Update app.py

app.py

@@ -1,148 +1,221 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-from datetime import datetime
-from transformers import pipeline, Tool
-from transformers.agents import Agent
 
+from smolagents import (
+    ToolCallingAgent, 
+    CodeAgent,
+    DuckDuckGoSearchTool, 
+    InferenceClientModel, 
+    HfApiModel, 
+    OpenAIServerModel
+)
+
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Custom Tools ---
-class CalculatorTool(Tool):
-    name = "calculator"
-    description = "Performs mathematical calculations"
-    inputs = {"expression": {"type": "text"}}
-    outputs = {"result": {"type": "text"}}
-    output_type = "text"  # Added required attribute
-    
-    def __call__(self, expression: str) -> str:
-        try:
-            return str(eval(expression))
-        except:
-            return "Error: Could not evaluate the expression"
-
-class TimeTool(Tool):
-    name = "current_time"
-    description = "Gets current UTC time"
-    inputs = {}
-    outputs = {"time": {"type": "text"}}
-    output_type = "text"  # Added required attribute
-    
-    def __call__(self) -> str:
-        return datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC")
-
-# --- Enhanced Agent ---
-class HFLocalAgent:
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
     def __init__(self):
-        print("Initializing local Hugging Face agent...")
-        self.tools = {
-            "calculator": CalculatorTool(),
-            "time": TimeTool()
-        }
-        
-        # Load local model (small but efficient)
-        self.llm = pipeline(
-            "text-generation",
-            model="HuggingFaceH4/zephyr-7b-beta",
-            device="cpu"  # Change to "cuda" if GPU available
+        self.model = OpenAIServerModel(
+            model_id='o4-mini',
+            api_base="HuggingFaceH4/zephyr-7b-beta",
+            #api_key=os.environ["OPENAI_API_KEY"],
         )
-        
+        self.agent = ToolCallingAgent(
+            tools=[DuckDuckGoSearchTool()], 
+            model=self.model,
+            add_base_tools=True
+        )
+        #self.agent.prompt_templates['system_prompt'] = """
+
+        #You are a general AI assistant. 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.
+
+        #"""
+        print("BasicAgent initialized.")
     def __call__(self, question: str) -> str:
-        print(f"Processing: {question[:100]}...")
-        question_lower = question.lower()
-        
-        # Math questions
-        if any(word in question_lower for word in ["calculate", "what is", "how much is", "+", "-", "*", "/"]):
-            return self.tools["calculator"](question.replace("?", ""))
-        
-        # Time questions
-        if any(word in question_lower for word in ["time", "current time"]):
-            return self.tools["time"]()
-        
-        # Fallback to local LLM
-        try:
-            response = self.llm(
-                f"Answer concisely: {question}",
-                max_new_tokens=100,
-                temperature=0.7
-            )
-            return response[0]['generated_text'].split(":")[-1].strip()
-        except Exception as e:
-            print(f"LLM error: {e}")
-            return "I couldn't process this question."
-
-# --- Evaluation Runner ---
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    if not profile:
-        return "Please login first", None
-    
-    space_id = os.getenv("SPACE_ID", "local-test")
-    api_url = os.getenv("API_URL", DEFAULT_API_URL)
-    
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = self.agent.run(question)
+        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 = HFLocalAgent()
-        response = requests.get(f"{api_url}/questions", timeout=15)
+        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 = response.json()
-        
-        results = []
-        answers = []
-        for q in questions:
-            try:
-                answer = agent(q["question"])
-                answers.append({
-                    "task_id": q["task_id"], 
-                    "submitted_answer": answer
-                })
-                results.append({
-                    "Task ID": q["task_id"], 
-                    "Question": q["question"], 
-                    "Answer": answer
-                })
-            except Exception as e:
-                results.append({
-                    "Task ID": q["task_id"], 
-                    "Question": q["question"], 
-                    "Answer": f"Error: {e}"
-                })
-        
-        submission = {
-            "username": profile.username,
-            "agent_code": f"https://huggingface.co/spaces/{space_id}",
-            "answers": answers
-        }
+        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 i, item in enumerate(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}"})
         
-        response = requests.post(f"{api_url}/submit", json=submission, timeout=60)
+
+    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 = response.json()
-        
-        return (
-            f"Success! Score: {result.get('score', 'N/A')}%\n"
-            f"Correct: {result.get('correct_count', '?')}/{result.get('total_attempted', '?')}",
-            pd.DataFrame(results)
+        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:
-        return f"Evaluation failed: {str(e)}", pd.DataFrame(results if 'results' in locals() else [])
-
-# --- Gradio Interface ---
-with gr.Blocks(title="Local HF Agent Evaluator") as app:
-    gr.Markdown("""
-    ## Local Hugging Face Agent Evaluation
-    Uses completely free/local models - no API keys required
-    """)
-    
+        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_btn = gr.Button("Start Evaluation")
-    output = gr.Textbox(label="Results")
-    results = gr.DataFrame(label="Details")
-    
-    run_btn.click(
+
+    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=[output, results]
+        outputs=[status_output, results_table]
     )
 
 if __name__ == "__main__":
-    app.launch()
+    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)