Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # ---------- Imports for Advanced Agent ----------
 import re
@@ -10,7 +10,6 @@ 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
-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
@@ -41,12 +40,17 @@ def arvix_search(query: str) -> str:
     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])
+    llm = AutoModelForCausalLM.from_pretrained("gpt2")  # Load Hugging Face GPT-2 model
+    tokenizer = AutoTokenizer.from_pretrained("gpt2")
 
     def assistant(state: MessagesState):
-        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+        input_text = state["messages"][-1]["content"]
+        inputs = tokenizer(input_text, return_tensors="pt")
+        outputs = llm.generate(**inputs)
+        result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return {"messages": [{"content": result}]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("assistant", assistant)
@@ -57,6 +61,7 @@ def build_tool_graph(system_prompt):
     builder.add_edge("tools", "assistant")
     return builder.compile()
 
+
 # --- Advanced BasicAgent Class ---
 class BasicAgent:
     def __init__(self):