Update app.py

app.py

@@ -7,19 +7,30 @@ from langchain.llms import CTransformers
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
 import sys
+import tempfile
 # Initialize the CSVLoader to load the uploaded CSV file
 from langchain.document_loaders.csv_loader import CSVLoader
-# Allow users to upload a CSV file
-uploaded_file = st.sidebar.file_uploader("Upload your Data", type="csv")
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+from transformers import pipeline
+
+pipe = pipeline("text-generation",model="mistralai/Mistral-7B-v0.1",model_type="llama",max_new_tokens=512,temperature=0.1 )
+llm=pipe
+
+
 
 # Display the title of the web page
 st.title("Chat with CSV using open source LLM Inference Point 🦙🦜")
 # Display a markdown message with additional information
 st.markdown("<h3 style='text-align: center; color: white;'>Built by <a href='https://github.com/AIAnytime'>AI Anytime with ❤️ </a></h3>", unsafe_allow_html=True)
 
+# Allow users to upload a CSV file
+uploaded_file = st.sidebar.file_uploader("Upload your Data", type="csv")
+
 if uploaded_file:
     # Initialize the CSVLoader to load the uploaded CSV file
-    import tempfile
+
     with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
         tmp_file.write(uploaded_file.getvalue())
         tmp_file_path = tmp_file.name
@@ -103,9 +114,7 @@ docsearch.save_local(DB_FAISS_PATH)
 
 #print("Result", docs)
 
-from transformers import pipeline
 
-pipe = pipeline("text-generation",model="mistralai/Mistral-7B-v0.1",model_type="llama",max_new_tokens=512,temperature=0.1 )
 
 qa = ConversationalRetrievalChain.from_llm(llm, retriever=docsearch.as_retriever())