Update app.py

app.py

@@ -1,196 +1,170 @@
 import os
-import gradio as gr
+import time
 import requests
-import inspect
+import gradio as gr
 import pandas as pd
+from huggingface_hub import InferenceClient
 
-# (Keep Constants as is)
-# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-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 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 web_search(query: str) -> str:
+    """Search using DuckDuckGo"""
+    try:
+        from duckduckgo_search import DDGS
+        with DDGS() as ddgs:
+            results = list(ddgs.text(query, max_results=3))
+        if results:
+            return "\n".join([f"- {r['title']}: {r['body']}" for r in results])
+    except:
+        pass
+    return ""
 
-    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)
+class BasicAgent:
+    def __init__(self):
+        print("Initializing agent...")
+        self.client = InferenceClient(
+            model="Qwen/Qwen2.5-72B-Instruct",
+            token=os.environ.get("HF_TOKEN"),
+        )
+        print("✅ Ready")
+    
+    def ask(self, prompt: str) -> str:
+        """Simple LLM call"""
+        try:
+            response = self.client.chat_completion(
+                messages=[{"role": "user", "content": prompt}],
+                max_tokens=50,
+                temperature=0.1,
+            )
+            return response.choices[0].message.content.strip()
+        except Exception as e:
+            print(f"    LLM error: {e}")
+            return ""
+    
+    def __call__(self, question: str, task_id: str = None) -> str:
+        # Handle reversed text
+        if '.rewsna' in question or 'tfel' in question or 'eht fo' in question:
+            question = question[::-1]
+            print(f"    [Reversed → {question[:50]}...]")
+        
+        # Search for context
+        search_results = web_search(question[:100])
+        
+        # Build simple prompt
+        context = f"Search results:\n{search_results}\n\n" if search_results else ""
+        
+        prompt = f"""{context}Question: {question}
+
+Answer with ONLY the final answer. 
+- If it's a number, just the number (e.g., "42")
+- If it's a name, just the name (e.g., "John Smith")
+- If it's a list, comma-separated (e.g., "apple, banana, cherry")
+- Maximum 5 words
+
+Answer:"""
+        
+        answer = self.ask(prompt)
+        
+        # Clean the answer
+        if not answer:
+            return "unknown"
+        
+        # Remove common prefixes
+        for prefix in ["Answer:", "The answer is:", "The answer is", "A:", "Final answer:"]:
+            if answer.lower().startswith(prefix.lower()):
+                answer = answer[len(prefix):].strip()
+        
+        # Remove quotes and periods
+        answer = answer.strip('."\'')
+        
+        # If answer is too long or contains excuses, retry with simpler prompt
+        if len(answer) > 100 or any(x in answer.lower() for x in ["i cannot", "i don't", "unable"]):
+            answer = self.ask(f"In 1-3 words, answer: {question}")
+            answer = answer.strip('."\'')
+        
+        return answer if answer else "unknown"
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "Please log in.", None
+    
+    username = profile.username
+    space_id = os.getenv("SPACE_ID")
+    
+    print(f"\n{'='*40}\nUser: {username}\n{'='*40}")
+    
     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 failed: {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 = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15).json()
+        print(f"📋 {len(questions)} questions\n")
     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
+        return f"❌ {e}", None
+    
+    results = []
+    answers = []
+    start = time.time()
+    
+    for i, q in enumerate(questions):
+        task_id = q.get("task_id")
+        question = q.get("question", "")
+        
+        print(f"[{i+1}] {question[:50]}...")
+        
         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})
+            answer = agent(question, task_id)
         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)
-
-    # 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}")
+            print(f"    Error: {e}")
+            answer = "unknown"
+        
+        print(f"    → {answer}")
+        
+        answers.append({"task_id": task_id, "submitted_answer": answer})
+        results.append({"#": i+1, "Q": question[:40]+"...", "A": answer[:50]})
+        
+        # Small delay to avoid rate limits
+        time.sleep(1)
+    
+    total = time.time() - start
+    print(f"\n⏱️ {total:.0f}s")
+    
     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
-    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
+        result = requests.post(
+            f"{DEFAULT_API_URL}/submit",
+            json={
+                "username": username,
+                "agent_code": f"https://huggingface.co/spaces/{space_id}/tree/main",
+                "answers": answers
+            },
+            timeout=60
+        ).json()
+        
+        score = result.get('score', 0)
+        correct = result.get('correct_count', 0)
+        
+        status = f"✅ Done in {total:.0f}s\n\n🎯 {score}% ({correct}/20)\n\n"
+        status += "🎉 PASSED!" if score >= 30 else f"Need {30-score}% more"
+        
+        return status, pd.DataFrame(results)
     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"❌ {e}", pd.DataFrame(results)
 
 
-# --- 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.Markdown("# 🎯 GAIA Agent - Simple Mode")
+    gr.Markdown("Direct search + LLM (no code execution)")
     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(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    btn = gr.Button("🚀 Run", variant="primary")
+    status = gr.Textbox(label="Status", lines=5)
+    table = gr.DataFrame(label="Results")
+    btn.click(run_and_submit_all, outputs=[status, table])
 
 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)
+    print(f"HF_TOKEN: {'✅' if os.environ.get('HF_TOKEN') else '❌'}")
+    demo.launch()