app.py

import os
import pandas as pd
import requests
import smolagents
from ddgs import DDGS
# from smolagents import DuckDuckGoSearchTool
from smolagents import Tool, CodeAgent, InferenceClientModel, load_tool
from smolagents import WikipediaSearchTool, PythonInterpreterTool, UserInputTool
import gradio as gr
from PIL import Image
from io import BytesIO
import base64
from typing import Any



class DuckDuckGoSearchTool(Tool):
    name = "web_search"
    description = "Performs a DuckDuckGo web search."
    inputs = {'query': {'type': 'string', 'description': 'Search query'}}
    output_type = "string"

    def __init__(self, max_results=10, **kwargs):
        super().__init__()
        self.max_results = max_results
        self.ddgs = DDGS(**kwargs)

    def forward(self, query: str) -> str:
        results = self.ddgs.text(query, max_results=self.max_results)
        if not results:
            return "No results found."
        return "\n\n".join(
            f"[{r['title']}]({r['href']})\n{r['body']}" for r in results
        )
model = InferenceClientModel("qwen/Qwen2.5-0.5B-Instruct",
                            max_tokens=512
                            
)


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

from smolagents.tools import Tool
from transformers import pipeline
from PIL import Image
import torch
from io import BytesIO
from smolagents import Tool

class ImageCaptioningTool(Tool):
    name = "image_captioning"
    description = "Generates a caption for an input image."
    inputs = {
        "image": {"type": "image", "description": "Input image"},
        "question": {"type": "string", "description": "The question related to the image"}
    }
    output_type = "string"

    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        self.captioner = pipeline(
            "image-to-text",
            model="Salesforce/blip-image-captioning-base",
            device=0 if torch.cuda.is_available() else -1
        )

    def forward(self, image, question):
        if not isinstance(image, Image.Image):
            image = Image.open(BytesIO(image))
        result = self.captioner(image)
        return result[0]["generated_text"] if result else "No caption generated"

image_captioner = ImageCaptioningTool(
    name="image_captioning",
    description="Generates a caption for an input image."
)

web_search = DuckDuckGoSearchTool(max_results=5)

tools = [
    image_captioner,
    web_search,
    WikipediaSearchTool(),
    PythonInterpreterTool(),
    UserInputTool(),
]



# ---------------------- MAIN LOGIC ---------------------- #

class BasicAgent:
    def __init__(self, model, tools):
        self.agent = CodeAgent(
            tools = tools,
            model=model
        
        )
        print("BasicAgent initialized.")

    def __call__(self, question):
        print("BasicAgent called")
        if isinstance(question, dict):
            text = question.get("question", "")
            image = question.get("image", None)
        else:
            text = question
            image = None
    
        print(f"Agent received question (first 50 chars): {text[:50]}...")
    
        prompt = system_prompt + "\n\nUser: " + text.strip()
        print("BasicAgent updated the prompt")
        inputs = {}
    
        if image:
            try:
                image_caption = image_captioner(image=image, question=text)
                prompt += f"\n\nThe image contains: {image_caption}"
                print("BasicAgent added the image caption to the prompt")
                inputs["image"] = image
            except Exception as e:
                print(f"Image captioning failed: {e}")

        inputs["question"] = prompt
        print("running the agent with the BasicAgent prompt")
        print(f"Prompt length (chars): {len(prompt)}")
        try:
            # result = self.agent(prompt).strip()
            result = self.agent(inputs).strip()
            print(f"Agent returned result: {result[:100]}")  
            print("Agent run completed")
            return result
        except Exception as e:
            print(f"Error running the agent: {e}")
            return "AGENT RUN ERROR"


        




system_prompt = """
You are a highly capable AI assistant designed to solve real-world, multi-step reasoning tasks in the GAIA benchmark.
Your job is to:
- Search the web or Wikipedia if needed
- Perform Python calculations or date arithmetic
- Automatically search for and describe images if the question mentions or refers to one
Instructions:
1. Think step-by-step and use tools wisely.
2. If the question references an image (e.g. "What’s in this image of..."), search for a relevant image online and generate a caption to assist your reasoning.
3. Use the image caption internally to help answer the question, but do not include it in your response.
4. Always return a single, short, direct answer — no explanation, formatting, or extra information.
Examples:
- Q: What is the capital of France?
- A: Paris
- Q: What date is 30 days after January 1, 2023?
- A: January 31, 2023
- Q: What is 17 times 4?
- A: 68
- Q: What is the tallest building shown in the image of Dubai’s skyline?
- A: Burj Khalifa
- Q: What fruit is in the image of a bowl on the kitchen table?
- A: Bananas
- Q: What is shown in the picture of the moon landing?
- A: Astronaut on the Moon
Your output must be: a single clean answer string only.
"""

# Agent initialization - moved here from the submit_and_run_all()
try:
    agent = BasicAgent(model=model, tools=tools) 
except Exception as e:
    agent = None
    print(f"Error instantiating agent: {e}")
    # return f"Error initializing agent: {e}", None
        
# -----------------------------------------------------
    

def find_image_online(query):
    """Use DuckDuckGo to find an image related to the query."""
    with DDGS() as ddgs:
        results = ddgs.images(query)
        for result in results:
            if result.get("image"):
                return result["image"]
    return None

def download_image(url):
    """Download an image form a URL and return a PIL image."""
    try:
        response = requests.get(url)
        response.raise_for_status()
        return Image.open(BytesIO(response.content))
    except Exception:
        return None

# def ask_agent(question):
#     try:
#         prompt = system_prompt + "\n\nUser: " + question.strip()

#         image = None
#         image_caption = ""
#         # Only try to get an image if the question mentions or implies one
#         keywords = ["image", "picture","photo","painting", "what's in this picture", "describe this picture"]
#         question_lower = question.lower()
#         if any(word in question_lower for word in keywords):
#             image_url = find_image_online(question)
#             if image_url:
#                 image = download_image(image_url)
#                 if image:
#                     # Use the ImageCaptioningTool to get a caption
#                     image_captioner = [tool for tool in tools if tool.name == "image_captioner "][0] 
#                     image_caption = image_captioner(image=image, question=question)
#                     #Append the caption to the user's original question
#                     prompt +=f"\n\nThe image contains: {image_caption}"

#                 #Run the agent (image is passed only if present; prompt always includes the caption if available)
#                 inputs = {"image":image} if image else{}
#                 return agent.run(prompt, inputs=inputs).strip()

#     except Exception as e:
#         return f"Error: {e}"


def ask_agent(question):
    print("ask_agent called")
    try:

        prompt = "\n\nUser: " + question.strip()
        print("ask_agent updated the prompt")
        image = None
        image_caption = ""
        question_input ={}
        keywords = ["image", "picture", "photo", "painting", "what's in this picture", "describe this picture"]
        question_lower = question.lower()

        if any(word in question_lower for word in keywords):
            image_url = find_image_online(question)
            if image_url:
                image = download_image(image_url)
                if image:
                    if image_captioner is None:
                        return "Image captioning tool is missing"

                    try:
                        image_caption = image_captioner(image=image, question=question)
                        prompt += f"\n\nThe image contains: {image_caption}"



                        print("ask_agent updated the prompt to include image caption")
                    except Exception as e:
                        print(f"Image captioning failed: {e}")

        print("running agent with the ask_agent prompt")
        result = agent(prompt)


        try:
            result = agent(prompt)

            if not result or str(result).strip() == "":
                return "I don't know"
            return str(result).strip()

        except Exception as e:
            print(f"ask_agent error during agent call: {e}")
            return "Error: Agent failed to generate a response."

    except Exception as e:
        print(f"ask_agent error: {e}")
        return "Error: Unable to generate response."
  

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)
    # moved to the top of ask_agent() to keep the agent global
    
    # 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")
        image = item.get("image", None)
    
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
    
        try:
            question_input = {"question": question_text}
            if image:
                try:
                    image_bytes = base64.b64decode(image)
                    pil_image = Image.open(BytesIO(image_bytes))
                    question_input["image"] = pil_image
                except Exception as e:
                    print(f"Failed to decode image for task {task_id}: {e}")

            # submitted_answer = agent(question_input)
            submitted_answer = ask_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)