Update app.py

app.py

@@ -10,6 +10,8 @@ import os
 import streamlit as st
 from langchain_groq import ChatGroq
 from langchain_community.document_loaders import WebBaseLoader
+# JB:
+from langchain_community.document_loaders import PyPDFLoader
 from langchain_community.embeddings import OllamaEmbeddings
 
 # JB:
@@ -39,8 +41,14 @@ if "vector" not in st.session_state:
     st.session_state.embeddings = FastEmbedEmbeddings() # JB
 
 
-    st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html")
-    st.session_state.docs = st.session_state.loader.load()
+    # st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html") # ORIGINAL
+    # st.session_state.docs = st.session_state.loader.load()                           # ORIGINAL
+    pdf_file_path = ""                                                                 # JB
+    st.session_state.loader = PyPDFLoader(file_path=pdf_file_path).load()              # JB
+    # chunks = self.text_splitter.split_documents(docs)
+    # chunks = filter_complex_metadata(chunks)
+
+
 
     st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
     st.session_state.documents = st.session_state.text_splitter.split_documents( st.session_state.docs)