From 74427404cc43f27a2b0e78a2a271958c2e2f1c76 Mon Sep 17 00:00:00 2001
From: Dicklesworthstone <jeff141421@gmail.com>
Date: Wed, 29 May 2024 14:21:11 -0400
Subject: [PATCH] Added pdf2text

---
 README.md        | 2 +-
 requirements.txt | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 3f6ba77..8a74385 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ To run it natively (not using Docker) in a Python venv (recommended!), you can u
 
 ```bash
 sudo apt-get update
-sudo apt-get install libxml2-dev libxslt1-dev antiword unrtf poppler-utils pstotext tesseract-ocr flac ffmpeg lame libmad0 libsox-fmt-mp3 sox libjpeg-dev swig redis-server -y
+sudo apt-get install build-essential libxml2-dev libxslt1-dev antiword unrtf poppler-utils pstotext tesseract-ocr flac ffmpeg lame libmad0 libsox-fmt-mp3 sox libjpeg-dev swig redis-server libpoppler-cpp-dev pkg-config -y
 sudo systemctl enable redis-server
 sudo systemctl start redis
 git clone https://github.com/Dicklesworthstone/swiss_army_llama
diff --git a/requirements.txt b/requirements.txt
index 5761ce8..3b39298 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -13,6 +13,7 @@ magika
 mutagen
 nvgpu
 pandas
+pdftotext
 pillow
 psutil
 pydantic