From bc7e84b1f97cc38fb0cc5bfb817164965414688d Mon Sep 17 00:00:00 2001
From: Stan Girard <girard.stanislas@gmail.com>
Date: Sat, 13 May 2023 00:25:12 +0200
Subject: [PATCH] feat(pdf): added pdf loader

---
 files.py       | 5 +++++
 loaders/pdf.py | 6 ++++++
 main.py        | 2 ++
 3 files changed, 13 insertions(+)
 create mode 100644 loaders/pdf.py

diff --git a/files.py b/files.py
index 9018d40b2..c3e22ca1c 100644
--- a/files.py
+++ b/files.py
@@ -5,12 +5,14 @@ from loaders.txt import process_txt
 from loaders.csv import process_csv
 from loaders.markdown import process_markdown
 from utils import compute_sha1_from_content
+from loaders.pdf import process_pdf
 
 def file_uploader(supabase, openai_key, vector_store):
     file_processors = {
         ".txt": process_txt,
         ".csv": process_csv,
         ".md": process_markdown,
+        ".markdown": process_markdown,
         ".m4a": process_audio,
         ".mp3": process_audio,
         ".webm": process_audio,
@@ -18,6 +20,7 @@ def file_uploader(supabase, openai_key, vector_store):
         ".mpga": process_audio,
         ".wav": process_audio,
         ".mpeg": process_audio,
+        ".pdf": process_pdf,
     }
 
     files = st.file_uploader("Upload a file", accept_multiple_files=True, type=list(file_processors.keys()))
@@ -26,6 +29,8 @@ def file_uploader(supabase, openai_key, vector_store):
             for file in files:
                 if file_already_exists(supabase, file):
                     st.write(f"😎 {file.name} is already in the database.")
+                elif file.size < 1:
+                    st.write(f"💨 {file.name} is empty.")
                 else:
                     file_extension = os.path.splitext(file.name)[-1]
                     if file_extension in file_processors:
diff --git a/loaders/pdf.py b/loaders/pdf.py
new file mode 100644
index 000000000..846168a2e
--- /dev/null
+++ b/loaders/pdf.py
@@ -0,0 +1,6 @@
+from .common import process_file
+from langchain.document_loaders import PyPDFLoader
+
+
+def process_pdf(vector_store, file):
+    return process_file(vector_store, file, PyPDFLoader, ".pdf")
diff --git a/main.py b/main.py
index 1cfc0a37a..d134858b8 100644
--- a/main.py
+++ b/main.py
@@ -43,6 +43,8 @@ if 'chunk_overlap' not in st.session_state:
 # Create a radio button for user to choose between adding knowledge or asking a question
 user_choice = st.radio("Choose an action", ('Add Knowledge to the Brain', 'Ask a Question to the Brain'))
 
+st.markdown("---\n\n")
+
 if user_choice == 'Add Knowledge to the Brain':
     # Display chunk size and overlap selection only when adding knowledge
     st.sidebar.title("Configuration")