Update app.py

app.py

@@ -1,195 +1,223 @@
 import os
 import gradio as gr
 import requests
-import inspect
+# import inspect
 import pandas as pd
+from typing import Optional
 
 
+from smolagents import CodeAgent, LiteLLMModel, VisitWebpageTool, DuckDuckGoSearchTool
+
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+
+# Define the 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
+        print("Initializing Mistral-Powered Agent...")
+        
+        # --- 1. API KEY CHECK ---
+        mistral_key = os.getenv("MISTRAL_API_KEY")
+        if not mistral_key:
+            # Agar Mistral nahi hai to error mat do, Qwen try karo (Fallback)
+            print("Mistral Key not found. Please set MISTRAL_API_KEY for best results.")
+            # Fallback logic if needed, but for now we raise error to alert user
+            raise ValueError("MISTRAL_API_KEY missing!")
+
+        # --- 2. MODEL SETUP ---
+        model = LiteLLMModel(
+            model_id="mistral/mistral-large-latest",
+            api_key=mistral_key
+        )
+
+        # --- 3. TOOLS ---
+        search_tool = DuckDuckGoSearchTool()
+        visit_tool = VisitWebpageTool()
+
+        # --- 4. CREATE AGENT ---
+        self.agent = CodeAgent(
+            tools=[search_tool, visit_tool],
+            model=model,
+            additional_authorized_imports=[
+                "numpy", "pandas", "math", "datetime", "re", "csv", "json", "random", "itertools"
+            ],
+            max_steps=25,
+            verbosity_level=2,
+            name="Mistral_Gaia_Solver" 
+        )
 
-    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
+    def __call__(self, question: str, file_path: str = None) -> str:
+        # Prompt Logic
+        prompt = f"""
+        Task: {question}
+        
+        INSTRUCTIONS:
+        1. Use Python code to solve this step-by-step.
+        2. If a file is attached, YOU MUST READ IT using Python immediately.
+        3. Output ONLY the final answer value.
+        """
+        
+        if file_path:
+            prompt += f"\n\n ATTACHED FILE: '{file_path}'"
 
+        try:
+            print(f" Agent working on: {question[:30]}...")
+            response = self.agent.run(prompt)
+            
+            # Output Cleaning
+            final_answer = str(response).replace("Final Answer:", "").strip()
+            
+            if final_answer.endswith(".") and len(final_answer) < 20:
+                final_answer = final_answer[:-1]
+                
+            return final_answer
+            
+        except Exception as e:
+            print(f" Error in Agent: {e}")
+            return f"Error: {e}"
+
+# Evaluation
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    1. Fetch questions.
+    2. Download the file (previously missing).
+    3. Run the agent.
+    4. Submit the results.
+    """
+    
+    # --- A. LOGIN CHECK ---
+    if profile is None:
+        return " Please Login to Hugging Face with the button above.", None
+    
+    username = profile.username
+    space_id = os.getenv("SPACE_ID")
+    
+    # URLs
     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)
+    # --- B. INIT 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" Agent Init Error: {e}", None
+
+    agent_code_link = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(f"🔗 Code Link: {agent_code_link}")
+
+    # --- C. FETCH QUESTIONS ---
     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
+        print(" Fetching questions...")
+        questions_data = requests.get(questions_url).json()
     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"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+
+    print(f" Starting processing of {len(questions_data)} questions...")
+
+    # --- D. PROCESSING LOOP ---
     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
+        task_id = item["task_id"]
+        question_text = item["question"]
+        file_name = item.get("file_name") # GAIA tasks often have files
+
+        print(f"\n--- Processing Task {task_id} ---")
+        
+        local_file_path = None
+
+        # 1. DOWNLOAD FILE (CRITICAL STEP)
+        if file_name:
+            print(f" Downloading file: {file_name}")
+            try:
+                file_url = f"{api_url}/files/{task_id}"
+                file_resp = requests.get(file_url, timeout=10)
+                
+                if file_resp.status_code == 200:
+                    with open(file_name, "wb") as f:
+                        f.write(file_resp.content)
+                    local_file_path = file_name
+                    print(" File downloaded successfully.")
+                else:
+                    print(f" File download failed (Status {file_resp.status_code})")
+            except Exception as e:
+                print(f" File download error: {e}")
+
+        # 2. RUN AGENT
         try:
-            submitted_answer = agent(question_text)
+            # The agent receives the file path as input.
+            submitted_answer = agent(question_text, file_path=local_file_path)
+            
+            print(f" Final Answer: {submitted_answer}")
+            
             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})
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text, 
+                "File": file_name if file_name else "None",
+                "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}"})
+            results_log.append({"Task ID": task_id, "Error": str(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)
+        # 3. CLEANUP (File delete karo)
+        if local_file_path and os.path.exists(local_file_path):
+            os.remove(local_file_path)
 
-    # 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) 
-  
+    # --- E. SUBMIT ---
+    print("Submitting answers to leaderboard...")
+    submission_data = {
+        "username": username,
+        "agent_code": agent_code_link,
+        "answers": answers_payload
+    }
 
-    # 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.')}"
+        res_json = response.json()
+        
+        score = res_json.get('score', 0)
+        correct = res_json.get('correct_count', 0)
+        
+        status_msg = (
+            f"Submission Done!\n"
+            f"User: {username}\n"
+            f"Score: {score}%\n"
+            f"Correct: {correct}"
         )
-        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
+        return status_msg, 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 Failed: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- GRADIO UI ---
 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.Markdown("# 🤖 GAIA Agent Solver (Mistral + Files Fix)")
+    gr.Markdown("""
+    **Instruction:**
+    1. Login via Hugging Face button.
+    2. Click 'Run Evaluation'.
+    3. Wait (it takes time to process all questions).
+    """)
+    
     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(
+    
+    run_btn = gr.Button("Run Evaluation & Submit", variant="primary")
+    
+    status_out = gr.Textbox(label="Status")
+    results_df = gr.DataFrame(label="Detailed Logs")
+    
+    run_btn.click(
         fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        outputs=[status_out, results_df]
     )
 
-
 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)
+    # Enabling the queue eliminates timeout issues.
+    demo.queue(default_concurrency_limit=1).launch()