Update app.py

app.py

@@ -1,16 +1,15 @@
-import os
 import streamlit as st
 from sentence_transformers import SentenceTransformer
-from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.text_splitters import RecursiveCharacterTextSplitter
 from langchain.vectorstores import FAISS
 from transformers import pipeline
 from datasets import load_dataset
 import torch
 
-# Set up the page configuration as the first Streamlit command
-st.set_page_config(page_title="RAG-based Document Chat", layout="centered", page_icon="📄")
+# Set up the Streamlit page configuration
+st.set_page_config(page_title="Gen AI Lawyers Guide", layout="centered", page_icon="📄")
 
-# Load the summarization pipeline model
+# Load summarization pipeline model
 @st.cache_resource
 def load_summarization_pipeline():
     summarizer = pipeline("summarization", model="facebook/bart-large-cnn")  # Use a summarization model
@@ -33,14 +32,18 @@ def get_text_chunks(text):
     return chunks
 
 # Initialize embedding model
-embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+@st.cache_resource
+def load_embedding_model():
+    model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+    return model
+
+embedding_model = load_embedding_model()
 
 # Create a FAISS vector store with embeddings
 @st.cache_resource
 def load_or_create_vector_store(text_chunks):
-    def embedding_function(text):
-        return embedding_model.encode(text)
-    vector_store = FAISS.from_texts(text_chunks, embedding=embedding_function)
+    embeddings = [embedding_model.encode(text) for text in text_chunks]
+    vector_store = FAISS.from_embeddings(embeddings, text_chunks)  # FAISS setup with embeddings
     return vector_store
 
 # Generate summary based on the retrieved text