Update agent.

.gitignore

@@ -0,0 +1,16 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# Environments
+.env
+.venv
+env/
+venv/
+
+!data/.gitkeep
+data/*

ac_tools.py

@@ -0,0 +1,38 @@
+from smolagents import Tool
+import time
+import random
+from duckduckgo_search import DDGS
+
+
+class DuckDuckGoSearchToolWH(Tool):
+    name = "web_search"
+    description = """Performs a DuckDuckGo web search based on your query (think a Google search) then returns the top search results."""
+    inputs = {"query": {"type": "string", "description": "The search query to perform."}}
+    output_type = "string"
+
+    def __init__(self, max_results=10, **kwargs):
+        super().__init__()
+        self.max_results = max_results
+        self.USER_AGENTS = [
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:122.0) Gecko/20100101 Firefox/122.0",
+            "Mozilla/5.0 (Macintosh; Intel Mac OS X 13_0) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15",
+            "Mozilla/5.0 (Linux; Android 11; Pixel 5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Mobile Safari/537.36",
+            "Mozilla/5.0 (iPhone; CPU iPhone OS 16_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.0 Mobile/15E148 Safari/604.1"
+        ]
+        self.kwargs = kwargs
+        self.kwargs.pop('headers', None)
+
+
+    def forward(self, query: str) -> str:
+        headers = {"User-Agent": random.choice(self.USER_AGENTS)}
+        self.ddgs = DDGS(headers=headers, **self.kwargs)
+        time.sleep(2.0)
+        results = self.ddgs.text(query, max_results=self.max_results)
+        if not results:
+            raise Exception("No results found! Try a less restrictive/shorter query.")
+        postprocessed_results = [
+            f"[{result['title']}]({result['href']})\n{result['body']}"
+            for result in results
+        ]
+        return "## Search Results\n\n" + "\n\n".join(postprocessed_results)

app.py

@@ -1,29 +1,48 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
+from basic_agent import init_agent
+
 # (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):
+
+def fetch_questions():
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/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
+    return None, questions_data
+
+
+def run_and_submit_all(submit: bool, max_questions: int | None, profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
+    message, questions_data = fetch_questions()
     # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
@@ -35,12 +54,11 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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()
+        agent = init_agent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -48,39 +66,23 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     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
+
+    if max_questions > 0:
+        questions_data = questions_data[:max_questions]  # Limit number of questions
 
     # 3. Run your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    for iid, item in enumerate(questions_data):
+        print(f"Running agent on question {iid}")
         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)
+            submitted_answer = agent(item)
             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:
@@ -91,6 +93,11 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
+    if not submit:
+        status_update = f"Processed {len(answers_payload)} questions. Submission skipped (submit checkbox unchecked)."
+        print(status_update)
+        return status_update, 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}'..."
@@ -140,8 +147,35 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         return status_message, results_df
 
 
+def fetch_and_run_single(selected_id, questions_data, profile: gr.OAuthProfile | None):
+    if profile:
+        print(f"User logged in: {profile.username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None, None
+
+    try:
+        index = int(selected_id)
+        question_item = questions_data[index]
+        task_id = question_item.get("task_id")
+        question_text = question_item.get("question")
+        if not task_id or question_text is None:
+            return "Invalid question format received.", None, None
+    except Exception as e:
+        return f"Error selecting question: {e}", None, None
+
+    agent = init_agent()
+    generated_answer = agent(question_item)
+    result_df = pd.DataFrame([{
+        "Task ID": task_id,
+        "Question": question_text,
+        "Generated Answer": generated_answer
+    }])
+    return "Fetched and ran agent on selected question.", result_df, question_item
+
+
 # --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
+with (gr.Blocks() as demo):
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
@@ -160,7 +194,59 @@ with gr.Blocks() as demo:
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    questions_data_state = gr.State()
+    question_ids_state = gr.State()
+
+
+    def show_questions():
+        message, questions_data = fetch_questions()
+        if not questions_data:
+            return pd.DataFrame([{'error': message}]), gr.update(choices=[]), questions_data
+        questions_data.sort(key=lambda item: item['task_id'])
+        for i in range(len(questions_data)):
+            questions_data[i]['ID'] = i
+
+        df = pd.DataFrame(questions_data)
+        return df, gr.update(choices=list(range(len(df)))), questions_data
+
+    q_button = gr.Button("Fetch all questions")
+    q_table = gr.DataFrame(label="All Questions", wrap=True)
+
+
+    question_id_dropdown = gr.Dropdown(label="Select Question ID to Run", choices=[])
+    questions_data_state = gr.State()
+
+    q_button.click(
+        fn=show_questions,
+        inputs=[],
+        outputs=[q_table, question_id_dropdown, questions_data_state]
+    )
+
+
+    # NEW BUTTON for single question run
+    gr.Markdown("## Single test run")
+    gr.Markdown("---")
+    single_run_button = gr.Button("Run Single Question")
+    single_question_json = gr.JSON(label="Raw Question JSON")
+    single_status = gr.Textbox(label="Single Question Status", lines=2, interactive=False)
+    single_result_table = gr.DataFrame(label="Single Question and Answer", wrap=True)
+
+    single_run_button.click(
+        fn=fetch_and_run_single,
+        inputs=[question_id_dropdown, questions_data_state],
+        outputs=[single_status, single_result_table, single_question_json]
+    )
+
+    # All questions for submission run
+    gr.Markdown("## Run and Submit")
+    submit_checkbox = gr.Checkbox(label="Submit Results?", value=False)
+    max_questions_input = gr.Dropdown(
+        label="Maximum Number of Questions to Process",
+        choices=[0, 1, 2, 5, 10, 20],  # 0 to 20
+        value=0
+    )
+
+    run_button = gr.Button("Run Evaluation & Maybe Submit Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     # Removed max_rows=10 from DataFrame constructor
@@ -168,9 +254,12 @@ with gr.Blocks() as demo:
 
