commit

app.py

@@ -1,330 +1,155 @@
 import os
 import re
-import math
+import time
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 from typing import TypedDict
 from langgraph.graph import StateGraph, START, END
-from langchain_core.messages import HumanMessage
 from langchain_openai import ChatOpenAI
+from langchain_core.messages import SystemMessage, HumanMessage
 
-# (Keep Constants as is)
-# --- Constants ---
+# -------------------------
+# Constants
+# -------------------------
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# -------------------------
 # Utils
-def _clean_answer(text: str) -> str:
+# -------------------------
+def clean_answer(text: str) -> str:
     if not text:
         return ""
     s = text.strip()
-    s = s.replace("Final answer:", "").replace("Answer:", "").strip()
+    s = re.sub(r"^(Final answer:|Answer:)\s*", "", s, flags=re.I)
     s = s.splitlines()[0].strip()
-    s = s.strip('"\'`')
-    if len(s) > 1 and s.endswith("."):
-        s = s[:-1].strip()
+    s = s.strip("\"'`")
+    if s.endswith(".") and len(s) > 1:
+        s = s[:-1]
     return s
 
-
-def try_simple_math(question: str) -> str | None:
-    """
-    매우 보수적인 산수 처리
-    - 질문에 노골적인 수식이 있을 때만 eval
-    """
-    m = re.search(r"([-+/*().\d\s]{3,})", question)
-    if not m:
-        return None
-    expr = m.group(1).strip()
-    if re.fullmatch(r"[0-9+\-*/().\s]+", expr) is None:
-        return None
-    try:
-        val = eval(expr, {"__builtins__": {}}, {})
-        if isinstance(val, (int, float)):
-            if abs(val - round(val)) < 1e-12:
-                return str(int(round(val)))
-            return str(val)
-    except:
-        return None
-    return None
-
-# 1. State 정의
+# -------------------------
+# State
+# -------------------------
 class AgentState(TypedDict):
     question: str
     answer: str
 
-# 2. LLM 초기화
-os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
-
+# -------------------------
+# LLM
+# -------------------------
 llm = ChatOpenAI(
-    model="gpt-4o-mini",  # Space 환경에 맞게 조정 가능
+    model="gpt-4o-mini",
     temperature=0,
-    max_tokens=256
+    max_tokens=128
 )
 
-# 3. Node 정의
-def solve_question(state: AgentState) -> dict:
-    question = state["question"]
-
-    # 0) 초간단 산수 선처리
-    math_ans = try_simple_math(question)
-    if math_ans is not None:
-        return {"answer": math_ans}
+SYSTEM_PROMPT = """
+You are solving GAIA benchmark questions.
 
-    # 1) 1-pass
-    prompt1 = f"""
-You are solving a GAIA benchmark question.
-
-Rules:
-- Think step-by-step internally (do NOT reveal reasoning).
+Rules (VERY IMPORTANT):
+- You MUST reason step by step internally.
+- NEVER show your reasoning.
 - Output ONLY the final answer.
 - No explanation.
 - No formatting.
-- No extra text.
-
-Question:
-{question}
-""".strip()
-
-    r1 = llm.invoke([HumanMessage(content=prompt1)])
-    a1 = _clean_answer(r1.content)
-
-    # 2) 2-pass (검증/수정)
-    if (not a1) or (len(a1) > 80):
-        prompt2 = f"""
-You are verifying a candidate answer for a GAIA question.
-
-Rules:
-- Think internally.
-- Output ONLY the corrected final answer.
-- No explanation.
-- No formatting.
-- No extra text.
+- No extra words.
+"""
 
-Question:
-{question}
+# -------------------------
+# Node
+# -------------------------
+def solve_question(state: AgentState) -> dict:
+    question = state["question"]
 
-Candidate answer:
-{a1}
-""".strip()
+    messages = [
+        SystemMessage(content=SYSTEM_PROMPT),
+        HumanMessage(content=question)
+    ]
 
-        r2 = llm.invoke([HumanMessage(content=prompt2)])
-        a2 = _clean_answer(r2.content)
-        final = a2 if a2 else a1
-    else:
-        final = a1
+    resp = llm.invoke(messages)
+    answer = clean_answer(resp.content)
 
-    return {"answer": final}
+    return {"answer": answer}
 
-# 4. Graph 구성
+# -------------------------
+# Graph
+# -------------------------
 builder = StateGraph(AgentState)
 builder.add_node("solve", solve_question)
-
 builder.add_edge(START, "solve")
 builder.add_edge("solve", END)
+agent_graph = builder.compile()
 
-langgraph_agent = builder.compile()
-
-
-# 6. 기존 BasicAgent를 LangGraph Agent로 교체
-"""
-중요 포인트
-- run_and_submit_all() 함수는 agent(question) 형태를 기대함
-- 따라서 LangGraph Agent를 감싸는 Wrapper 클래스를 유지
-"""
+# -------------------------
+# Wrapper
+# -------------------------
 class BasicAgent:
-    def __init__(self):
-        print("LangGraphAgent initialized.")
-
     def __call__(self, question: str) -> str:
-        """
-        question: GAIA 질문 (string)
-        return: 정답만 포함된 string
-        """
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        result = agent_graph.invoke({"question": question, "answer": ""})
+        return result["answer"]
 
-        result = langgraph_agent.invoke({
-            "question": question,
-            "answer": ""
-        })
+# -------------------------
+# Runner
+# -------------------------
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "Please login first.", None
 
-        final_answer = result["answer"]
-        print(f"Agent returning answer: {final_answer}")
+    username = profile.username
+    questions_url = f"{DEFAULT_API_URL}/questions"
+    submit_url = f"{DEFAULT_API_URL}/submit"
 
-        return final_answer
+    agent = BasicAgent()
 
-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
+    # fetch once
+    questions = requests.get(questions_url).json()
 
-    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
-        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}"})
+    log = []
 
-    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}."
+    for q in questions:
         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
+            ans = agent(q["question"])
+            answers_payload.append({
+                "task_id": q["task_id"],
+                "submitted_answer": ans
+            })
+            log.append({
+                "task_id": q["task_id"],
+                "answer": ans
+            })
+        except Exception as e:
+            log.append({
+                "task_id": q["task_id"],
+                "answer": f"ERROR: {e}"
+            })
+
+    submission = {
+        "username": username,
+        "agent_code": "https://huggingface.co/spaces/ahnhs2k/Agents_Final_Assignment_",
+        "answers": answers_payload
+    }
+
+    res = requests.post(submit_url, json=submission).json()
+
+    status = (
+        f"Score: {res.get('score')}% "
+        f"({res.get('correct_count')}/{res.get('total_attempted')})\n"
+        f"{res.get('message')}"
+    )
 
+    return status, pd.DataFrame(log)
 
-# --- Build Gradio Interface using Blocks ---
+# -------------------------
+# UI
+# -------------------------
 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.Markdown("# GAIA Level-1 Agent")
     gr.LoginButton()
+    btn = gr.Button("Run & Submit")
+    out = gr.Textbox(lines=4)
+    table = gr.DataFrame()
+    btn.click(run_and_submit_all, outputs=[out, table])
 
-    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)
+demo.launch()