Update app.py

app.py

@@ -1,163 +1,225 @@
 import os
-from dotenv import load_dotenv
-from typing import TypedDict, Annotated
-from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.graph.message import add_messages
-from langchain_core.messages import AnyMessage, HumanMessage, AIMessage, SystemMessage
-from langgraph.prebuilt import ToolNode
-from langgraph.graph import START, StateGraph
-from langgraph.prebuilt import tools_condition
-from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
-from langchain_core.tools import tool
-from langchain_community.document_loaders import WikipediaLoader
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_tavily import TavilySearch
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+from agent import LangGraphAgent
 import json
 
-load_dotenv()
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# ReAct System Prompt
-REACT_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.w
-"""
-
-@tool
-def multiply(a:int, b:int) -> int:
-    """
-    Multiply two numbers
-    """
-    return a * b
-
-@tool
-def add(a:int, b:int) -> int:
-    """
-    Add two numbers
-    """
-    return a + b
-
-@tool
-def subtract(a:int, b:int) -> int:
-    """
-    Subtract two numbers
-    """
-    return a - b
-
-@tool
-def divide(a:int, b:int) -> int:
-    """
-    Divide two numbers
-    """
-    return a / b
-
-@tool
-def wikidata_search(query: str) -> str:
-    """
-    Search for information on Wikipedia and return maximum 2 results.
-    
-    Args:
-        query: The search query.
-    """
-    loader = WikipediaLoader(query=query, load_max_docs=2)
-    docs = loader.load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in docs
-        ])
-    return {"wiki_results": formatted_search_docs}
-
-# Initialize Tavily Search Tool
-tavily_search_tool = TavilySearch(
-    max_results=3,
-    topic="general",
-)
-
-tools = [multiply, add, subtract, divide, wikidata_search, tavily_search_tool]
-
-def build_graph():
-    llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", api_key=os.getenv("GOOGLE_API_KEY"))
-    llm_with_tools = llm.bind_tools(tools)
-
-    def agent_node(state: MessagesState) -> MessagesState:
-        """This is the agent node with ReAct methodology"""
-        messages = state["messages"]
-        
-        # Add system prompt if not already present
-        if not messages or not isinstance(messages[0], SystemMessage):
-            messages = [SystemMessage(content=REACT_SYSTEM_PROMPT)] + messages
-            
-        return {"messages": [llm_with_tools.invoke(messages)]}
-    
-    
-
-    builder = StateGraph(MessagesState)
-    builder.add_node("agent", agent_node)
-    builder.add_node("tools", ToolNode(tools))
-    
-    
-    builder.add_edge(START, "agent")
-    builder.add_conditional_edges("agent", tools_condition)
-    builder.add_edge("tools", "agent")
-
-    return builder.compile()
-
-class LangGraphAgent:
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
     def __init__(self):
-        self.graph = build_graph()
-        print("LangGraphAgent initialized with tools.")
-        
+        print("BasicAgent initialized.")
     def __call__(self, question: str, task_id: str = None) -> dict:
-        """Run the agent on a question and return structured answer with reasoning trace"""
+        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 {
+            "task_id": task_id or "unknown",
+            "model_answer": fixed_answer,
+            "reasoning_trace": "Basic agent with fixed response - no actual reasoning performed"
+        }
+
+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)
+    try:
+        agent = LangGraphAgent()  # Use LangGraphAgent instead of 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
         try:
-            messages = [HumanMessage(content=question)]
-            result = self.graph.invoke({"messages": messages})
-            
-            # Print all messages for debugging
-            for m in result["messages"]:
-                m.pretty_print()
-            
-            # Extract the final answer and build reasoning trace
-            final_answer = result["messages"][-1].content
-            
-            # Build reasoning trace from all messages
-            reasoning_steps = []
-            for i, msg in enumerate(result["messages"]):
-                if isinstance(msg, SystemMessage):
-                    reasoning_steps.append(f"Step {i+1}: System prompt loaded for ReAct methodology")
-                elif isinstance(msg, HumanMessage):
-                    reasoning_steps.append(f"Step {i+1}: Received question: {msg.content}")
-                elif isinstance(msg, AIMessage):
-                    if msg.tool_calls:
-                        for tool_call in msg.tool_calls:
-                            reasoning_steps.append(f"Step {i+1}: Called tool '{tool_call['name']}' with args: {tool_call['args']}")
-                    else:
-                        reasoning_steps.append(f"Step {i+1}: AI reasoning: {msg.content}")
-                else:
-                    reasoning_steps.append(f"Step {i+1}: Tool response: {str(msg.content)[:200]}...")
+            agent_response = agent(question_text, task_id)
             
-            reasoning_trace = " | ".join(reasoning_steps)
-            
-            # Extract the final answer from the AI response
-            model_answer = final_answer
-            if "FINAL ANSWER:" in final_answer:
-                model_answer = final_answer.split("FINAL ANSWER:")[-1].strip()
-            
-            return {
-                "task_id": task_id or "unknown",
-                "model_answer": model_answer,
-                "reasoning_trace": reasoning_trace
-            }
+            # Format the submission answer to include both model_answer and reasoning_trace
+            submission_answer = json.dumps({
+                "model_answer": agent_response["model_answer"],
+                "reasoning_trace": agent_response["reasoning_trace"]
+            })
             
+            answers_payload.append({"task_id": task_id, "submitted_answer": submission_answer})
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text, 
+                "Model Answer": agent_response["model_answer"],
+                "Reasoning Trace": agent_response["reasoning_trace"][:200] + "..." if len(agent_response["reasoning_trace"]) > 200 else agent_response["reasoning_trace"]
+            })
         except Exception as e:
-            return {
-                "task_id": task_id or "unknown",
-                "model_answer": f"Error: {str(e)}",
-                "reasoning_trace": f"Error occurred during processing: {str(e)}"
-            }
+             print(f"Error running agent on task {task_id}: {e}")
+             error_response = {
+                 "model_answer": f"AGENT ERROR: {e}",
+                 "reasoning_trace": f"Error occurred during processing: {e}"
+             }
+             submission_answer = json.dumps(error_response)
+             answers_payload.append({"task_id": task_id, "submitted_answer": submission_answer})
+             results_log.append({
+                 "Task ID": task_id, 
+                 "Question": question_text, 
+                 "Model Answer": error_response["model_answer"],
+                 "Reasoning Trace": error_response["reasoning_trace"]
+             })
+
+    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}."
+        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.
+        """
+    )
+
+    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__":
-    agent = LangGraphAgent()
-    question = ".rewsna eht sa \"tfel\" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI"
-    answer = agent(question)
-
-
-
+    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)