Update app.py

app.py

@@ -1,196 +1,241 @@
 import os
-import gradio as gr
+import json
 import requests
-import inspect
+import openai
+import traceback
+import gradio as gr
 import pandas as pd
+from typing import Optional
+from dotenv import load_dotenv
 
-# (Keep Constants as is)
-# --- Constants ---
+# ────────────────  Load Environment  ────────────────
+load_dotenv()
+openai.api_key = os.getenv("OPENAI_API_KEY")
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+# ────────────────  Utility: Python Executor  ────────────────
+def python_exec(code: str) -> str:
+    try:
+        safe_globals = {"__builtins__": {}}
+        local_vars = {}
+        exec(code, safe_globals, local_vars)
+        if "result" in local_vars:
+            return str(local_vars["result"])
+        else:
+            return "No variable named 'result' was produced."
+    except Exception:
+        return "Error during Python execution:\n" + traceback.format_exc()
+
+
+# ────────────────  Function Schema  ────────────────
+function_definitions = [
+    {
+        "name": "python_exec",
+        "description": "Execute Python code and return the value of `result` (or printed output).",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "code": {
+                    "type": "string",
+                    "description": "The Python code to execute. Must assign the final answer to a variable named `result`."
+                }
+            },
+            "required": ["code"]
+        }
+    }
+]
+
+
+# ────────────────  Agent Class  ────────────────
 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 not openai.api_key:
+            raise RuntimeError("Please set OPENAI_API_KEY in your .env file")
+        print("✅ BasicAgent initialized with GPT-4o-mini.")
 
+    def __call__(self, question: str) -> str:
+        try:
+            first_resp = openai.chat.completions.create(
+                model="gpt-4o-mini",
+                messages=[
+                    {
+                        "role": "system",
+                        "content": "You are an assistant that can solve math/programming questions by calling python_exec when needed."
+                    },
+                    {"role": "user", "content": question}
+                ],
+                functions=function_definitions,
+                function_call="auto"
+            )
+        except Exception as e:
+            print(f"LLM call failed: {e}")
+            return f"LLM Error: {e}"
+
+        first_msg = first_resp.choices[0].message
+
+        if first_msg.function_call is not None:
+            fn_name = first_msg.function_call.name
+            fn_args_str = first_msg.function_call.arguments
+            try:
+                fn_args = json.loads(fn_args_str)
+            except json.JSONDecodeError:
+                return "Error: could not parse function_call arguments."
+
+            if fn_name == "python_exec":
+                code_to_run = fn_args.get("code", "")
+                python_output = python_exec(code_to_run)
+
+                try:
+                    second_resp = openai.chat.completions.create(
+                        model="gpt-4o-mini",
+                        messages=[
+                            {
+                                "role": "system",
+                                "content": "You are an assistant that can call python_exec when needed."
+                            },
+                            {"role": "user", "content": question},
+                            {
+                                "role": "assistant",
+                                "content": None,
+                                "function_call": {
+                                    "name": "python_exec",
+                                    "arguments": json.dumps({"code": code_to_run})
+                                }
+                            },
+                            {"role": "function", "name": "python_exec", "content": python_output}
+                        ]
+                    )
+                    return second_resp.choices[0].message.content.strip()
+                except Exception as e:
+                    return f"LLM Error: {e}"
+            else:
+                return f"Requested unknown function {fn_name}."
+        else:
+            return first_msg.content.strip()
+
+
+# ────────────────  API Helpers  ────────────────
+def get_all_questions(api_url: str) -> list[dict]:
+    resp = requests.get(f"{api_url}/questions", timeout=15)
+    resp.raise_for_status()
+    return resp.json()
+
+def submit_answers(api_url: str, username: str, code_link: str, answers: list[dict]) -> dict:
+    payload = {
+        "username": username,
+        "agent_code": code_link,
+        "answers": answers
+    }
+    resp = requests.post(f"{api_url}/submit", json=payload, timeout=60)
+    resp.raise_for_status()
+    return resp.json()
+
+
+# ────────────────  Gradio Evaluation Logic  ────────────────
+def run_and_submit_all(profile: Optional[gr.OAuthProfile]):
     if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
+        username = profile.username.strip()
     else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        return "❌ Please log in to Hugging Face using the button above.", None
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    space_id = os.getenv("SPACE_ID", "")
+    code_link = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else ""
 
-    # 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}")
+        return f"❌ Error initializing agent: {e}", None
+
     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 = get_all_questions(DEFAULT_API_URL)
     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"❌ Failed to load questions: {e}", None
 
-    # 3. Run your Agent
-    results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+    results_log = []
     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}")
+        question_text = item.get("question", "")
+        if not task_id or not question_text:
             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}"})
+            submitted_answer = f"AGENT ERROR: {e}"
+        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})
 
     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)
+        return "❌ No answers submitted.", pd.DataFrame(results_log)
 
-    # 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
+        result_data = submit_answers(DEFAULT_API_URL, username, code_link, answers_payload)
     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
+            detail = e.response.json().get("detail", e.response.text)
+        except Exception:
+            detail = e.response.text
+        return f"❌ Submission Failed: HTTP {e.response.status_code}. Detail: {detail}", pd.DataFrame(results_log)
     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
+        return f"❌ Submission Error: {e}", pd.DataFrame(results_log)
+
+    score = result_data.get("score", "N/A")
+    correct_count = result_data.get("correct_count", "?")
+    total = result_data.get("total_attempted", "?")
+    message = result_data.get("message", "")
+
+    final_status = (
+        f"✅ Submission Successful!\n"
+        f"User: {username}\n"
+        f"Score: {score}% ({correct_count}/{total} correct)\n"
+        f"Message: {message}"
+    )
+    return final_status, pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# ────────────────  Gradio UI  ────────────────
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# 🧠 Basic Agent Evaluation")
     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. Copy this Space and define your own agent logic.
+        2. Log in with your Hugging Face account.
+        3. Click “Run Evaluation & Submit All Answers” to test and submit.
 
-        ---
-        **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.
+        - Format matters. Leaderboard uses exact match!
         """
     )
-
     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)
+    status_output = gr.Textbox(label="Status", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Agent Answers", wrap=True)
 
     run_button.click(
         fn=run_and_submit_all,
+        inputs=[gr.State()],
         outputs=[status_output, results_table]
     )
 
+
+# ────────────────  Launch App ────────────────
 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?).")
+    space_host = os.getenv("SPACE_HOST")
+    space_id = os.getenv("SPACE_ID")
 
-    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")
+    if space_host:
+        print(f"✅ SPACE_HOST found: {space_host}")
+        print(f"   Runtime URL: https://{space_host}.hf.space")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        print("ℹ️  SPACE_HOST not found (running locally)")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    if space_id:
+        print(f"✅ SPACE_ID found: {space_id}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id}")
+    else:
+        print("ℹ️  SPACE_ID not found")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, server_name="0.0.0.0", server_port=7860)