From 6ed7e8a0b406f6ae829aabb333ba5de112098ec3 Mon Sep 17 00:00:00 2001
From: PVBLIC Foundation <saas@pvblic.org>
Date: Tue, 21 Oct 2025 12:46:13 -0700
Subject: [PATCH] Dockerfile: Add system dependencies for Unstructured.io PDF
 processing

- Add poppler-utils for PDF processing (resolves 'pdfinfo not found' error)
- Add tesseract-ocr for OCR capabilities
- Add libmagic1 for file type detection
- These dependencies are required for full Unstructured.io functionality
---
 Dockerfile | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Dockerfile b/Dockerfile
index ad393338d8..47890d9442 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -122,6 +122,9 @@ RUN apt-get update && \
     git build-essential pandoc gcc netcat-openbsd curl jq \
     python3-dev \
     ffmpeg libsm6 libxext6 \
+    poppler-utils \
+    tesseract-ocr \
+    libmagic1 \
     && rm -rf /var/lib/apt/lists/*
 
 # install python dependencies