Update app.py

app.py

@@ -1,158 +1,44 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-from duckduckgo_search import DDGS
-import re
 
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from smolagents import OpenAIServerModel, DuckDuckGoSearchTool, CodeAgent, WikipediaSearchTool
+
+# (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.ddg_search = DDGS()
-        self.api_url = DEFAULT_API_URL
-        print("BasicAgent initialized with DDGS search.")
-
-    def search_web(self, query: str) -> str:
-        try:
-            results = self.ddg_search.text(keywords=query, max_results=3)
-            if results:
-                return " ".join(result["body"] for result in results)
-            return "No results found."
-        except Exception as e:
-            return f"Search error: {e}"
-
-    def get_file(self, task_id: str) -> str:
-        try:
-            file_url = f"{self.api_url}/files/{task_id}"
-            response = requests.get(file_url, timeout=15)
-            response.raise_for_status()
-            return response.text
-        except requests.exceptions.RequestException as e:
-            print(f"Error fetching file for task {task_id}: {e}")
-            return "Error fetching file."
-
-    def __call__(self, task_id: str, question: str) -> str:
+        self.agent = CodeAgent(
+            model=OpenAIServerModel(model_id="gpt-4o-mini"),
+            tools=[DuckDuckGoSearchTool(), WikipediaSearchTool()],
+            add_base_tools=True,
+        )
+        print("BasicAgent initialized.")
+    def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        try:
-            file_content = self.get_file(task_id)
-            print(f"File content for task {task_id}: {file_content[:100]}...")
-
-            # 1. Mercedes Sosa albums (2000-2009)
-            if task_id == "8e867cd7-cff9-4e6c-867a-ff5ddc2550be":
-                return "5"  # Đã xác định: Misa Criolla, Voz y Sentimiento, Corazón Libre, Cantora 1, Cantora 2
-
-            # 2. Số loài chim trong video
-            if task_id == "a1e91b78-d3d8-4675-bb8d-62741b4b68a6":
-                search_result = self.search_web("highest number of bird species in video L1vXCYZAYYM")
-                numbers = re.findall(r"\b\d+\b", search_result)
-                return numbers[0] if numbers else "2"  # Giả định một số hợp lý
-
-            # 3. Đảo ngược câu
-            if task_id == "2d83110e-a098-4ebb-9987-066c06fa42d0":
-                return "right"
-
-            # 4. Nước đi cờ vua
-            if task_id == "cca530fc-4052-43b2-b130-b30968d8aa44":
-                # Giả định nước đi chiếu tướng cơ bản
-                return "Qe8"  # Một nước đi giả định (cần phân tích bàn cờ thực tế)
-
-            # 5. Người đề cử bài viết Wikipedia
-            if task_id == "4fc2f1ae-8625-45b5-ab34-ad4433bc21f8":
-                return "FunkMonk"  # Dựa trên lịch sử Wikipedia
-
-            # 6. Toán tử không giao hoán
-            if task_id == "6f37996b-2ac7-44b0-8e68-6d28256631b4":
-                # Phân tích bảng: a*b = b, b*a = c (không giao hoán), v.v.
-                return "a, b, c, d, e"
-
-            # 7. Teal'c trong video
-            if task_id == "9d191bce-651d-4746-be2d-7ef8ecadb9c2":
-                return "Indeed"  # Dựa trên Stargate SG-1
-
-            # 8. Bác sĩ thú y
-            if task_id == "cabe07ed-9eca-40ea-8ead-410ef5e83f91":
-                return "Smith"  # Dựa trên tài liệu LibreTexts
+        # fixed_answer = "This is a default answer."
+        fixed_answer = self.agent.run(question)
+        print(f"Agent returning fixed answer: {fixed_answer}")
+        return fixed_answer
 
-            # 9. Rau củ
-            if task_id == "3cef3a44-215e-4aed-8e3b-b1e3f08063b7":
-                return "broccoli, celery, fresh basil, green beans, lettuce, sweet potatoes, zucchini"
 
