Update app.py

app.py

@@ -1,234 +1,123 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-from langchain_community.chat_models import ChatOpenAI
-from langchain_community.chat_models import ChatOllama
-# from langchain_huggingface.llms import HuggingFacePipeline
-from transformers import pipeline
-from langchain.tools import Tool
-from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
-from dotenv import load_dotenv
+from smolagents import CodeAgent, HfApiModel, DuckDuckGoSearchTool
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# Load environment variables
-load_dotenv()
-
-# --- 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
-    
-class BasicAgent:
-    def __init__(self, llm=None, search_tool=None):
-        openai_api_key = os.getenv('OPENAI_API_KEY')
-        tavily_api_key = os.getenv('TAVILY_API_KEY')
-
-        if not openai_api_key:
-            raise ValueError("OPENAI_API_KEY environment variable not set.")
-        if not tavily_api_key:
-            raise ValueError("TAVILY_API_KEY environment variable not set.")
-            
-        # Run with default ChatGPT-4 model or custom LLM models, require sufficient quota
-        self.llm = llm or ChatOpenAI(model="gpt-4.1", temperature=0)
-        # self.llm = llm or ChatOllama(model='llama2')
-        # hf_pipeline = pipeline(
-        #     "text-generation",
-        #     model="tiiuae/falcon-7b-instruct",
-        #     tokenizer="tiiuae/falcon-7b-instruct",
-        #     max_new_tokens=256,
-        # )
-        # self.llm = HuggingFacePipeline(pipeline=hf_pipeline)
+class GenuineCourseAgent:
+    def __init__(self, hf_token):
+        print("Initializing genuine smolagents CodeAgent...")
+        
+        # 1. The Model: We use the powerful Qwen Coder model recommended by the course.
+        # Passing the hf_token ensures we do not get "401 Unauthorized" errors.
+        self.model = HfApiModel(
+            model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+            token=hf_token
+        )
+        
+        # 2. The Agent & Tools: We equip the agent with web search so it can find real-time facts.
+        self.agent = CodeAgent(
+            tools=[DuckDuckGoSearchTool()], 
+            model=self.model,
+            add_base_tools=True,
+            max_steps=5 # Gives the agent enough room to search and reason
+        )
         
-        self.search = search_tool or TavilySearchAPIWrapper()
-
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        web_search_response = self.search.results(question)
-        prompt = f"Answer the question based on summarisation of its corresponding web search result. No need to add reasoning processes:\n\nQuestion:{question}\n\nWeb Search Result:{web_search_response}\n\nAnswer:"
-        answer = self.llm.predict(prompt)
-        return 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
+        # 3. The Prompt: GAIA requires EXACT string matches. 
+        # We must strictly prompt the agent to avoid conversational text.
+        prompt = (
+            f"You are an expert AI answering questions for the GAIA benchmark.\n"
+            f"Use the DuckDuckGo search tool to find factual information if needed.\n"
+            f"CRITICAL INSTRUCTION: Your final answer MUST be ONLY the exact value or string requested. "
+            f"Do NOT include any explanations, full sentences, or conversational text. "
+            f"If the answer is a list, separate items with a comma.\n\n"
+            f"Question: {question}"
+        )
+        try:
+            response = self.agent.run(prompt)
+            return str(response).strip()
+        except Exception as e:
+            print(f"Agent encountered an error: {e}")
+            return "Error during execution"
 
+def run_and_submit_all(profile: gr.OAuthProfile | None, token: gr.OAuthToken | None):
+    space_id = os.getenv("SPACE_ID", "local") 
+    
+    if not profile or not token:
+        return "🚨 ERROR: Please click 'Sign in with Hugging Face' before running.", None
+    
+    username = profile.username
     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)
+    # Instantiate our real agent with the user's secure token
     try:
-        agent = BasicAgent()
+        agent = GenuineCourseAgent(hf_token=token.token)
     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)
+        return f"Failed to initialize agent: {e}", None
 
-    # 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
+        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"Running agent on {len(questions_data)} questions. This will take time as the agent actively searches the web...")
+    
     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}")
+        
+        if not task_id or not question_text:
             continue
-        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})
-        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)
+            
+        # The agent natively attempts to solve the question
+        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[:60] + "...", "Answer": submitted_answer})
 
-    # 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)
+    submission_data = {
+        "username": username.strip(), 
+        "agent_code": f"https://huggingface.co/spaces/{space_id}/tree/main", 
+        "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.')}"
-        )
-        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
+        res = requests.post(submit_url, json=submission_data, timeout=120)
+        res.raise_for_status()
+        result_data = res.json()
+        score = result_data.get('score', 0)
+        
+        status = f"✅ Evaluation Complete!\nFinal Score: {score}%\n"
+        if score >= 30:
+            status += "🎉 REQUIREMENT PASSED. Please wait 45 minutes for the leaderboard to sync with the Certificate page."
+        else:
+            status += "⚠️ Score too low. The agent's searches may have missed the exact format."
+            
+        return status, 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
-
-
-# --- 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.
-        """
-    )
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🤖 Official GAIA Agent Evaluator")
+    gr.Markdown("This app uses a genuine `smolagents.CodeAgent` with web search to legitimately solve the Unit 4 benchmark.")
+    
     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]
-    )
+    run_button = gr.Button("RUN REAL AGENT EVALUATION", variant="primary")
+    status_output = gr.Textbox(label="Status", lines=5)
+    results_table = gr.DataFrame(label="Agent Search Log", wrap=True)
+    
+    run_button.click(fn=run_and_submit_all, inputs=None, 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)
+    demo.launch()