Update app.py

app.py

@@ -1,126 +1,47 @@
+""" Basic Agent Evaluation Runner"""
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
-from smolagents import GradioUI, CodeAgent, HfApiModel
-from smolagents import TransformersModel
-import torch
-from transformers import AutoTokenizer
-from smolagents import DuckDuckGoSearchTool
-# Import your custom tools from their modules
-from tools import (
-    WeatherInfoTool, HubStatsTool,
-    CalculatorTool, CalendarTool, EmailTool, FileManagementTool,
-    DatabaseQueryTool, TranslationTool, TextToSpeechTool,
-    SpeechToTextTool, ImageRecognitionTool, NLPTool, APIIntegrationTool
-)
-from retriever import load_guest_dataset
+from langchain_core.messages import HumanMessage
+from agent import build_graph
 
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-HUGGINGFACE_TOKEN = os.getenv("agents_token")
-
-# # Initialize the Hugging Face model with better generation parameters
-# model = TransformersModel(
-#     model_id="allenai/OLMo-2-0425-1B-Instruct",
-#     device="auto",
-#     # Add generation parameters to prevent loops
-#     generation_kwargs={
-#         "max_new_tokens": 512,
-#         "temperature": 0.7,
-#         "do_sample": True,
-#         "pad_token_id": None,  # Will be set automatically
-#         "eos_token_id": None,  # Will be set automatically
-#         "repetition_penalty": 1.1,
-#         "no_repeat_ngram_size": 3,
-#     }
-# )
-model = HfApiModel(
-    model_id="microsoft/DialoGPT-medium",
-    token=HUGGINGFACE_TOKEN
-)
-# Initialize the web search tool
-search_tool = DuckDuckGoSearchTool()
 
-# Initialize the weather tool
-weather_info_tool = WeatherInfoTool()
 
-# Initialize the Hub stats tool
-hub_stats_tool = HubStatsTool()
-
-# Initialize additional tools (only the most essential ones to avoid confusion)
-calculator_tool = CalculatorTool()
-calendar_tool = CalendarTool()
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# Load the guest dataset and initialize the guest info tool
-guest_info_tool = load_guest_dataset()
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 
-# Create AgentChen with essential tools only
-AgentChen = CodeAgent(
-    tools=[
-        search_tool,
-        guest_info_tool,
-        calculator_tool,
-        weather_info_tool,
-        hub_stats_tool,
-    ],
-    model=model,
-    add_base_tools=True,  # Add any additional base tools
-    planning_interval=None,  # Disable planning to reduce complexity
-    max_iterations=3,  # Limit iterations to prevent loops
-)
 
-class AgentChenWrapper:
+class BasicAgent:
+    """A langgraph agent."""
     def __init__(self):
-        self.agent = AgentChen
-        print("AgentChenWrapper initialized.")
-    
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        
-        # Ensure the question is a string
-        if not isinstance(question, str):
-            print(f"Error: Expected a string, got {type(question)}")
-            return "Error: Input must be a string."
-        
-        # Clean and prepare the question
-        question = question.strip()
-        if not question:
-            return "Error: Empty question received."
-        
-        try:
-            # Use the CodeAgent to run the question with a timeout-like approach
-            print("Running agent...")
-            answer = self.agent.run(question)
-            
-            # Ensure we get a string response
-            if answer is None:
-                answer = "No response generated."
-            else:
-                answer = str(answer).strip()
-            
-            # Limit response length to prevent issues
-            if len(answer) > 1000:
-                answer = answer[:1000] + "... [truncated]"
-            
-            print(f"Agent returning answer (first 100 chars): {answer[:100]}...")
-            return answer
-            
-        except Exception as e:
-            error_msg = f"Error in agent execution: {str(e)}"
-            print(error_msg)
-            return error_msg
+        # Wrap the question in a HumanMessage from langchain_core
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages['messages'][-1].content
+        return answer[14:]
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+
+def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the AgentChen on them, submits all answers,
+    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}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -130,13 +51,13 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = AgentChenWrapper()
+        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)
 
@@ -146,57 +67,44 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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("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
+         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 (limit to first 5 questions for testing)
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    
-    # Limit questions for initial testing
-    test_questions = questions_data[:5]  # Only process first 5 questions
-    print(f"Running agent on {len(test_questions)} questions (limited for testing)...")
-    
-    for i, item in enumerate(test_questions):
+    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
-        
-        print(f"Processing question {i+1}/{len(test_questions)}: {task_id}")
-        
         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[:100] + "...", "Submitted Answer": submitted_answer[:200] + "..."})
-            print(f"Successfully processed question {i+1}")
+            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}")
-            error_answer = f"AGENT ERROR: {str(e)}"
-            answers_payload.append({"task_id": task_id, "submitted_answer": error_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text[:100] + "...", "Submitted Answer": error_answer})
+             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
+    # 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)
@@ -207,7 +115,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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"
@@ -218,7 +125,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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:
@@ -226,30 +132,27 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             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")
@@ -261,15 +164,19 @@ with gr.Blocks() as demo:
         3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
         ---
         **Disclaimers:**
-        This version processes only the first 5 questions for testing purposes. Once working properly, you can remove the limit.
+        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.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]
@@ -277,24 +184,24 @@ with gr.Blocks() as demo:
 
 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=True)
+    demo.launch(debug=True, share=False)