Update agent.py

agent.py

@@ -3,78 +3,66 @@ from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
 from langgraph.prebuilt import tools_condition
 from langgraph.prebuilt import ToolNode
-from langchain_community.tools.duckduckgo_search import DuckDuckGoSearchResults
+from duckduckgo_search import DDGS
 from langchain_community.document_loaders import WikipediaLoader
 from langchain_community.document_loaders import ArxivLoader
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-# .env laden (falls lokal)
 load_dotenv()
 
-# Google API Key aus Environment
 GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
 
-# --- Tools definieren ---
+# --- Tools ---
 @tool
 def multiply(a: int, b: int) -> int:
-    """Multiplies two numbers."""
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
-    """Adds two numbers."""
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
-    """Subtracts two numbers."""
     return a - b
 
 @tool
 def divide(a: int, b: int) -> float:
-    """Divides two numbers."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulo(a: int, b: int) -> int:
-    """Returns the remainder after division."""
     return a % b
 
 @tool
 def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query and return up to 2 results."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).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 search_docs
-        ]
+    formatted = "\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 search_docs]
     )
-    return {"wiki_results": formatted_search_docs}
+    return {"wiki_results": formatted}
 
 @tool
 def arxiv_search(query: str) -> str:
-    """Search Arxiv for a query and return up to 3 results."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}">\n{doc.page_content[:1000]}\n</Document>'
-            for doc in search_docs
-        ]
+    formatted = "\n\n---\n\n".join(
+        [f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}">\n{doc.page_content[:1000]}\n</Document>' for doc in search_docs]
     )
-    return {"arxiv_results": formatted_search_docs}
+    return {"arxiv_results": formatted}
 
 @tool
 def web_search(query: str) -> str:
-    """Search DuckDuckGo for a query and return results."""
-    search = DuckDuckGoSearchResults(max_results=5)
-    return search.run(query)
-
-# Tools-Liste
+    """Searches DuckDuckGo for a query."""
+    with DDGS() as ddgs:
+        results = ddgs.text(query, max_results=5)
+        if not results:
+            return "No results found."
+        return "\n\n".join(f"{r['title']}: {r['href']}" for r in results)
+
+# --- Setup LLM und Tools ---
 tools = [
     multiply,
     add,
@@ -86,7 +74,6 @@ tools = [
     web_search,
 ]
 
-# System Prompt
 system_prompt = (
     "You are a highly accurate AI assistant. "
     "Use tools when needed. Be very concise and precise. "
@@ -94,7 +81,6 @@ system_prompt = (
 )
 sys_msg = SystemMessage(content=system_prompt)
 
-# --- Build Graph ---
 def build_graph():
     llm = ChatGoogleGenerativeAI(
         model="gemini-2.0-flash",
@@ -106,7 +92,6 @@ def build_graph():
     llm_with_tools = llm.bind_tools(tools)
 
     def assistant(state: MessagesState):
-        """Assistant Node"""
         return {"messages": [llm_with_tools.invoke(state["messages"])]}
 
     builder = StateGraph(MessagesState)
@@ -118,7 +103,7 @@ def build_graph():
 
     return builder.compile()
 
-# --- Agent Executor für app.py ---
+# Agent Executor für app.py
 def agent_executor(question: str) -> str:
     graph = build_graph()
     messages = [HumanMessage(content=question)]