Update app.py

app.py

@@ -1,73 +1,178 @@
 import os
 import gradio as gr
 import requests
+import inspect # Behåll denna, mallen använder den kanske internt
 import pandas as pd
-import subprocess # Needed for runtime pip install
-import sys        # Needed for runtime pip install
 
-# --- START: Force ddgs installation workaround ---
-# This block ensures 'ddgs' (which provides 'duckduckgo_search') is installed
-# early, before smolagents tries to use its DuckDuckGoSearchTool.
-try:
-    # Attempt to import duckduckgo_search to check if it's already available
-    import duckduckgo_search
-    print("duckduckgo_search (via ddgs) is already installed.")
-except ImportError:
-    print("duckduckgo_search not found. Attempting to install ddgs...")
+# Importera din GaiaAgent från den separata agent.py filen
+from agent import GaiaAgent
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# --- Main Evaluation Function ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the GaiaAgent 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:
-        # Use 'ddgs' as it's the updated package name
-        subprocess.check_call([sys.executable, "-m", "pip", "install", "ddgs>=4.0.0"])
-        print("ddgs installed successfully.")
+        # Instantiera din GaiaAgent här istället för BasicAgent
+        agent = GaiaAgent()
     except Exception as e:
-        print(f"Failed to install ddgs: {e}")
-        # Critical error: if ddgs can't be installed, the app can't function.
-        raise RuntimeError(f"CRITICAL: Failed to install ddgs: {e}")
-# --- END: Force ddgs installation workaround ---
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
 
-# Now import the agent, as its dependencies (smolagents, duckduckgo_search) should be ready
-from agent import GaiaAgent
+    # In the case of an app running as a hugging Face space, this link points toward your codebase ( useful for others so please keep it public)
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
 
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+    # 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
+
+    # 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")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        try:
+            # Anropa din GaiaAgent med frågan
+            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}"})
+
+    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)
 
-def run_agent_and_score(task_description: str) -> str:
-    # Initialize the agent within the function, so it's fresh for each run
-    # This also helps if the agent initialization is heavy or stateful
-    gaia_agent = GaiaAgent()
-    
-    # Process the task
-    agent_output = gaia_agent.process_task(task_description)
-    
-    # Send output to the scoring API
+    # 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(
-            f"{DEFAULT_API_URL}/score_agent",
-            json={"task_description": task_description, "agent_response": agent_output}
+        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.')}"
         )
-        response.raise_for_status()  # Raise an HTTPError for bad responses (4xx or 5xx)
-        scoring_result = response.json()
-        score_info = f"Scoring Result:\nTotal Score: {scoring_result.get('total_score')}\nCorrectness Score: {scoring_result.get('correctness_score')}\nExplanation: {scoring_result.get('explanation', 'No explanation provided.')}"
-        return f"Agent Output:\n{agent_output}\n\n---\n\n{score_info}"
+        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:
-        return f"Agent Output:\n{agent_output}\n\n---\n\nError connecting to scoring API: {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"Agent Output:\n{agent_output}\n\n---\n\nAn unexpected error occurred during scoring: {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 Interface setup
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# GAIA Basic Agent Evaluator (Freddolin)")
-    gr.Markdown("Enter a task description for the agent to process. The agent's output will be displayed, followed by its score from the GAIA scoring API.")
-
-    task_input = gr.Textbox(label="Task Description", placeholder="e.g., 'What is the capital of France?'")
-    output_text = gr.Textbox(label="Agent Output & Score", interactive=False)
-
-    run_button = gr.Button("Run Agent & Score")
+    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)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True) # Ensure max_rows is not breaking it
 
     run_button.click(
-        fn=run_agent_and_score,
-        inputs=task_input,
-        outputs=output_text
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
     )
 
-# Launch the Gradio app
-demo.launch(debug=True) # debug=True can provide more info in logs during development
+if __name__ == "__main__":
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID")
+    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(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)