Update app.py

app.py

@@ -1,279 +1,359 @@
-import os
-import pandas as pd
-import requests
-import smolagents
-print("SmolAgents version:", smolagents.__version__)
-from smolagents import Tool, CodeAgent, InferenceClientModel, load_tool
-from smolagents import DuckDuckGoSearchTool, WikipediaSearchTool, PythonInterpreterTool, UserInputTool
 import gradio as gr
-from PIL import Image
+import pandas as pd
+import json
+from smolagents import CodeAgent, InferenceClientModel
+from smolagents.tools import (
+    DuckDuckGoSearchTool,
+    WikipediaSearchTool,
+    PythonInterpreterTool,
+    UserInputTool
+)
 
-# 🧠 Inference model
-model = InferenceClientModel("qwen/Qwen2.5-0.5B-Instruct", max_tokens=512)
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+# -------------------------- MODEL SETUP -------------------------- #
+model = InferenceClientModel(
+    model_id="Qwen/Qwen2-7B-Instruct",  # You can change this to another Hugging Face Inference-compatible model
+    system_message="You are a helpful AI assistant for answering academic questions in a concise and accurate way.",
+    max_tokens=512,
+)
 
-# --- 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
-
-
-# class ImageCaptioningTool(Tool):
-#     name = "image_captioner"
-#     description = "Generate a caption for an image."
-#     inputs = {"image": "image"}
-#     output_type = "text"
-    
-#     def run(self, inputs: dict) -> str:
-#         image = inputs.get("image")
-#         if not image:
-#             return "No image provided."
-#         # You could run your model here instead
-#         return "This is a placeholder caption for the uploaded image."
-        
-class BasicAgent:
-    def __init__(self):
-        model = InferenceClientModel(
-            "qwen/Qwen2.5-0.5B-Instruct",
-            max_tokens=512,
-            system_message="""
-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
-
-Instructions:
-1. Think step-by-step and use tools wisely.
-2. Always return a short, direct answer — no explanation or formatting.
-
-Examples:
-- Q: What is the capital of France?
-- A: Paris
-
-Your output must be: a single clean answer string only.
-
-"""
-        )
-        self.agent = CodeAgent(
-            tools=[
-                    DuckDuckGoSearchTool(max_results=5, rate_limit=2.0),
-                    WikipediaSearchTool(user_agent="my-agent", language="en"),
-                    PythonInterpreterTool(),
-                    UserInputTool(),
-                    # ImageCaptioningTool(),
-            ],
-            model=model
-        
-        )
-        print("BasicAgent initialized.")
-        # print("Available tools:", [tool.name for tool in self.agent.tools])
-    def __call__(self, question):
-        if isinstance(question, dict):
-            text = question.get("question", "")
-            # ignoring image context for now since agent.run doesn't support it
-        else:
-            text = question
-    
-        print(f"Agent received question (first 50 chars): {text[:50]}...")
-        answer = self.agent.run(text)
-        return answer.strip()
+# -------------------------- TOOLS SETUP -------------------------- #
+tools = [
+    DuckDuckGoSearchTool(max_results=5, rate_limit=2.0),
+    WikipediaSearchTool(language="en", user_agent="my-eval-agent"),
+    PythonInterpreterTool(),
+    UserInputTool()
+]
 
-        
-           
-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}")
+# -------------------------- AGENT SETUP -------------------------- #
+agent = CodeAgent(
+    model=model,
+    tools=tools
+)
+
+# -------------------------- EVALUATION FUNCTION -------------------------- #
+def run_agent(file):
     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
+        questions_data = json.load(file)
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
+        return f"Invalid JSON: {e}", pd.DataFrame()
 
