Update app.py

app.py

@@ -1,101 +1,36 @@
+""" Basic Agent Evaluation Runner"""
 import os
+import inspect
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-
-
-from typing import Sequence, Annotated, TypedDict, Union
-from langgraph.graph import StateGraph, END
-from langgraph.graph.message import add_messages
-from langgraph.prebuilt import ToolNode
-from langchain_core.messages import BaseMessage, SystemMessage, HumanMessage
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_community.tools import DuckDuckGoSearchRun
-from langchain.tools import tool
-from dotenv import load_dotenv
-load_dotenv()
+from langchain_core.messages import HumanMessage
+from agent import build_graph
 
 
 
+# (Keep Constants as is)
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# ----------- Agent State -----------
-class AgentState(TypedDict):
-    messages: Annotated[Sequence[BaseMessage], add_messages]
-
-
-# ----------- Math Tools ------------
-@tool
-def add(a: int, b: int):
-    """Adds two numbers."""
-    return a + b
-
-@tool
-def subtract(a: int, b: int):
-    """Subtracts two numbers."""
-    return a - b
-
-@tool
-def multiply(a: int, b: int):
-    """Multiplies two numbers."""
-    return a * b
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 
-# ----------- DuckDuckGo Tool (LangChain built-in) -----------
-ddg_tool = DuckDuckGoSearchRun(name="duckduckgo_search")
 
-# ----------- Combine all tools -----------
-tools = [add, subtract, multiply, ddg_tool]
-
-
-# ----------- BasicAgent Class -----------
 class BasicAgent:
+    """A langgraph agent."""
     def __init__(self):
-        print("LangGraph Gemini Agent with LangChain DuckDuckGo Tool Initialized.")
-
-        self.model = ChatGoogleGenerativeAI(model="gemini-2.0-flash").bind_tools(tools)
-
-        def model_call(state: AgentState) -> AgentState:
-            system_prompt = SystemMessage(
-                content="""
-                You are an AI assistant. Use tools like math functions and web search (DuckDuckGo) to answer queries.
-                You don't have to explain or give reasons just you have to answer the question
-                Just reply the question eg.
-                if asked about what is capital of France just answer paris nothing more 
-                """
-            )
-            response = self.model.invoke([system_prompt] + state["messages"])
-            return {"messages": [response]}
-
-        def should_continue(state: AgentState):
-            last_message = state["messages"][-1]
-            if not getattr(last_message, "tool_calls", None):
-                return "end"
-            return "continue"
-
-        graph = StateGraph(AgentState)
-        graph.add_node("our_agent", model_call)
-        graph.add_node("tools", ToolNode(tools=tools))
-        graph.set_entry_point("our_agent")
-        graph.add_conditional_edges("our_agent", should_continue, {
-            "continue": "tools",
-            "end": END
-        })
-        graph.add_edge("tools", "our_agent")
-
-        self.agent = graph.compile()
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
-    def __call__(self, query: Union[str, Sequence[BaseMessage]]) -> str:
-        if isinstance(query, str):
-            messages = [HumanMessage(content=query)]
-        elif isinstance(query, list):
-            messages = query
-        else:
-            raise ValueError("Invalid input: Must be a string or list of messages.")
+    def __call__(self, question: str) -> str:
+        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:]
 
-        result = self.agent.invoke({"messages": messages})
-        last_message = result["messages"][-1]
-        return last_message.content if hasattr(last_message, "content") else str(last_message)
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """