Update app.py

app.py

@@ -1,196 +1,292 @@
 import os
-import gradio as gr
+import re
+import time
 import requests
-import inspect
+import gradio as gr
 import pandas as pd
+from groq import Groq
+from duckduckgo_search import DDGS
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+TIMEOUT_PER_QUESTION = 30
+DELAY_BETWEEN_QUESTIONS = 6  # Longer delay to avoid rate limits
+
+# ============================================
+# GROQ CLIENT
+# ============================================
+
+def get_groq_client():
+    api_key = os.environ.get("GROQ_API_KEY")
+    if not api_key:
+        raise ValueError("GROQ_API_KEY not set!")
+    return Groq(api_key=api_key)
+
+# ============================================
+# TOOL FUNCTIONS
+# ============================================
+
+def web_search(query: str, num_results: int = 3) -> str:
+    """Search the web"""
+    try:
+        with DDGS() as ddgs:
+            results = list(ddgs.text(query, max_results=num_results))
+        if not results:
+            return "No results found"
+        output = []
+        for r in results:
+            output.append(f"- {r.get('title', '')}: {r.get('body', '')}")
+        return "\n".join(output)
+    except Exception as e:
+        return f"Search error: {e}"
+
+
+def get_task_file(task_id: str) -> dict:
+    """Get GAIA task file"""
+    try:
+        url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
+        response = requests.get(url, timeout=15)
+        
+        if response.status_code == 404:
+            return {"has_file": False, "content": ""}
+        
+        content_type = response.headers.get('content-type', '').lower()
+        disposition = response.headers.get('content-disposition', '')
+        
+        filename = ""
+        if 'filename=' in disposition:
+            filename = disposition.split('filename=')[-1].strip('"\'')
+        
+        result = {"has_file": True, "filename": filename, "type": content_type}
+        
+        # Text/code files
+        if 'text' in content_type or filename.endswith(('.txt', '.py', '.md', '.csv', '.json')):
+            result["content"] = response.text[:6000]
+            return result
+        
+        # Excel files
+        if 'spreadsheet' in content_type or 'excel' in content_type or filename.endswith(('.xlsx', '.xls')):
+            try:
+                from io import BytesIO
+                df = pd.read_excel(BytesIO(response.content))
+                result["content"] = f"Excel data:\n{df.to_string()}"
+                return result
+            except:
+                result["content"] = "Excel file (cannot parse)"
+                return result
+        
+        # Images - can't process
+        if 'image' in content_type:
+            result["content"] = "[IMAGE FILE - Cannot analyze]"
+            result["is_image"] = True
+            return result
+        
+        result["content"] = f"[Binary file: {content_type}]"
+        return result
+        
+    except Exception as e:
+        return {"has_file": False, "content": ""}
+
+
+def reverse_string(text: str) -> str:
+    return text[::-1]
+
+
+def is_reversed_text(text: str) -> bool:
+    indicators = ['.rewsna', 'eht sa', 'tfel', 'drow eht']
+    return any(ind in text.lower() for ind in indicators)
+
+
+# ============================================
+# AGENT CLASS
+# ============================================
 
