Update app.py

app.py

@@ -1,10 +1,7 @@
 import base64
 import os
 
-import sys
 import streamlit as st
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.llms import OpenAI
 from langchain.chains import RetrievalQA
 from langchain.document_loaders import PDFMinerLoader
 from langchain.embeddings import SentenceTransformerEmbeddings
@@ -17,8 +14,6 @@ import torch
 
 st.set_page_config(layout="wide")
 
-
-
 def process_answer(instruction, qa_chain):
     response = ''
     generated_text = qa_chain.run(instruction)
@@ -41,13 +36,11 @@ def data_ingestion():
                 loader = PDFMinerLoader(os.path.join(root, file))
 
     documents = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=500)
     splits = text_splitter.split_documents(documents)
 
-    # create embeddings of the chunked document
+    # create embeddings here
     embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
-    
-    #embeddings = OpenAIEmbeddings()
     vectordb = FAISS.from_documents(splits, embeddings)
     vectordb.save_local("faiss_index")