Update app.py

app.py

@@ -1,4 +1,12 @@
-from langgraph.graph import START, StateGraph, MessagesState
+import os
+import gradio as gr
+import requests
+import pandas as pd
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# ---------- Imports for Advanced Agent ----------
+import re
+from langgraph.graph import StateGraph, MessagesState
 from langgraph.prebuilt import tools_condition, ToolNode
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
@@ -6,35 +14,32 @@ from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
 from langchain_community.tools.tavily_search import TavilySearchResults
 from groq import Groq
-import os
-import re
 
-# Define the tools
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# ---------- Tools ----------
 @tool
 def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query and return up to 2 results."""
     docs = WikipediaLoader(query=query, load_max_docs=2).load()
     return "\n\n".join([doc.page_content for doc in docs])
 
 @tool
 def web_search(query: str) -> str:
-    """Search the web using Tavily."""
     docs = TavilySearchResults(max_results=3).invoke(query)
     return "\n\n".join([doc.page_content for doc in docs])
 
 @tool
 def arvix_search(query: str) -> str:
-    """Search Arxiv and return up to 3 results."""
     docs = ArxivLoader(query=query, load_max_docs=3).load()
     return "\n\n".join([doc.page_content[:1000] for doc in docs])
 
-# Tool-based LangGraph builder
 def build_tool_graph(system_prompt):
     llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     llm_with_tools = llm.bind_tools([wiki_search, web_search, arvix_search])
 
     def assistant(state: MessagesState):
-        return {"messages": [llm_with_tools.invoke(state["messages"]) ]}
+        return {"messages": [llm_with_tools.invoke(state["messages"])]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("assistant", assistant)
@@ -45,6 +50,7 @@ def build_tool_graph(system_prompt):
     builder.add_edge("tools", "assistant")
     return builder.compile()
 
+# --- Advanced BasicAgent Class ---
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
@@ -65,7 +71,8 @@ class BasicAgent:
 
     def format_final_answer(self, answer: str) -> str:
         cleaned = " ".join(answer.split())
-        return f"FINAL ANSWER: {cleaned}"
+        match = re.search(r"FINAL ANSWER:\s*(.*)", cleaned, re.IGNORECASE)
+        return f"FINAL ANSWER: {match.group(1).strip()}" if match else f"FINAL ANSWER: {cleaned}"
 
     def query_groq(self, question: str) -> str:
         full_prompt = f"{self.agent_prompt}\n\nQuestion: {question}"
@@ -150,4 +157,92 @@ class BasicAgent:
                 }
                 opposite = opposites.get(word, f"UNKNOWN_OPPOSITE_OF_{word}")
                 return f"FINAL ANSWER: {opposite.upper()}"
-        return self.format_final_answer("COULD_NOT_SOLVE")
+        return self.format_final_answer("COULD_NOT_SOLVE")
+
+# --- Evaluation Logic ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+    if profile:
+        username = profile.username
+        print(f"User logged in: {username}")
+    else:
+        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"
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        return f"Error initializing agent: {e}", None
+
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+            return "Fetched questions list is empty or invalid format.", None
+    except Exception as e:
+        return f"Error fetching questions: {e}", None
+
+    results_log = []
+    answers_payload = []
+
+    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:
+            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:
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+
+    if not answers_payload:
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+
+    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.')}"
+        )
+        return final_status, pd.DataFrame(results_log)
+    except Exception as e:
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+
+# --- Gradio UI ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1. Clone and customize your agent logic.
+        2. Log in with Hugging Face.
+        3. Click the button to run evaluation and submit your answers.
+        """
+    )
+    gr.LoginButton()
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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("Launching Gradio Interface...")
+    demo.launch(debug=True, share=False)