-# --- 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
-
-    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)
+        print("Initializing Groq agent...")
+        self.client = get_groq_client()
+        print("✅ Agent ready!")
+    
+    def ask_llm(self, prompt: str) -> str:
+        """Ask Groq - using faster model with better rate limits"""
+        max_retries = 2
+        
+        for attempt in range(max_retries):
+            try:
+                # Use mixtral - good balance of speed and quality
+                response = self.client.chat.completions.create(
+                    model="mixtral-8x7b-32768",  # Better rate limits than llama-70b
+                    messages=[{"role": "user", "content": prompt}],
+                    temperature=0,
+                    max_tokens=150,
+                    timeout=TIMEOUT_PER_QUESTION,
+                )
+                return response.choices[0].message.content.strip()
+            except Exception as e:
+                if "rate" in str(e).lower() or "429" in str(e):
+                    wait = (attempt + 1) * 10
+                    print(f"    ⏳ Rate limited, waiting {wait}s...")
+                    time.sleep(wait)
+                else:
+                    return f"Error: {e}"
+        
+        return "unknown"
+    
+    def clean_answer(self, answer: str) -> str:
+        # Remove prefixes
+        for prefix in ["Answer:", "The answer is:", "Final answer:", "A:", "The answer is", "**"]:
+            if answer.lower().startswith(prefix.lower()):
+                answer = answer[len(prefix):].strip()
+        
+        # Remove quotes and trailing punctuation
+        answer = answer.strip('"\'')
+        if answer.endswith('.') and len(answer.split()) <= 3:
+            answer = answer[:-1]
+        
+        # Remove markdown
+        answer = answer.replace("**", "").strip()
+        
+        return answer
+    
+    def __call__(self, question: str, task_id: str = None) -> str:
+        try:
+            context = ""
+            
+            # Check for reversed text
+            if is_reversed_text(question):
+                question = reverse_string(question)
+                context += f"[Decoded reversed text]\n"
+            
+            # Check for file
+            if task_id:
+                file_info = get_task_file(task_id)
+                if file_info.get("has_file") and file_info.get("content"):
+                    context += f"FILE:\n{file_info['content']}\n\n"
+            
+            # Web search for questions that need it
+            needs_search = any(kw in question.lower() for kw in [
+                "who ", "what ", "when ", "where ", "how many", "how much",
+                "album", "actor", "movie", "wikipedia", "surname", "athlete",
+                "pitcher", "country", "competition", "nominated"
+            ])
+            
+            # Don't search if we have file content
+            if context and "FILE:" in context:
+                needs_search = False
+            
+            if needs_search:
+                search_results = web_search(question[:100], 3)
+                if "No results" not in search_results:
+                    context += f"SEARCH RESULTS:\n{search_results}\n\n"
+            
+            prompt = f"""{context}Question: {question}
+
+Give ONLY the final answer. No explanation. Be precise."""
+
+            answer = self.ask_llm(prompt)
+            return self.clean_answer(answer)
+            
+        except Exception as e:
+            print(f"    Error: {e}")
+            return "unknown"
+
+
+# ============================================
+# MAIN
+# ============================================
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "Please log in first.", None
+
+    username = profile.username
+    space_id = os.getenv("SPACE_ID")
+    
+    print(f"\n{'='*50}")
+    print(f"User: {username}")
+    
+    if not os.environ.get("GROQ_API_KEY"):
+        return "❌ Add GROQ_API_KEY to Space secrets!", None
+    
+    print("✅ GROQ_API_KEY found")
+    print(f"{'='*50}\n")
+
     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 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"❌ Failed to fetch questions: {e}", None
+
+    results = []
+    answers = []
+    start_time = time.time()
+    
+    for i, q in enumerate(questions):
+        task_id = q.get("task_id")
+        question = q.get("question", "")
+        
+        print(f"[{i+1}/{len(questions)}] {question[:60]}...")
+        
         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)
+            print(f"    → {answer[:50]}")
         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)
+            answer = "unknown"
+            print(f"    ✗ {e}")
+        
+        answers.append({"task_id": task_id, "submitted_answer": answer})
+        results.append({"#": i+1, "Question": question[:50]+"...", "Answer": answer[:60]})
+        
+        # Delay between questions
+        if i < len(questions) - 1:
+            time.sleep(DELAY_BETWEEN_QUESTIONS)
 
-    # 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)
+    total_time = time.time() - start_time
+    print(f"\n⏱️ {total_time:.0f}s total")
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # Submit
     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
+        submission = {
+            "username": username,
+            "agent_code": f"https://huggingface.co/spaces/{space_id}/tree/main",
+            "answers": answers
+        }
+        result = requests.post(f"{DEFAULT_API_URL}/submit", json=submission, timeout=60).json()
+        
+        score = result.get('score', 0)
+        correct = result.get('correct_count', 0)
+        total = result.get('total_attempted', 0)
+        
+        status = f"✅ Done in {total_time:.0f}s\n\n🎯 Score: {score}% ({correct}/{total})\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"❌ Submit failed: {e}", pd.DataFrame(results)
+
 
+# ============================================
+# UI
+# ============================================
 
-# --- 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 - Unit 4")
+    gr.Markdown("**Groq + Mixtral 8x7B** (better rate limits)")
 
     gr.LoginButton()
+    run_btn = gr.Button("🚀 Run", variant="primary", size="lg")
+    status = gr.Textbox(label="Status", lines=5)
+    table = gr.DataFrame(label="Results")
 
-    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]
-    )
+    run_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("🎯 GAIA Agent Starting...")
+    print(f"GROQ_API_KEY: {'✅' if os.environ.get('GROQ_API_KEY') else '❌'}")
+    demo.launch()