-            # 10. Nguyên liệu làm bánh
-            if task_id == "99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3":
-                return "lemon juice, ripe strawberries, salt, sugar"  # Giả định
+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
 
-            # 11. Diễn viên trong Magda M.
-            if task_id == "305ac316-eef6-4446-960a-92d80d542f82":
-                search_result = self.search_web("actor who played Ray in Polish Everybody Loves Raymond in Magda M")
-                return "Jacek"  # Giả định dựa trên tìm kiếm
-
-            # 12. Output mã Python
-            if task_id == "f918266a-b3e0-4914-865d-4faa564f1aef":
-                return "42"  # Giả định (cần phân tích mã Python thực tế)
-
-            # 13. Số lần đánh bóng (Yankees 1977)
-            if task_id == "3f57289b-8c60-48be-bd80-01f8099ca449":
-                search_result = self.search_web("Yankee with most walks 1977 regular season at bats")
-                numbers = re.findall(r"\b\d+\b", search_result)
-                return numbers[0] if numbers else "500"  # Giả định
-
-            # 14. Số trang bài tập
-            if task_id == "1f975693-876d-457b-a649-393859e79bf3":
-                return "10, 15, 20"  # Giả định (cần file âm thanh)
-
-            # 15. NASA award number
-            if task_id == "840bfca7-4f7b-481a-8794-c560c340185d":
-                search_result = self.search_web("R. G. Arendt NASA award number Universe Today June 6 2023")
-                return "NNX17AJ88G"  # Dựa trên bài báo
-
-            # 16. Thành phố lưu trữ mẫu vật
-            if task_id == "bda648d7-d618-4883-88f4-3466eabd860e":
-                return "Hanoi"  # Dựa trên bài báo của Nedoshivina
-
-            # 17. Quốc gia ít vận động viên nhất 1928 Olympics
-            if task_id == "cf106601-ab4f-4af9-b045-5295fe67b37d":
-                return "MON"  # Monaco, 2 vận động viên (ít nhất, xếp theo thứ tự alphabet)
-
-            # 18. Pitchers trước và sau Taishō Tamai
-            if task_id == "a0c07678-e491-4bbc-8f0b-07405144218f":
-                return "Suzuki, Tanaka"  # Giả định (cần dữ liệu thực tế)
-
-            # 19. Tổng doanh thu từ thực phẩm
-            if task_id == "7bd855d8-463d-4ed5-93ca-5fe35145f733":
-                return "1500.00"  # Giả định (cần file Excel)
-
-            # 20. Người nhận Malko Competition
-            if task_id == "5a0c1adf-205e-4841-a666-7c3ef95def9d":
-                return "Vladimir"  # Vladimir Verbitsky (USSR, sau 1977)
-
-            # Các câu hỏi khác: Tìm kiếm thông tin chung
-            search_result = self.search_web(question)
-            if file_content != "Error fetching file.":
-                search_result += " " + file_content
-            answer = self.extract_short_answer(search_result)
-            return answer
-
-        except Exception as e:
-            print(f"Error processing question: {e}")
-            return "Error answering question."
-
-    def extract_short_answer(self, text: str) -> str:
-        numbers = re.findall(r"\b\d+\b", text)
-        if numbers:
-            return numbers[0]
-        words = text.split()
-        for word in words:
-            if word[0].isupper() or len(word) < 10:
-                return word
-        return "Unknown"
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")
     if profile:
-        username = f"{profile.username}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -162,35 +48,38 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     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("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
+         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...")
@@ -201,21 +90,23 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(task_id, question_text)
+            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}"})
+             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)
@@ -258,22 +149,20 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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.
-
+        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 separate action or even to answer the questions in async.
+        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.
         """
     )
 
@@ -282,6 +171,7 @@ with gr.Blocks() as demo:
     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(
@@ -291,8 +181,9 @@ with gr.Blocks() as demo:
 
 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")
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -300,7 +191,7 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup:
+    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")