-#     question_text = item.get("question")
-# question_input = {"question": question_text}
-# if "image" in item:
-#     question_input["image"] = item["image"]
-# submitted_answer = agent(question_input)
-    # 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:
-                question_input["image"] = {"type": "image", "data": image}
-            submitted_answer = agent(question_input)
-    
-            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})
-    
+            answer = agent.run(question_text)
+            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": 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}"})
+            error_msg = f"AGENT ERROR: {e}"
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg})
 
     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)
+    results_df = pd.DataFrame(results_log)
+    return "Agent run completed!", results_df
 
-    # 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
+# -------------------------- GRADIO UI -------------------------- #
+demo = gr.Interface(
+    fn=run_agent,
+    inputs=gr.File(label="Upload questions.json"),
+    outputs=[
+        gr.Textbox(label="Status"),
+        gr.Dataframe(label="Results", wrap=True),
+    ],
+    title="SmolAgent Question Evaluator",
+    description="Upload a JSON file with `task_id` and `question` fields to evaluate the agent's performance.",
+)
+
+if __name__ == "__main__":
+    demo.launch()
 
 
-# --- 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.
+# import os
+# import pandas as pd
+# import requests
+# import smolagents
+# print("SmolAgents version:", smolagents.__version__)
+# from smolagents import Tool, CodeAgent, InferenceClientModel, load_tool
+# from smolagents import DuckDuckGoSearchTool, WikipediaSearchTool, PythonInterpreterTool, UserInputTool
+# import gradio as gr
+# from PIL import Image
 
-        ---
-        **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.
-        """
-    )
+# # 🧠 Inference model
+# model = InferenceClientModel("qwen/Qwen2.5-0.5B-Instruct", max_tokens=512)
+# # (Keep Constants as is)
+# # --- Constants ---
+# DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-    gr.LoginButton()
+# # --- 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
 
-    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)
+# # class ImageCaptioningTool(Tool):
+# #     name = "image_captioner"
+# #     description = "Generate a caption for an image."
+# #     inputs = {"image": "image"}
+# #     output_type = "text"
+    
+# #     def run(self, inputs: dict) -> str:
+# #         image = inputs.get("image")
+# #         if not image:
+# #             return "No image provided."
+# #         # You could run your model here instead
+# #         return "This is a placeholder caption for the uploaded image."
+        
+# class BasicAgent:
+#     def __init__(self):
+#         model = InferenceClientModel(
+#             "qwen/Qwen2.5-0.5B-Instruct",
+#             max_tokens=512,
+#             system_message="""
+# 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
+
+# Instructions:
+# 1. Think step-by-step and use tools wisely.
+# 2. Always return a short, direct answer — no explanation or formatting.
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+# Examples:
+# - Q: What is the capital of France?
+# - A: Paris
 
-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)
+# Your output must be: a single clean answer string only.
+
+# """
+#         )
+#         self.agent = CodeAgent(
+#             tools=[
+#                     DuckDuckGoSearchTool(max_results=5, rate_limit=2.0),
+#                     WikipediaSearchTool(user_agent="my-agent", language="en"),
+#                     PythonInterpreterTool(),
+#                     UserInputTool(),
+#                     # ImageCaptioningTool(),
+#             ],
+#             model=model
+        
+#         )
+#         print("BasicAgent initialized.")
+#         # print("Available tools:", [tool.name for tool in self.agent.tools])
+#     def __call__(self, question):
+#         if isinstance(question, dict):
+#             text = question.get("question", "")
+#             # ignoring image context for now since agent.run doesn't support it
+#         else:
+#             text = question
+    
+#         print(f"Agent received question (first 50 chars): {text[:50]}...")
+#         answer = self.agent.run(text)
+#         return answer.strip()
+
+        
+           
+# 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
+
+
+# #     question_text = item.get("question")
+# # question_input = {"question": question_text}
+# # if "image" in item:
+# #     question_input["image"] = item["image"]
+# # submitted_answer = agent(question_input)
+#     # 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:
+#                 question_input["image"] = {"type": "image", "data": image}
+#             submitted_answer = agent(question_input)
+    
+#             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)