Update app.py

app.py

@@ -5,9 +5,10 @@ import os
 from dotenv import load_dotenv
 from datetime import datetime
 import zipfile
-from langchain.llms import HuggingFaceHub
 from langchain.chains import ConversationChain
 from langchain.memory import ConversationBufferMemory
+from langchain.llms import HuggingFacePipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 
 # 🔓 Extract .streamlit folder if zipped
@@ -20,11 +21,17 @@ load_dotenv()
 HF_API_TOKEN = os.getenv("HF_API_TOKEN")
 
 # ✅ Initialize LangChain LLM
-llm = HuggingFaceHub(
-    repo_id="mistralai/Mistral-7B-Instruct-v0.1",
-    model_kwargs={"temperature": 0.7, "max_new_tokens": 2048},
-    huggingfacehub_api_token=HF_API_TOKEN
-)
+model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+
+# Load tokenizer and model locally
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+
+# Create Hugging Face pipeline
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=2048, temperature=0.7)
+
+# LangChain wrapper
+llm = HuggingFacePipeline(pipeline=pipe)
 
 # ✅ Setup LangChain memory and conversation
 if "memory" not in st.session_state: