Update app.py

app.py

@@ -18,6 +18,12 @@ from langchain_community.embeddings import OllamaEmbeddings
 from langchain.embeddings import FastEmbedEmbeddings
 from langchain_community.document_loaders import PyPDFDirectoryLoader
 
+# JB:
+# File Directory
+# This covers how to load all documents in a directory.
+# Under the hood, by default this uses the UnstructuredLoader.
+from langchain_community.document_loaders import DirectoryLoader
+
 from langchain_community.vectorstores import FAISS
 # from langchain.vectorstores import Chroma
 # from langchain_community.vectorstores import Chroma
@@ -84,7 +90,9 @@ if "vector" not in st.session_state:
     # JB:
     # https://python.langchain.com/docs/modules/data_connection/document_loaders/file_directory
     text_loader_kwargs={'autodetect_encoding': True}
-    loader = DirectoryLoader(path, glob="**/*.pdf", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)
+    # loader = DirectoryLoader(path, glob="**/*.pdf", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)
+    # PyPDFDirectoryLoader (TEST):
+    loader = PyPDFDirectoryLoader(path, glob="**/*.pdf", loader_cls=TextLoader, loader_kwargs=text_loader_kwargs)
     docs = loader.load()
     st.session_state.docs = docs