Update app.py

app.py

@@ -6,9 +6,10 @@ import requests
 import torch
 import streamlit as st
 from langchain_huggingface import HuggingFaceEndpoint
+from langchain.llms import HuggingFacePipeline
 from langchain_core.prompts import PromptTemplate
 from langchain_core.output_parsers import StrOutputParser
-from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
 from langdetect import detect
 
 # ✅ Device setup
@@ -33,6 +34,12 @@ if "chat_history" not in st.session_state:
 # ✅ Switched to Flan-T5 Model
 MODEL_ID = "google/flan-t5-large"
 
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+
+llm = HuggingFacePipeline(pipeline=pipe)
+
 def get_llm_hf_inference(model_id=MODEL_ID, max_new_tokens=500, temperature=0.3):
     return HuggingFaceEndpoint(
         repo_id=model_id,