     run_button.click(
         fn=run_and_submit_all,
+        inputs=[submit_checkbox, max_questions_input],
         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
@@ -193,4 +282,5 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)
+

basic_agent.py

@@ -0,0 +1,115 @@
+
+from smolagents import Tool, CodeAgent, HfApiModel, OpenAIServerModel
+import dotenv
+from ac_tools import DuckDuckGoSearchToolWH
+import requests
+import os
+from PIL import Image
+from transformers import pipeline
+
+
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+
+def init_agent():
+    dotenv.load_dotenv()
+    model = OpenAIServerModel(model_id="gpt-4o")
+    agent = BasicSmolAgent(model=model)
+    return agent
+
+
+def download_file(task_id: str, filename: str) -> str:
+    """
+    Downloads a file associated with the given task_id and saves it to the specified filename.
+
+    Args:
+        task_id (str): The task identifier used to fetch the file.
+        filename (str): The desired filename to save the file as.
+
+    Returns:
+        str: The absolute path to the saved file.
+    """
+    api_url = DEFAULT_API_URL
+    file_url = f"{api_url}/files/{task_id}"
+    folder = 'data'
+    print(f"📡 Fetching file from: {file_url}")
+    try:
+        response = requests.get(file_url, timeout=15)
+        response.raise_for_status()
+
+        # Save binary content to the given filename
+        fpath = os.path.join(folder, filename)
+        with open(fpath, "wb") as f:
+            f.write(response.content)
+
+        abs_path = os.path.abspath(fpath)
+        print(f"✅ File saved as: {abs_path}")
+        return abs_path
+
+    except requests.exceptions.RequestException as e:
+        error_msg = f"❌ Failed to download file for task {task_id}: {e}"
+        print(error_msg)
+        raise RuntimeError(error_msg)
+
+
+class BasicAgent:
+    def __init__(self):
+        print("BasicAgent initialized.")
+    def __call__(self, question_item: dict) -> str:
+        task_id = question_item.get("task_id")
+        question_text = question_item.get("question")
+        file_name = question_item.get("file_name")
+        print(f"Agent received question (first 50 chars): {question_text[:50]}...")
+        fixed_answer = "This is a default answer."
+        print(f"Agent returning fixed answer: {fixed_answer}")
+        return fixed_answer
+
+
+class BasicSmolAgent:
+    def __init__(self, model=None):
+        print("BasicSmolAgent initialized.")
+        if not model:
+            model = HfApiModel()
+        search_tool = DuckDuckGoSearchToolWH()
+        self.agent = CodeAgent(tools=[search_tool], model=model)
+        self.prompt = ("You are a general AI assistant. I will ask you a question."
+                             " Return only 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."
+                             " make sure you don’t include the text “FINAL ANSWER” in your submission, just reply with the answer and nothing else."
+                            " The question is the following: {}")
+        # Load the Whisper pipeline
+        self.mp3_pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+
+    def __call__(self, question_item: dict) -> str:
+        task_id = question_item.get("task_id")
+        question_text = question_item.get("question")
+        file_name = question_item.get("file_name")
+
+        print(f"Agent received question (first 50 chars): {question_text[:50]}...")
+        prompted_question = self.prompt.format(question_text)
+
+        images = []
+        if file_name:
+            fpath = download_file(task_id, file_name)
+            if fpath.endswith('.png'):
+                image = Image.open(fpath).convert("RGB")
+                images.append(image)
+            if fpath.endswith('xlsx') or fpath.endswith('.py'):
+                data = open(fpath, "rb").read().decode("utf-8", errors="ignore")
+                prompted_question += f"\nThere is textual data included with the question, it is from a file {fpath} and is: ```{data}```"
+            if fpath.endswith('.mp3'):
+                try:
+                    result = self.mp3_pipe(fpath)
+                    text = result["text"]
+                    prompted_question += f"\nThere is textual data included with the question, it is from a file {fpath} and is: ```{text}```"
+                except Exception as e:
+                    print("Exception occurred during mp3 transcription: ", e)
+
+        result = self.agent.run(prompted_question, images=images)
+        print(f"Agent returning answer: {result}")
+        return result
+

requirements.txt

@@ -1,2 +1,8 @@
-gradio
-requests
+gradio[oauth]
+requests
+openai
+python-dotenv
+pandas
+duckduckgo_search
+smolagents
+transformers