Improved logic in app.py

app.py

@@ -1,231 +1,248 @@
 import os
-import gradio as gr
+import re
+import json
+import time
 import requests
-import inspect
-import pandas as pd
-from smolagents import CodeAgent, HfApiModel, PromptTemplates, OpenAIServerModel
-from tools import search_tool, speech_to_text, python_interpreter
+import gradio as gr
 
-# (Keep Constants as is)
-# --- Constants ---
+# ── Constants ──────────────────────────────────────────────────────────────────
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+PERPLEXITY_API_URL = "https://api.perplexity.ai/chat/completions"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-if os.getenv("ENV") != "production":
-    load_dotenv()
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-# model = HfApiModel()
-model = OpenAIServerModel(model_id="gpt-4.1", api_key=OPENAI_API_KEY)
-system_prompt = "You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."
-
-class BasicAgent:
-    def __init__(self):
-        self.agent = CodeAgent(
-            tools=[search_tool, speech_to_text, python_interpreter],
-            model=model,
-            # max_steps=5,
-            # add_base_tools=True,
-            # prompt_templates=PromptTemplates(system_prompt=system_prompt),
-            additional_authorized_imports=[
-                "os",
-                "io",
-                "pathlib",
-                "json",
-                "csv",
-                "pandas",
-                "openpyxl",
-                "zipfile",
-                "mutagen",
-                "PIL"
-            ]
-        )
-        print("Agent initialized.")
-    def __call__(self, question: str, file_name: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        task = f"{system_prompt} \n{question}"
-        if file_name != "":
-            response = self.agent.run(task=task, additional_args=file_name)
-        elif file_name == "":
-            response = self.agent.run(task)
-        print(f"Agent's answer: {response}")
-        return response
-
-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"
-
-    # 1. Instantiate Agent ( modify this part to create your agent)
+
+# ── Helper Tools ───────────────────────────────────────────────────────────────
+def download_file(task_id: str) -> str:
+    """Download file from GAIA API."""
+    url = f"{DEFAULT_API_URL}/files/{task_id}"
+    try:
+        resp = requests.get(url, timeout=30)
+        resp.raise_for_status()
+        return resp.text[:10000]
+    except Exception as e:
+        return f"[File error: {e}]"
+
+
+# ── Direct Perplexity Call ─────────────────────────────────────────────────────
+def call_perplexity(system_prompt: str, user_message: str, api_key: str) -> str:
+    """Call Perplexity API directly."""
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json",
+    }
+    
+    data = {
+        "model": "sonar-pro",  # Updated model name (sonar-large was deprecated Feb 2025)
+        "messages": [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_message},
+        ],
+        "temperature": 0.2,
+        "max_tokens": 500,
+    }
+    
     try:
-        agent = BasicAgent()
+        resp = requests.post(PERPLEXITY_API_URL, headers=headers, json=data, timeout=60)
+        resp.raise_for_status()
+        result = resp.json()
+        content = result["choices"][0]["message"]["content"]
+        print(f"[DEBUG] Raw Perplexity response: {content[:200]}")  # Debug log
+        return content
+    except requests.HTTPError as e:
+        error_body = e.response.text if hasattr(e.response, 'text') else str(e)
+        print(f"[DEBUG] HTTP Error: {e.response.status_code} - {error_body[:200]}")
+        return f"HTTP_ERROR: {e.response.status_code}"
     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}")
+        print(f"[DEBUG] Exception: {str(e)[:200]}")
+        return f"ERROR: {e}"
+
+
+# ── Answer Cleaner ─────────────────────────────────────────────────────────────
+def clean_answer(raw: str) -> str:
+    """Strip preamble and get bare answer."""
+    original = raw
+    raw = str(raw).strip()
+    
+    # Don't clean error messages - return them as-is for debugging
+    if raw.startswith("ERROR:") or raw.startswith("HTTP_ERROR:"):
+        return raw
+    
+    # Remove common prefixes
+    for prefix in ["FINAL ANSWER:", "Final Answer:", "final answer:", "Answer:", "answer:", 
+                   "The answer is:", "The answer is", "Result:", "**Answer:**", "Based on"]:
+        if raw.lower().startswith(prefix.lower()):
+            raw = raw[len(prefix):].strip()
+            break
+    
+    # Take first line if multi-line and short enough
+    if '\n' in raw:
+        first_line = raw.split('\n')[0].strip()
+        if len(first_line) < 150:
+            raw = first_line
+    
+    # Remove quotes
+    if len(raw) >= 2 and raw[0] in ('"', "'") and raw[0] == raw[-1]:
+        raw = raw[1:-1].strip()
+    
+    # Remove markdown bold
+    raw = re.sub(r'\*\*(.*?)\*\*', r'\1', raw)
+    
+    # DON'T filter out answers - just clean them
+    result = raw.strip()
+    
+    # Debug log the cleaning
+    if result != original:
+        print(f"[DEBUG] Cleaned '{original[:100]}...' → '{result[:100]}'")
+    
+    return result
+
+
+# ── System Prompt ──────────────────────────────────────────────────────────────
+SYSTEM_PROMPT = """Answer the question with ONLY the final answer. No explanation.
+RULES:
+- NO periods at end ("right" NOT "right.")
+- Numbers: digits only ("42")
+- Country names: full name ("Malta" NOT "MLT")
+- Lists: comma-separated
+EXAMPLES:
+Q: "What year was Mona Lisa painted?" → 1503
+Q: "Opposite of left" → right
+"""
+
+
+# ── Main Runner ────────────────────────────────────────────────────────────────
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "❌ Please log in first.", None
+
+    username = profile.username
+    api_key = os.environ.get("PERPLEXITY_API_KEY")
+    
+    if not api_key:
+        return "❌ PERPLEXITY_API_KEY not found in Space secrets!", None
+    
+    # Test the API key first
+    print(f"[DEBUG] API key exists, length: {len(api_key)}, starts with: {api_key[:10]}")
+    
+    space_id = os.environ.get("SPACE_ID", "")
+    agent_code_url = (
+        f"https://huggingface.co/spaces/{space_id}/tree/main"
+        if space_id
+        else f"https://huggingface.co/spaces/{username}/my-gaia-agent/tree/main"
+    )
+
+    log = [f"👤 User: {username}", "📥 Fetching questions..."]
+
+    # 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
+        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+        resp.raise_for_status()
+        questions = resp.json()
+        log.append(f"✅ {len(questions)} questions loaded")
     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 fetch questions: {e}", None
 
