app.py

import os
import gradio as gr
import pandas as pd
from huggingface_hub import InferenceClient
import asyncio
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
from llama_index.core.agent.workflow import AgentWorkflow
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.readers.web import SimpleWebPageReader
import requests
from huggingface_hub import InferenceClient

from llama_index.readers.wikipedia import WikipediaReader
from llama_index.core.agent.workflow import (
    AgentInput,
    AgentOutput,
    ToolCall,
    ToolCallResult,
    AgentStream,
)
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"


# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
class BasicAgent:
    def __init__(self):
        self.llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
        self.vision_llm = HuggingFaceInferenceAPI(model_name="CohereLabs/aya-vision-32b")
        self.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
        self.search_client = DuckDuckGoSearchToolSpec()
        self.wiki_reader = WikipediaReader()
        system_prompt = """
            You are a helpful tool that uses the web to find out answers to specific questions in the manner that a human would.
            Your answers should contain just ONE single word.

            You have access to the following tools:

            1. search_web: This uses DuckDuckGo to search the web. It's useful when you need to find generic info or links to 
            web pages;

            2. search_wiki: Use this when you think searching Wikipedia directly is more useful;

            3. webpage_reader: Use this to extract content from web pages;

            4. describe_images: This tool will return descriptions of all the images on a web page. Use this to describe
            images and figures;

            5. Use multiply_nums, divide_nums, add_nums and subtract_nums for basic math operations.
        """
        self.agent = AgentWorkflow.from_tools_or_functions([self.search_web, self.search_wiki, self.webpage_reader,
                                                            self.describe_images, self.multiply_nums, self.divide_nums,
                                                            self.add_nums, self.subtract_nums],
                                                           llm=self.llm,
                                                           system_prompt=system_prompt)
        print("BasicAgent initialized.")

    async def __call__(self, question: str) -> str:
        handler = self.agent.run(user_msg=question)
        # async for event in handler.stream_events():
        #     if isinstance(event, AgentStream):
        #         print(event.delta, end="", flush=True)
        #     elif isinstance(event, ToolCallResult):
        #         print(event.tool_name)  # the tool name
        #         print(event.tool_kwargs)  # the tool kwargs
        #         print(event.tool_output)  # the tool output
        response = await handler
        return str(response)

    def extract_image_urls(self, page_url):
        try:
            # Send HTTP GET request to the page
            response = requests.get(page_url)
            response.raise_for_status()  # Raise an error for bad status codes

            # Parse HTML content
            soup = BeautifulSoup(response.text, 'html.parser')

            # Find all <img> tags
            img_tags = soup.find_all('img')

            # Extract and resolve image URLs
            img_urls = []
            for img in img_tags:
                src = img.get('src')
                if src:
                    # Make relative URLs absolute
                    full_url = urljoin(page_url, src)
                    img_urls.append(full_url)

            return img_urls

        except requests.RequestException as e:
            print(f"Request failed: {e}")
            return []

    async def describe_images(self, webpage_url: str) -> str:
        """Extracts and describes images from an input webpage url based on a query."""

        image_urls = self.extract_image_urls(webpage_url)
        print("image urls: ", image_urls)
        if len(image_urls) == 0:
            return "Looks like there are no images on this webpage"

        docs = []
        for image_url in image_urls:
            messages = [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": "Describe this image in one sentence."
                        },
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": image_url
                            }
                        }
                    ]
                }
            ]

            # print(messages)

            client = InferenceClient(
                provider="hyperbolic",
                api_key=os.getenv('INFERENCE_KEY'),
            )

            try:
                completion = client.chat.completions.create(
                    model="Qwen/Qwen2.5-VL-7B-Instruct",
                    messages=messages,
                )

                # print(completion.choices[0].message.content)
                docs.append(completion.choices[0].message.content)
            except:
                continue
        return str(docs)

    async def search_wiki(self, query: str) -> str:
        """Useful for browsing Wikipedia to look up specific info."""
        reader = self.wiki_reader
        documents = reader.load_data(pages=[query])
        index = VectorStoreIndex.from_documents(documents, embed_model=self.embed_model)
        search_res = index.as_query_engine(llm=self.llm).query(query)
        return str(search_res)

    async def search_web(self, query: str) -> str:
        """Useful for using the web to answer questions. Keep the query very concise in order to get good results."""
        client = self.search_client
        search_res = client.duckduckgo_full_search(query)
        return str(search_res)

    async def webpage_reader(self, webpage_url: str) -> str:
        """Useful for when you want to read and extract information from a specific webpage."""
        documents = SimpleWebPageReader(html_to_text=True).load_data(
            [webpage_url]
        )
        return str(documents)

    async def multiply_nums(self, a: int, b: int) -> float:
        """Useful for multiplying two numbers"""
        return a * b

    async def divide_nums(self, a: int, b: int) -> float:
        """Useful for dividing two numbers"""
        return a / b

    async def add_nums(self, a: int, b: int) -> int:
        """Useful for adding two numbers"""
        return a + b

    async def subtract_nums(self, a: int, b: int) -> int:
        """Useful for subtracting two numbers"""
        return a - b

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")
        question_text += "One-word answer only."
        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)
            print("Answer: ", submitted_answer)
            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__":
    # agent = BasicAgent()
    # while True:
    #     query = input("Ask a question here: ")
    #     answ = asyncio.run(agent(query))
    #     print(answ)

    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)