app.py

# app.py
from llama_index.llms.huggingface import HuggingFaceLLM
from llama_index.core.agent import ReActAgent
from llama_index.core.tools import FunctionTool
from transformers import AutoTokenizer
import os
import gradio as gr
import requests
import pandas as pd

from duckduckgo_search import DDGS
from sympy import sympify
from sympy.core.sympify import SympifyError

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- Advanced Agent Definition ---
class SmartAgent:
    def __init__(self):
        print("Initializing Local LLM Agent...")

        # Initialize Zephyr-7B model
        self.llm = HuggingFaceLLM(
            model_name="HuggingFaceH4/zephyr-7b-beta",
            tokenizer_name="HuggingFaceH4/zephyr-7b-beta",
            context_window=2048,
            max_new_tokens=256,
            generate_kwargs={"temperature": 0.7, "do_sample": True},
            device_map="auto"
        )

        # Define tools with real implementations
        self.tools = [
            FunctionTool.from_defaults(
                fn=self.web_search,
                name="web_search",
                description="Searches the web for current information using DuckDuckGo."
            ),
            FunctionTool.from_defaults(
                fn=self.math_calculator,
                name="math_calculator",
                description="Performs symbolic math using SymPy."
            )
        ]

        # Create ReAct agent with tools
        self.agent = ReActAgent.from_tools(
            tools=self.tools,
            llm=self.llm,
            verbose=True
        )
        print("Local LLM Agent initialized successfully.")

    def web_search(self, query: str) -> str:
        """Real web search using DuckDuckGo"""
        print(f"Web search triggered for: {query[:50]}...")
        try:
            with DDGS() as ddgs:
                results = ddgs.text(query, max_results=3)
                if results:
                    return "\n\n".join([f"{r['title']}: {r['href']}" for r in results])
                else:
                    return "No results found."
        except Exception as e:
            print(f"Web search error: {e}")
            return f"Error during web search: {e}"

    def math_calculator(self, expression: str) -> str:
        """Safe math evaluation using SymPy"""
        print(f"Math calculation triggered for: {expression}")
        try:
            result = sympify(expression).evalf()
            return str(result)
        except SympifyError as e:
            return f"Error: Could not parse the expression ({e})"
        except Exception as e:
            return f"Error: Calculation failed ({e})"

    def __call__(self, question: str) -> str:
        print(f"Processing question (first 50 chars): {question[:50]}...")
        try:
            response = self.agent.query(question)
            return str(response)
        except Exception as e:
            print(f"Agent error: {str(e)}")
            return f"Error processing question: {str(e)}"


# --- Original Submission Logic ---
def run_and_submit_all(profile: gr.OAuthProfile | None):
    """
    Fetches all questions, runs the agent on them, submits all answers,
    and displays the results.
    """
    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"

    # Instantiate Agent
    try:
        agent = SmartAgent()
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None

    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 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

    # Run Agent on all questions
    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)

    # 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)

    # 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


# --- Gradio UI ---
with gr.Blocks() as demo:
    gr.Markdown("# Local LLM Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**
        1. Log in to your Hugging Face account
        2. Click 'Run Evaluation & Submit All Answers'
        3. Wait for the local LLM to process all questions
        """
    )

    gr.LoginButton()
    run_button = gr.Button("Run Evaluation & Submit All Answers")
    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, 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]
    )


if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")

    if space_host_startup:
        print(f"✅ SPACE_HOST found: {space_host_startup}")
        print(f"✅ SPACE_ID found: {space_id_startup}")
    else:
        print("❌ SPACE_HOST not found. Please set environment variables.")

    demo.launch()