Update veryfinal.py

veryfinal.py

@@ -15,9 +15,8 @@ from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
 from langchain_core.tools import tool
 from langchain_groq import ChatGroq
 from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_nvidia_ai_endpoints import ChatNVIDIA
 from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
+from langchain_community.document_loaders import WikipediaLoader
 from langchain_community.vectorstores import FAISS
 from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings
 from langchain.tools.retriever import create_retriever_tool
@@ -30,7 +29,7 @@ from agno.models.groq import Groq
 from agno.models.google import Gemini
 from agno.tools.duckduckgo import DuckDuckGoTools
 from agno.memory.agent import AgentMemory
-from agno.storage.agent import AgentStorage
+from agno.storage.sqlite import SqliteStorage
 
 load_dotenv()
 
@@ -73,7 +72,7 @@ def create_agno_agents():
     """Create high-performance Agno agents"""
     
     # Storage for persistent memory
-    storage = AgentStorage(
+    storage = SqliteStorage(
         table_name="agent_sessions",
         db_file="tmp/agent_storage.db"
     )
@@ -81,7 +80,7 @@ def create_agno_agents():
     # Math specialist using Groq (fastest)
     math_agent = Agent(
         name="MathSpecialist",
-        model=GroqChat(
+        model=Groq(
             model="llama-3.3-70b-versatile",
             api_key=os.getenv("GROQ_API_KEY"),
             temperature=0
@@ -105,7 +104,7 @@ def create_agno_agents():
     # Research specialist using Gemini (most capable)
     research_agent = Agent(
         name="ResearchSpecialist",
-        model=GeminiChat(
+        model=Gemini(
             model="gemini-2.0-flash-lite",
             api_key=os.getenv("GOOGLE_API_KEY"),
             temperature=0