Update app.py

app.py

@@ -10,6 +10,9 @@ from langchain.document_loaders import PyPDFLoader
 import os
 import tempfile
 
+
+
+
 def initialize_session_state():
     if 'history' not in st.session_state:
         st.session_state['history'] = []
@@ -50,23 +53,19 @@ def display_chat_history(chain):
 def create_conversational_chain(vector_store):
     # Create llm
     llm = LlamaCpp(
-        streaming=True,
-        model_path="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
-        temperature=0.75,
-        top_p=1, 
-        verbose=True,
-        n_ctx=4096,
-        device='cuda'  # Specify GPU device
-    )
+    streaming = True,
+    model_path="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
+    temperature=0.75,
+    top_p=1, 
+    verbose=True,
+    n_ctx=4096
+)
     
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
 
-    chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        chain_type='stuff',
-        retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
-        memory=memory
-    )
+    chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
+                                                 retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
+                                                 memory=memory)
     return chain
 
 def main():
@@ -77,6 +76,7 @@ def main():
     st.sidebar.title("Document Processing")
     uploaded_files = st.sidebar.file_uploader("Upload files", accept_multiple_files=True)
 
+
     if uploaded_files:
         text = []
         for file in uploaded_files:
@@ -97,18 +97,17 @@ def main():
         text_chunks = text_splitter.split_documents(text)
 
         # Create embeddings
-        embeddings = HuggingFaceEmbeddings(
-            model_name="sentence-transformers/all-MiniLM-L6-v2", 
-            model_kwargs={'device': 'cuda'}  # Use GPU for embeddings
-        )
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", 
+                                           model_kwargs={'device': 'cpu'})
 
         # Create vector store
         vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
 
         # Create the chain object
         chain = create_conversational_chain(vector_store)
+
         
         display_chat_history(chain)
 
 if __name__ == "__main__":
-    main()
+    main()