-    # 3. Run your Agent
+    log.append(f"🤖 Testing Perplexity API (key: {api_key[:10]}...)")
+    
+    # Test API with simple question first
+    test_answer = call_perplexity("You are helpful.", "What is 2+2?", api_key)
+    log.append(f"🧪 Test call result: {test_answer[:100]}")
+    
+    log.append("─" * 40)
+
+    answers = []
     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
+
+    for i, q in enumerate(questions):
+        task_id = q.get("task_id", "")
+        question_text = q.get("question", "")
+        log.append(f"[{i+1}/20] {question_text[:65]}...")
+
+        # Rate limit
+        if i > 0:
+            time.sleep(4)
+
+        # Check if file mentioned
+        file_content = ""
+        if any(word in question_text.lower() for word in ["file", "image", "attached", "spreadsheet", "document", "excel"]):
+            file_content = download_file(task_id)
+            if not file_content.startswith("[File error"):
+                question_text = f"{question_text}\n\nFile content:\n{file_content[:2000]}"
+
+        # Call Perplexity
+        try:
+            user_prompt = f"Question: {question_text}\n\nAnswer with ONLY the answer, nothing else."
+            raw_answer = call_perplexity(SYSTEM_PROMPT, user_prompt, api_key)
+            final_answer = clean_answer(raw_answer)
+            
+            log.append(f"  📝 Raw: {raw_answer[:80]}")
+            log.append(f"  ✅ Final: {final_answer[:80] if final_answer else '(empty after cleaning)'}")
+        
+        except Exception as e:
+            final_answer = f"EXCEPTION: {str(e)[:80]}"
+            log.append(f"  ❌ Error: {final_answer}")
+
+        answers.append({"task_id": task_id, "submitted_answer": final_answer})
+        results_log.append({
+            "#": i + 1,
+            "Task ID": task_id[:8] + "...",
+            "Question": question_text[:65] + "..." if len(question_text) > 65 else question_text,
+            "Answer": final_answer or "(empty)",
+        })
+
+    answered = sum(1 for a in answers if a["submitted_answer"] and not a["submitted_answer"].startswith("ERROR") and not a["submitted_answer"].startswith("EXCEPTION"))
+    log.append("─" * 40)
+    log.append(f"📊 Answered: {answered}/20")
+
+    # Submit
+    payload = {
+        "username": username,
+        "agent_code": agent_code_url,
+        "answers": answers,
+    }
+
+    for attempt in range(3):
         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})
+            log.append(f"📤 Submitting ({attempt+1}/3)...")
+            sub = requests.post(f"{DEFAULT_API_URL}/submit", json=payload, timeout=60)
+            sub.raise_for_status()
+            data = sub.json()
+            score = data.get("score", "N/A")
+            correct = data.get("correct_count", "?")
+            log += [
+                "─" * 40,
+                "✅ SUBMITTED!",
+                f"📊 Score: {score}%",
+                f"✔️  Correct: {correct}/20",
+                f"🔗 {agent_code_url}",
+                "─" * 40,
+                "🏆 https://huggingface.co/spaces/agents-course/Students_leaderboard",
+            ]
+            break
         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}"})
+            log.append(f"⚠️ Failed: {str(e)[:60]}")
+            if attempt < 2:
+                time.sleep(5)
 
-    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)
+    return "\n".join(log), 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=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:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-
-# --- 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.
-        """
-    )
+# ── Gradio UI ──────────────────────────────────────────────────────────────────
+with gr.Blocks(title="GAIA Agent", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 🤖 HF Agents Course — Unit 4
+    **Perplexity Sonar Large (Direct API with Debug Logging)**
+    1. Log in with Hugging Face
+    2. Click Run & Submit
+    3. Check the logs to see what Perplexity is returning
+    """)
 
     gr.LoginButton()
+    run_btn = gr.Button("🚀 Run Agent & Submit All Answers", variant="primary", size="lg")
+    status_box = gr.Textbox(label="Live Log (with debug info)", lines=25, interactive=False)
+    results_table = gr.DataFrame(label="Results", headers=["#", "Task ID", "Question", "Answer"])
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_btn.click(fn=run_and_submit_all, outputs=[status_box, results_table])
 
-    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]
-    )
+    gr.Markdown("**Debug version** - Shows raw Perplexity responses")
 
-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("��️  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)
+demo.launch()