
            return response.json()[0]['generated_text']
        except Exception as e:
            return f"Error generating response: {str(e)}"

    def web_search(self, query: str) -> List[Dict]:
        """Search using SearxNG (meta-search engine)"""
        params = {
            "q": query,
            "format": "json",
            "engines": "google,bing,duckduckgo"
        }
        try:
            response = requests.get(self.searx_url, params=params)
            response.raise_for_status()
            return response.json().get("results", [])
        except requests.RequestException:
            return []

    def wikipedia_search(self, query: str) -> str:
        """Get Wikipedia summary"""
        page = self.wiki.page(query)
        return page.summary if page.exists() else "No Wikipedia page found"

    def process_document(self, file_path: str) -> str:
        """Extract text from PDF, Word, CSV, Excel"""
        if not os.path.exists(file_path):
            return "File not found"
        
        ext = os.path.splitext(file_path)[1].lower()
        
        try:
            if ext == '.pdf':
                with open(file_path, 'rb') as f:
                    reader = PyPDF2.PdfReader(f)
                    return "\n".join([page.extract_text() for page in reader.pages])
            elif ext in ('.doc', '.docx'):
                doc = Document(file_path)
                return "\n".join([para.text for para in doc.paragraphs])
            elif ext == '.csv':
                return pd.read_csv(file_path).to_string()
            elif ext in ('.xls', '.xlsx'):
                return pd.read_excel(file_path).to_string()
            else:
                return "Unsupported file format"
        except Exception as e:
            return f"Error processing document: {str(e)}"

    def __call__(self, query: str) -> str:
        """Handle queries (text, search, or file processing)"""
        print(f"Processing query: {query[:50]}...")
        
        # If it's a file path, process it
        if os.path.exists(query):
            return self.process_document(query)
        
        # If it's a Wikipedia-style query (e.g., "wikipedia:Python")
        if query.lower().startswith("wikipedia:"):
            topic = query.split(":")[1].strip()
            return self.wikipedia_search(topic)
        
        # If it's a web search (e.g., "search:best LLMs 2024")
        if query.lower().startswith("search:"):
            search_query = query.split(":")[1].strip()
            results = self.web_search(search_query)
            return "\n".join([f"{r['title']}: {r['url']}" for r in results])
        
        # Default: Use HuggingFace for text generation
        return self.generate_response(query)

# Example Usage
if __name__ == "__main__":
    agent = BasicAgent()
    
    # Test Wikipedia search
    print(agent("wikipedia:Python"))
    
    # Test web search (requires SearxNG instance)
    # print(agent("search:best programming languages 2024"))
    
    # Test text generation
    print(agent("Explain quantum computing in simple terms"))
    
    # Test file processing (example: PDF)
    # print(agent("/path/to/document.pdf"))
    

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)