newfiles_add

README.md

@@ -0,0 +1,15 @@
+---
+title: Template Final Assignment
+emoji: 🕵🏻‍♂️
+colorFrom: indigo
+colorTo: indigo
+sdk: gradio
+sdk_version: 5.25.2
+app_file: app.py
+pinned: false
+hf_oauth: true
+# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
+hf_oauth_expiration_minutes: 480
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

agent.py

@@ -0,0 +1,229 @@
+import os
+import pandas as pd
+from smolagents import (
+    CodeAgent, 
+    LiteLLMModel, 
+    DuckDuckGoSearchTool, 
+    FinalAnswerTool,
+    VisitWebpageTool,
+    WikipediaSearchTool,
+    WebSearchTool,
+    tool,
+    OpenAIServerModel
+)
+from langchain_community.document_loaders import ArxivLoader
+
+import requests
+import yaml
+from dotenv import load_dotenv
+load_dotenv()
+
+
+def fetch_questions():
+    DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+    try:
+        response = requests.get(f"{DEFAULT_API_URL}/questions")
+        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.")
+        return questions_data
+    except Exception as e:
+        print(f"Error fetching questions: {e}")
+        raise e
+    
+def fetch_file(task_id: str, file_name: str):
+    DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+    try:
+        response = requests.get(f"{DEFAULT_API_URL}/files/{task_id}")
+        response.raise_for_status()
+        with open(f"/content/Final_Assignment_Template/data/question_files/{file_name}", "wb") as f:
+            f.write(response.content)
+        file_content = response.content
+        return file_content
+    except Exception as e:
+        print(f"Error fetching file: {e}")
+        raise e
+    
+
+def submit_answers(answers):
+    DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+    request_payload = {
+        "username": "GoReed",
+        "agent_code": "test",
+        "answers": answers
+    }
+    try:
+        response = requests.post(
+            f"{DEFAULT_API_URL}/submit",
+            json=json.dumps(request_payload),
+            headers={"Content-Type": "application/json"}
+        )
+        response.raise_for_status()
+        json_response = response.json()
+        print(f"Response: {json_response}")
+        return json_response
+    except Exception as e:
+        print(f"Error submitting answers: {e}")
+
+@tool
+def arxiv_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return {"arxiv_results": formatted_search_docs}
+
+@tool
+def read_python_file(file_name: str) -> str:
+    """Read a python file and return the content.
+    Args:
+        file_name: The name of the file to read.
+    Returns:
+        The content of the file.
+    """
+    base_path = "/content/Final_Assignment_Template/data/question_files"
+    with open(os.path.join(base_path, file_name), "r") as f:
+        return f.read()
+
+@tool
+def read_excel_file(file_name: str) -> str:
+    """Read an excel file with xlsx extension and return the content.
+    Args:
+        file_name: The name of the file to handle.
+    Returns:
+        The content of the file.
+    """
+    base_path = "/content/Final_Assignment_Template/data/question_files"
+    df = pd.read_excel(os.path.join(base_path, file_name))
+    return df.to_string()
+
+@tool
+def extract_text_from_image(image_path: str) -> str:
+    """
+    Extract text from an image using pytesseract (if available).
+    
+    Args:
+        image_path: Path to the image file
+        
+    Returns:
+        Extracted text or error message
+    """
+    try:
+        # Try to import pytesseract
+        import pytesseract
+        from PIL import Image
+        
+        # Open the image
+        image = Image.open(image_path)
+        
+        # Extract text
+        text = pytesseract.image_to_string(image)
+        print(f"Extracted text from image:\n\n{text}")
+        return f"Extracted text from image:\n\n{text}"
+    except ImportError:
+        return "Error: pytesseract is not installed. Please install it with 'pip install pytesseract' and ensure Tesseract OCR is installed on your system."
+    except Exception as e:
+        return f"Error extracting text from image: {str(e)}"
+
+MODEL_ID = "ollama_chat/qwen2.5-coder:7b"
+API_KEY = "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"
