Update app.py

app.py

@@ -1,174 +1,207 @@
-# app.py (Final version)
-
+""" Basic Agent Evaluation Runner"""
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
-import base64
-import json
-import operator
-from typing import Annotated, List, TypedDict
-
-from dotenv import load_dotenv
-from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_core.messages import BaseMessage, HumanMessage, AIMessage
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_core.tools import tool
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langgraph.graph import END, StateGraph
-from langgraph.prebuilt import ToolNode
-
-API_BASE_URL = "https://agents-course-unit4-scoring.hf.space"
-
-class GaiaLangGraphAgent:
-    def __init__(self):
-        print("Initializing GaiaLangGraphAgent...")
-        load_dotenv()
-
-        google_api_key = os.getenv("GEMINI_API_KEY")
-        if not google_api_key:
-            raise ValueError("GEMINI_API_KEY secret not found. Please set it in your Hugging Face Space settings.")
-
-        class AgentState(TypedDict):
-            question: str
-            intermediate_steps: Annotated[List[BaseMessage], operator.add]
-        self.AgentState = AgentState
-
-        web_search_tool = TavilySearchResults(
-            tavily_api_key=os.getenv("TAVILY_API_KEY"),
-            search_engine="google",
-            max_results=3,
-            return_direct=True,
-        )
+from langchain_core.messages import HumanMessage
+from agent import build_graph
+
+
 
-        @tool
-        def calculator(expression: str) -> str:
-            """Evaluates a simple mathematical expression."""
-            try:
-                import numexpr
-                return str(numexpr.evaluate(expression).item())
-            except Exception as e: return f"Error: {e}"
-
-        llm_vision = ChatGoogleGenerativeAI(model="gemini-2.5-pro-preview-06-05", google_api_key=google_api_key)
-
-        def get_file_path(file_name: str) -> str:
-            if not os.path.exists("task_files"): os.makedirs("task_files")
-            return os.path.join("task_files", file_name)
-
-        @tool
-        def file_reader(file_name: str) -> str:
-            """Reads a file, downloading if necessary. Handles text and images."""
-            local_path = get_file_path(file_name)
-            if not os.path.exists(local_path):
-                download_url = f"{API_BASE_URL}/files/{file_name}"
-                print(f"Downloading: {download_url}")
-                try:
-                    response = requests.get(download_url); response.raise_for_status()
-                    with open(local_path, "wb") as f: f.write(response.content)
-                except Exception as e: return f"Error downloading {file_name}: {e}"
-            try:
-                if any(file_name.lower().endswith(ext) for ext in ['.png', '.jpg', '.jpeg', '.webp']):
-                    with open(local_path, "rb") as image_file: b64_image = base64.b64encode(image_file.read()).decode('utf-8')
-                    vision_prompt = HumanMessage(content=[
-                        {"type": "text", "text": "Describe this image in detail, focusing on text or identifiable objects."},
-                        {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{b64_image}"}}
-                    ])
-                    return llm_vision.invoke([vision_prompt]).content
-                else:
-                    with open(local_path, 'r', encoding='utf-8') as f: return f.read()
-            except Exception as e: return f"Error processing {file_name}: {e}"
-
-        tools = [web_search_tool, file_reader, calculator]
-
-        llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest", temperature=0, convert_system_message_to_human=True)
-        llm_with_tools = llm.bind_tools(tools)
-
-        planner_prompt = ChatPromptTemplate.from_messages([
-            ("system", """You are a world-class AI assistant.
-            **Principles:** 1. Analyze the question for nuances. 2. Create multi-step plans. 3. Use tools intelligently (search, file read, calculator) or solve logic puzzles directly. 4. Provide exact-match answers.
-            **Execution:** Loop through plan->act cycles until you have the final answer."""),
-            ("human", "{question}\n\n{intermediate_steps}"),
-        ])
-
-        def planner_node(state: AgentState):
-            print("\n---PLANNER---")
-            chain = planner_prompt | llm_with_tools
-            response = chain.invoke(state)
-            print(f"Planner decision: {'Tool call' if response.tool_calls else 'Final Answer'}")
-            return {'intermediate_steps': [response]}
-
-        tool_node = ToolNode(tools)
-
-        def should_continue(state: AgentState):
-            last_message = state['intermediate_steps'][-1]
-            if isinstance(last_message, AIMessage):
-                if len(getattr(last_message, "tool_calls", [])) > 0: return "action"
-            return END
-
-        workflow = StateGraph(AgentState)
-        workflow.add_node("planner", planner_node)
-        workflow.add_node("action", tool_node)
-        workflow.set_entry_point("planner")
-        workflow.add_conditional_edges("planner", should_continue)
-        workflow.add_edge("action", "planner")
-        self.app = workflow.compile()
-        print("GaiaLangGraphAgent initialized successfully.")
+# (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:
+    """A langgraph agent."""
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
-        print(f"\n>>>>>> AGENT EXECUTING FOR QUESTION: {question[:70]}...")
-        initial_state = {"question": question, "intermediate_steps": []}
-        final_state = self.app.invoke(initial_state, config={"recursion_limit": 15})
-        final_answer = final_state["intermediate_steps"][-1].content
-        print(f"<<<<<< AGENT FINISHED. FINAL ANSWER: {final_answer}")
-        return final_answer
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    if not profile: return "Please Login to Hugging Face with the button first.", None
-    space_id = os.getenv("SPACE_ID")
-    if not space_id: return "CRITICAL ERROR: SPACE_ID not found. Run this from a deployed Hugging Face Space.", None
-    username = profile.username
-    print(f"User logged in: {username}")
-    questions_url = f"{API_BASE_URL}/questions"
-    submit_url = f"{API_BASE_URL}/submit"
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # 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):
+    """
+    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 = GaiaLangGraphAgent()
-    except Exception as e: return f"Error initializing agent: {e}", None
+        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=20); response.raise_for_status()
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
         questions_data = response.json()
-    except Exception as e: return f"Error fetching questions: {e}", None
-    results_log, answers_payload = [], []
-    print(f"Running agent on {len(questions_data)} questions. This may take several minutes...")
+        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, question_text = item.get("task_id"), item.get("question")
+        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:
             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}"})
-    submission_data = {"username": username, "agent_code": agent_code, "answers": answers_payload}
-    print(f"Submitting {len(answers_payload)} answers...")
+
+    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()
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response.raise_for_status()
         result_data = response.json()
-        final_status = (f"Submission Successful!\nUser: {result_data.get('username')}\n"
-                        f"Score: {result_data.get('score', 'N/A')}% "
-                        f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)")
-        return final_status, pd.DataFrame(results_log)
-    except Exception as e: return f"Submission Failed: {e}", pd.DataFrame(results_log)
-
+        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("# GAIA - Advanced Agent Runner")
-    gr.Markdown("Log in and click 'Run' to evaluate the agent.")
+    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])
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
 
 if __name__ == "__main__":
-    print("Launching Gradio Interface...")
-    demo.launch()
+    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)