Update app.py

app.py

@@ -3,7 +3,7 @@ from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain.llms import HuggingFaceHub
+from langchain_community.llms import HuggingFaceHub
 from langchain.chains import ConversationalRetrievalChain
 from langchain.memory import ConversationBufferMemory
 import os
@@ -13,6 +13,7 @@ import base64
 import tempfile
 import io
 from pathlib import Path
+from huggingface_hub import InferenceClient
 
 # Load environment variables
 load_dotenv()
@@ -70,12 +71,17 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db):
     """Initialize the LLM chain with correct parameters"""
     llm = HuggingFaceHub(
         repo_id=llm_model,
+        task="text-generation",
+        client=InferenceClient(
+            model=llm_model,
+            token=api_token
+        ),
         model_kwargs={
             "temperature": float(temperature),
             "max_new_tokens": int(max_tokens),
-            "top_k": int(top_k)
-        },
-        huggingfacehub_api_token=api_token
+            "top_k": int(top_k),
+            "do_sample": True
+        }
     )
 
     memory = ConversationBufferMemory(