+print(API_KEY, "HEELLLOOoooooo", os.getenv("OPENAI_API_KEY_AG"))
+# model = LiteLLMModel(
+#     model_id=MODEL_ID,
+#     api_base="http://127.0.0.1:11434",
+#     num_ctx=8192,
+# )
+model = OpenAIServerModel(model_id="gpt-4.1-nano", api_key=API_KEY)
+MODEL_ID = "openai/gpt-4.1-nano"
+
+with open("/content/Final_Assignment_Template/system_prompt.yaml", 'r') as stream:
+    prompt_templates = yaml.safe_load(stream)
+
+agent = CodeAgent(
+    model=model,
+    tools=[
+        WebSearchTool(),
+        VisitWebpageTool(),
+        WikipediaSearchTool(),
+        arxiv_search,
+        FinalAnswerTool(),
+        extract_text_from_image,
+        #read_python_file,
+        #read_excel_file
+    ],
+    planning_interval=3,
+    max_steps=10,
+    verbosity_level=-1,
+    additional_authorized_imports=[
+                "pandas",
+                "numpy",
+                "requests",
+                "os",
+                "math",
+                "sympy",
+                "scipy",
+                "markdownify",
+                "unicodedata",
+                "stat",
+                "datetime",
+                "random",
+                "itertools",
+                "statistics",
+                "queue",
+                "time",
+                "collections",
+                "re",
+            ],
+    add_base_tools=True,
+    #prompt_templates=prompt_templates,
+)
+questions = fetch_questions()
+answers = []
+counter = 0
+for index, question in enumerate(questions):
+    # print(f"Question {index + 1}: Question Key: {question.keys()}")
+    # print(
+    #     f"Task ID: {question['task_id']}\n"
+    #     f"Question: {question['question']}\n"
+    #     f"Level: {question['Level']}\n"
+    #     f"File_name: {question['file_name']}"
+    # )
+    # if not question['file_name']:
+    #     continue
+    if question['file_name']:
+        file_content = fetch_file(question['task_id'], question['file_name'])
+        file_path = os.path.join("/content/Final_Assignment_Template/data/question_files", question['file_name'])
+        #print(f"File content: {file_content}")
+        answer = agent.run(
+                f"""You are a general AI assistant.You can use the provided tools and websearch for finding answers. I will ask you a question and provide you with a file_name. Report your thoughts, and finish your answer. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+                question:{question['question']}
+                file_path:{file_path}""",
+        )
+    else:
+        answer = agent.run(
+                f"""You are a general AI assistant.You can use the provided tools and websearch for finding answers. I will ask you a question. Report your thoughts, and finish your answer. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+                Question:{question['question']}""",
+        )
+    print(f"Task ID: {question['task_id']} \nQuestion: {question['question']} \nAnswer: {answer}")
+    print()
+    answers.append(
+        {
+            "task_id": question['task_id'],
+            "submitted_answer": answer
+        }
+    )
+import json
+with open(f"/content/Final_Assignment_Template/data/answers_with_prompt_{MODEL_ID.split('/')[-1]}_with_file_content_handling.json", "w") as f:
+    json.dump(answers, f, indent=2)
+print("Submitting answers...")
+submit_answers(answers)
+print("Answers submitted successfully")

app.py

@@ -0,0 +1,196 @@
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+
+# (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):
+        print("BasicAgent initialized.")
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = "This is a default answer."
+        print(f"Agent returning fixed answer: {fixed_answer}")
+        return fixed_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)

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+requests

system_prompt.yaml

@@ -0,0 +1,6 @@
+"system_prompt": |-
+  You are a helpful assistant tasked with answering questions using a set of tools. 
+  Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+  FINAL ANSWER: [YOUR FINAL ANSWER]. 
+  YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+  Your answer should only start with "FINAL ANSWER: ", then follows with the answer.