Update app.py

app.py

@@ -2,147 +2,203 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
+from typing import Dict, List
 
-# -----------------------------
-# Constants
-# -----------------------------
+# custom imports
+from agents import Agent
+from tool import get_tools
+from model import get_model
+
+# (Keep Constants as is)
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MODEL_ID = "gemini/gemini-2.5-flash-preview-04-17"
 
-# -----------------------------
-# AGENT LOGIC
-# -----------------------------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized")
-
-    def __call__(self, question: str) -> str:
-        q = question.lower()
-
-        # Vegetables
-        if "vegetables" in q and "grocery" in q:
-            vegetables = [
-                "bell pepper",
-                "broccoli",
-                "celery",
-                "fresh basil",
-                "green beans",
-                "lettuce",
-                "sweet potatoes",
-                "zucchini"
-            ]
-            return ", ".join(sorted(vegetables))
-
-        # Fruits
-        if "fruits" in q and "grocery" in q:
-            fruits = ["plums", "acorns", "peanuts"]
-            return ", ".join(sorted(fruits))
-
-        # Mercedes Sosa albums
-        if "mercedes sosa" in q and "studio albums" in q:
-            return "3"
-
-        # Bird species in video
-        if "bird species" in q or "number of bird species" in q:
-            return "4"
-
-        # Opposite word
-        if "opposite" in q:
-            if "left" in q:
-                return "right"
-            if "up" in q:
-                return "down"
-            if "hot" in q:
-                return "cold"
-
-        # Simple arithmetic or counts
-        if "sum of" in q:
-            # Example: "sum of 2 and 3"
-            import re
-            numbers = list(map(int, re.findall(r'\d+', q)))
-            return str(sum(numbers))
-
-        # Chess fallback
-        if "chess" in q:
-            return "Qh5"
-
-        # Reverse / pattern questions
-        if "reverse" in q or "backwards" in q:
-            return q[::-1]
-
-        # Default fallback
-        return "I don't know"
-
-# -----------------------------
-# GAIA RUN + SUBMIT
-# -----------------------------
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    if not profile:
-        return "Please login to Hugging Face", None
-
-    username = profile.username
-    space_id = os.getenv("SPACE_ID")
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+# --- Async Question Processing ---
+async def process_question(agent, question: str, task_id: str) -> Dict:
+    """Process a single question and return both answer AND full log entry"""
+    try:
+        answer = agent(question)
+        return {
+            "submission": {"task_id": task_id, "submitted_answer": answer},
+            "log": {"Task ID": task_id, "Question": question, "Submitted Answer": answer}
+        }
+    except Exception as e:
+        error_msg = f"ERROR: {str(e)}"
+        return {
+            "submission": {"task_id": task_id, "submitted_answer": error_msg},
+            "log": {"Task ID": task_id, "Question": question, "Submitted Answer": error_msg}
+        }
+
+async def run_questions_async(agent, questions_data: List[Dict]) -> tuple:
+    """Process questions sequentially instead of in batch"""
+    submissions = []
+    logs = []
+    
+    for q in questions_data:
+        result = await process_question(agent, q["question"], q["task_id"])
+        submissions.append(result["submission"])
+        logs.append(result["log"])
+    
+    return submissions, logs
+
+
+async 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"
 
-    agent = BasicAgent()
+    # 1. Instantiate Agent
+    try:
+        agent = Agent(
+            model=get_model("LiteLLMModel", MODEL_ID),
+            tools=get_tools()
+        )
+    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)
-        questions = response.json()
-    except Exception as e:
+        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.")
+        questions_data = questions_data[:2]
+    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
+    print(f"Running agent on {len(questions_data)} questions...")
+    answers_payload, results_log = await run_questions_async(agent, questions_data)
 
-    answers = []
-    log = []
-
-    for q in questions:
-        answer = agent(q.get("question", ""))
-        answers.append({
-            "task_id": q.get("task_id"),
-            "submitted_answer": answer
-        })
-        log.append({
-            "Task ID": q.get("task_id"),
-            "Question": q.get("question"),
-            "Answer": answer
-        })
-
-    payload = {
-        "username": username,
-        "agent_code": agent_code,
-        "answers": answers
-    }
+    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=payload, timeout=30)
-        result = response.json()
+        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:
-        return f"Submission failed: {e}", pd.DataFrame(log)
-
-    status = (
-        f"✅ Submission Successful!\n"
-        f"User: {result.get('username')}\n"
-        f"Score: {result.get('score')}%\n"
-        f"Correct: {result.get('correct_count')}/{result.get('total_attempted')}\n"
-        f"Message: {result.get('message')}"
-    )
+        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 status, pd.DataFrame(log)
 
-# -----------------------------
-# GRADIO UI
-# -----------------------------
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# 🤖 GAIA Level 1 Agent")
+    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.
+        """
+    )
+
     gr.LoginButton()
 
-    run_btn = gr.Button("Run Evaluation & Submit All Answers")
-    status_out = gr.Textbox(label="Submission Result", lines=5)
-    table_out = gr.Dataframe(label="Questions and Answers")
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    run_btn.click(run_and_submit_all, outputs=[status_out, table_out])
+    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]
+    )
 
-demo.launch()
+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)