Update app.py

app.py

@@ -3,194 +3,212 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+import json
+import re
+from typing import Dict, List, Any, Optional
+import asyncio
+from datetime import datetime
+import tempfile
+import base64
+from io import BytesIO
+from PIL import Image
+import numpy as np
+
+# Additional imports for enhanced capabilities
+try:
+    from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+    import torch
+except ImportError:
+    print("Warning: transformers not available. Install with: pip install transformers torch")
+
+try:
+    from sentence_transformers import SentenceTransformer
+except ImportError:
+    print("Warning: sentence-transformers not available. Install with: pip install sentence-transformers")
+
+try:
+    import wikipediaapi
+except ImportError:
+    print("Warning: wikipedia-api not available. Install with: pip install wikipedia-api")
 
-# (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):
+class EnhancedGAIAAgent:
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Enhanced agent for GAIA benchmark with multi-modal capabilities,
+    web search, RAG, and multiple reasoning strategies.
     """
-    # --- 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:
-        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}")
-    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
+    
+    def __init__(self):
+        print("EnhancedGAIAAgent initializing...")
+        self.setup_models()
+        self.setup_tools()
+        self.knowledge_base = {}
+        print("EnhancedGAIAAgent initialized successfully.")
+    
+    def setup_models(self):
+        """Initialize models for different tasks"""
         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})
+            # Text generation model for reasoning
+            self.text_model = None  # Will lazy load when needed
+            
+            # Embedding model for RAG
+            try:
+                self.embedder = SentenceTransformer('all-MiniLM-L6-v2')
+                print("✅ Embedding model loaded")
+            except:
+                self.embedder = None
+                print("⚠️ Embedding model not available")
+            
+            # Vision model for image analysis
+            try:
+                self.vision_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+                print("✅ Vision model loaded")
+            except:
+                self.vision_model = None
+                print("⚠️ Vision model not available")
+                
         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}")
-    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}."
+            print(f"Model setup error: {e}")
+    
+    def setup_tools(self):
+        """Initialize tools for web search and knowledge retrieval"""
         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(
+            self.wiki = wikipediaapi.Wikipedia(
+                language='en',
+                extract_format=wikipediaapi.ExtractFormat.WIKI,
+                user_agent='GAIA-Agent/1.0'
+            )
+            print("✅ Wikipedia API initialized")
+        except:
+            self.wiki = None
+            print("⚠️ Wikipedia API not available")
+    
+    def web_search(self, query: str, max_results: int = 3) -> List[Dict]:
         """
-        **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.
+        Simulate web search using multiple sources
         """
-    )
-
-    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]
-    )
-
-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)
+        results = []
+        
+        # Wikipedia search
+        if self.wiki:
+            try:
+                page = self.wiki.page(query)
+                if page.exists():
+                    results.append({
+                        'title': page.title,
+                        'content': page.text[:1000],
+                        'source': 'Wikipedia',
+                        'url': page.fullurl
+                    })
+            except:
+                pass
+        
+        # Add more search sources here (DuckDuckGo, etc.)
+        return results[:max_results]
+    
+    def extract_numbers_and_calculations(self, text: str) -> Dict:
+        """Extract numbers and perform calculations from text"""
+        numbers = re.findall(r'-?\d+\.?\d*', text)
+        calculations = {
+            'numbers_found': [float(n) for n in numbers if n],
+            'sum': sum(float(n) for n in numbers if n),
+            'count': len(numbers)
+        }
+        return calculations
+    
+    def analyze_image(self, image_path: str) -> str:
+        """Analyze image content"""
+        if not self.vision_model:
+            return "Image analysis not available"
+        
+        try:
+            image = Image.open(image_path)
+            result = self.vision_model(image)
+            return result[0]['generated_text'] if result else "Could not analyze image"
+        except Exception as e:
+            return f"Image analysis error: {e}"
+    
+    def rag_retrieval(self, query: str, context: str) -> str:
+        """Simple RAG-like retrieval and generation"""
+        if not self.embedder:
+            return context[:500]  # Return truncated context
+        
+        try:
+            # Split context into chunks
+            chunks = [context[i:i+200] for i in range(0, len(context), 200)]
+            
+            # Find most relevant chunk
+            query_embedding = self.embedder.encode([query])
+            chunk_embeddings = self.embedder.encode(chunks)
+            
+            similarities = np.dot(query_embedding, chunk_embeddings.T)[0]
+            best_chunk_idx = np.argmax(similarities)
+            
+            return chunks[best_chunk_idx]
+        except:
+            return context[:500]
+    
+    def mathematical_reasoning(self, question: str) -> str:
+        """Handle mathematical questions"""
+        # Extract mathematical expressions
+        math_patterns = [
+            r'(\d+(?:\.\d+)?)\s*[\+\-\*\/]\s*(\d+(?:\.\d+)?)',
+            r'(\d+)\s*percent|(\d+)%',
+            r'(\d+)\s*degrees?',
+        ]
+        
+        for pattern in math_patterns:
+            matches = re.findall(pattern, question)
+            if matches:
+                # Simple calculation handling
+                try:
+                    nums = self.extract_numbers_and_calculations(question)
+                    if nums['numbers_found']:
+                        return f"Based on the numbers found: {nums['numbers_found']}, the sum is {nums['sum']}"
+                except:
+                    pass
+        
+        return "Mathematical reasoning applied but no clear calculation found."
+    
+    def factual_qa(self, question: str) -> str:
+        """Handle factual questions using web search"""
+        search_results = self.web_search(question)
+        
+        if not search_results:
+            return "I couldn't find relevant information to answer this question."
+        
+        # Combine search results
+        combined_info = ""
+        for result in search_results:
+            combined_info += f"{result['content']}\n"
+        
+        # Use RAG to get most relevant information
+        relevant_info = self.rag_retrieval(question, combined_info)
+        
+        return f"Based on available information: {relevant_info}"
+    
+    def multi_step_reasoning(self, question: str) -> str:
+        """Handle complex multi-step questions"""
+        steps = []
+        
+        # Step 1: Identify question type
+        question_lower = question.lower()
+        
+        if any(word in question_lower for word in ['calculate', 'compute', 'math', 'number']):
+            steps.append("Identified as mathematical question")
+            result = self.mathematical_reasoning(question)
+        elif any(word in question_lower for word in ['when', 'where', 'who', 'what', 'how']):
+            steps.append("Identified as factual question")
+            result = self.factual_qa(question)
+        else:
+            steps.append("Using general reasoning")
+            result = self.general_reasoning(question)
+        
+        return result
+    
+    def general_reasoning(self, question: str) -> str:
+        """General reasoning for questions that don't fit other categories"""
+        # Try to extract key entities and concepts
+        key